Bowen Chen

Ming Y. Lu, Bowen Chen, Andrew Zhang et al.

Contrastive visual language pretraining has emerged as a powerful method for either training new language-aware image encoders or augmenting existing pretrained models with zero-shot visual recognition capabilities. However, existing works typically train on large datasets of image-text pairs and have been designed to perform downstream tasks involving only small to medium sized-images, neither of which are applicable to the emerging field of computational pathology where there are limited publicly available paired image-text datasets and each image can span up to 100,000 x 100,000 pixels. In this paper we present MI-Zero, a simple and intuitive framework for unleashing the zero-shot transfer capabilities of contrastively aligned image and text models on gigapixel histopathology whole slide images, enabling multiple downstream diagnostic tasks to be carried out by pretrained encoders without requiring any additional labels. MI-Zero reformulates zero-shot transfer under the framework of multiple instance learning to overcome the computational challenge of inference on extremely large images. We used over 550k pathology reports and other available in-domain text corpora to pre-train our text encoder. By effectively leveraging strong pre-trained encoders, our best model pretrained on over 33k histopathology image-caption pairs achieves an average median zero-shot accuracy of 70.2% across three different real-world cancer subtyping tasks. Our code is available at: https://github.com/mahmoodlab/MI-Zero.

Amazon AGI, Aaron Langford, Aayush Shah et al. · amazon-science

We present Amazon Nova, a new generation of state-of-the-art foundation models that deliver frontier intelligence and industry-leading price performance. Amazon Nova Pro is a highly-capable multimodal model with the best combination of accuracy, speed, and cost for a wide range of tasks. Amazon Nova Lite is a low-cost multimodal model that is lightning fast for processing images, video, documents and text. Amazon Nova Micro is a text-only model that delivers our lowest-latency responses at very low cost. Amazon Nova Canvas is an image generation model that creates professional grade images with rich customization controls. Amazon Nova Reel is a video generation model offering high-quality outputs, customization, and motion control. Our models were built responsibly and with a commitment to customer trust, security, and reliability. We report benchmarking results for core capabilities, agentic performance, long context, functional adaptation, runtime performance, and human evaluation.

Arif Hassan Zidan, Yi Pan, Hanqi Jiang et al.

World models, internal simulators that learn the structure and dynamics of an environment, have emerged as a central paradigm in the pursuit of artificial general intelligence, enabling agents to predict, plan, and reason within learned representations. Despite rapid progress across reinforcement learning, robotics, autonomous driving, and video generation, the field lacks a unified framework integrating its diverse architectural choices, training methods, reasoning mechanisms, and application settings. This survey addresses that gap with a multi-axis taxonomy organized along four dimensions: (i) architecture, encompassing representation format, dynamics formulation, input modality, learning paradigm, and downstream application; (ii) methodological family, including state-space and recurrent approaches, transformer-based models, diffusion-based generators, physics-informed networks, and language-augmented multimodal systems; (iii) reasoning strategy, covering imagination-based planning, latent policy learning, counterfactual reasoning, and planning under uncertainty; and (iv) application domain, spanning robotics, autonomous driving, video prediction, multimodal agents, reinforcement learning, scientific modeling, medical imaging, educational measurement, and business and finance. Tracing the field from early cognitive-science foundations to milestone systems such as PlaNet, the Dreamer family, MuZero, Sora, Cosmos, and Genie, we examine how these dimensions interact and highlight the recent convergence of chain-of-thought reasoning with world-model imagination. We review evaluation protocols and benchmarks, identify persistent challenges such as compounding prediction errors, sim-to-real transfer, and fragmented evaluation, and outline future directions toward unified multimodal world models, foundation-scale interactive simulators, and safe deployment in safety-critical domains.

LLM-jp, Akiko Aizawa, Eiji Aramaki et al.

This paper introduces LLM-jp, a cross-organizational project for the research and development of Japanese large language models (LLMs). LLM-jp aims to develop open-source and strong Japanese LLMs, and as of this writing, more than 1,500 participants from academia and industry are working together for this purpose. This paper presents the background of the establishment of LLM-jp, summaries of its activities, and technical reports on the LLMs developed by LLM-jp. For the latest activities, visit https://llm-jp.nii.ac.jp/en/.

Chuyu Zhong, Keyan Chen, Qinzhe Yang et al.

Pixel count and geographical coverage are two key characteristics of remote sensing images. Existing remote sensing image segmentation methods typically focus on images with either a small pixel count or a large pixel count but limited geographical coverage. In this paper, we introduce a novel segmentation task targeting ultra-wide area (UWA) remote sensing images, characterized by both a large pixel count and extremely wide geographical coverage. The core challenges of UWA segmentation lie in simultaneously handling ground objects with significantly varying scales and maintaining long-range contextual semantic continuity. To address these challenges, we propose the Scale-Frustum Representation Network (SFR-Net). Inspired by the viewing frustums of remote sensing images captured from different altitudes, we construct scale-frustum representations, enabling unified modeling of ground objects and contextual features at different scales. Furthermore, we design a cascaded cross-scale fusion mechanism to effectively integrate these representations, enhancing local semantic understanding while ensuring long-range contextual continuity. Experimental results on GID and FBPS demonstrate that SFR-Net achieves state-of-the-art performance, improving mIoU by 1.72% and 4.29%, respectively, over the strongest competing methods. In addition, the proposed scale-frustum representations can be integrated into generic segmentation networks to improve both segmentation accuracy and convergence speed. The implementation code will be publicly available at https://github.com/ChuyuZhong/SFR-Net.

Huichao Zhang, Bowen Chen, Hao Yang et al.

Creating expressive, diverse and high-quality 3D avatars from highly customized text descriptions and pose guidance is a challenging task, due to the intricacy of modeling and texturing in 3D that ensure details and various styles (realistic, fictional, etc). We present AvatarVerse, a stable pipeline for generating expressive high-quality 3D avatars from nothing but text descriptions and pose guidance. In specific, we introduce a 2D diffusion model conditioned on DensePose signal to establish 3D pose control of avatars through 2D images, which enhances view consistency from partially observed scenarios. It addresses the infamous Janus Problem and significantly stablizes the generation process. Moreover, we propose a progressive high-resolution 3D synthesis strategy, which obtains substantial improvement over the quality of the created 3D avatars. To this end, the proposed AvatarVerse pipeline achieves zero-shot 3D modeling of 3D avatars that are not only more expressive, but also in higher quality and fidelity than previous works. Rigorous qualitative evaluations and user studies showcase AvatarVerse's superiority in synthesizing high-fidelity 3D avatars, leading to a new standard in high-quality and stable 3D avatar creation. Our project page is: https://avatarverse3d.github.io

Richard J. Chen, Tong Ding, Ming Y. Lu et al.

Tissue phenotyping is a fundamental computational pathology (CPath) task in learning objective characterizations of histopathologic biomarkers in anatomic pathology. However, whole-slide imaging (WSI) poses a complex computer vision problem in which the large-scale image resolutions of WSIs and the enormous diversity of morphological phenotypes preclude large-scale data annotation. Current efforts have proposed using pretrained image encoders with either transfer learning from natural image datasets or self-supervised pretraining on publicly-available histopathology datasets, but have not been extensively developed and evaluated across diverse tissue types at scale. We introduce UNI, a general-purpose self-supervised model for pathology, pretrained using over 100 million tissue patches from over 100,000 diagnostic haematoxylin and eosin-stained WSIs across 20 major tissue types, and evaluated on 33 representative CPath clinical tasks in CPath of varying diagnostic difficulties. In addition to outperforming previous state-of-the-art models, we demonstrate new modeling capabilities in CPath such as resolution-agnostic tissue classification, slide classification using few-shot class prototypes, and disease subtyping generalization in classifying up to 108 cancer types in the OncoTree code classification system. UNI advances unsupervised representation learning at scale in CPath in terms of both pretraining data and downstream evaluation, enabling data-efficient AI models that can generalize and transfer to a gamut of diagnostically-challenging tasks and clinical workflows in anatomic pathology.

Ming Y. Lu, Bowen Chen, Drew F. K. Williamson et al.

The accelerated adoption of digital pathology and advances in deep learning have enabled the development of powerful models for various pathology tasks across a diverse array of diseases and patient cohorts. However, model training is often difficult due to label scarcity in the medical domain and the model's usage is limited by the specific task and disease for which it is trained. Additionally, most models in histopathology leverage only image data, a stark contrast to how humans teach each other and reason about histopathologic entities. We introduce CONtrastive learning from Captions for Histopathology (CONCH), a visual-language foundation model developed using diverse sources of histopathology images, biomedical text, and notably over 1.17 million image-caption pairs via task-agnostic pretraining. Evaluated on a suite of 13 diverse benchmarks, CONCH can be transferred to a wide range of downstream tasks involving either or both histopathology images and text, achieving state-of-the-art performance on histology image classification, segmentation, captioning, text-to-image and image-to-text retrieval. CONCH represents a substantial leap over concurrent visual-language pretrained systems for histopathology, with the potential to directly facilitate a wide array of machine learning-based workflows requiring minimal or no further supervised fine-tuning.

Xiaohua Wang, Muzhao Tian, Yuqi Zeng et al.

Reinforcement Learning from Human Feedback (RLHF) and related alignment paradigms have become central to steering large language models (LLMs) and multimodal large language models (MLLMs) toward human-preferred behaviors. However, these approaches introduce a systemic vulnerability: reward hacking, where models exploit imperfections in learned reward signals to maximize proxy objectives without fulfilling true task intent. As models scale and optimization intensifies, such exploitation manifests as verbosity bias, sycophancy, hallucinated justification, benchmark overfitting, and, in multimodal settings, perception--reasoning decoupling and evaluator manipulation. Recent evidence further suggests that seemingly benign shortcut behaviors can generalize into broader forms of misalignment, including deception and strategic gaming of oversight mechanisms. In this survey, we propose the Proxy Compression Hypothesis (PCH) as a unifying framework for understanding reward hacking. We formalize reward hacking as an emergent consequence of optimizing expressive policies against compressed reward representations of high-dimensional human objectives. Under this view, reward hacking arises from the interaction of objective compression, optimization amplification, and evaluator--policy co-adaptation. This perspective unifies empirical phenomena across RLHF, RLAIF, and RLVR regimes, and explains how local shortcut learning can generalize into broader forms of misalignment, including deception and strategic manipulation of oversight mechanisms. We further organize detection and mitigation strategies according to how they intervene on compression, amplification, or co-adaptation dynamics. By framing reward hacking as a structural instability of proxy-based alignment under scale, we highlight open challenges in scalable oversight, multimodal grounding, and agentic autonomy.

Andrew H. Song, Mane Williams, Drew F. K. Williamson et al.

Human tissue and its constituent cells form a microenvironment that is fundamentally three-dimensional (3D). However, the standard-of-care in pathologic diagnosis involves selecting a few two-dimensional (2D) sections for microscopic evaluation, risking sampling bias and misdiagnosis. Diverse methods for capturing 3D tissue morphologies have been developed, but they have yet had little translation to clinical practice; manual and computational evaluations of such large 3D data have so far been impractical and/or unable to provide patient-level clinical insights. Here we present Modality-Agnostic Multiple instance learning for volumetric Block Analysis (MAMBA), a deep-learning-based platform for processing 3D tissue images from diverse imaging modalities and predicting patient outcomes. Archived prostate cancer specimens were imaged with open-top light-sheet microscopy or microcomputed tomography and the resulting 3D datasets were used to train risk-stratification networks based on 5-year biochemical recurrence outcomes via MAMBA. With the 3D block-based approach, MAMBA achieves an area under the receiver operating characteristic curve (AUC) of 0.86 and 0.74, superior to 2D traditional single-slice-based prognostication (AUC of 0.79 and 0.57), suggesting superior prognostication with 3D morphological features. Further analyses reveal that the incorporation of greater tissue volume improves prognostic performance and mitigates risk prediction variability from sampling bias, suggesting the value of capturing larger extents of heterogeneous 3D morphology. With the rapid growth and adoption of 3D spatial biology and pathology techniques by researchers and clinicians, MAMBA provides a general and efficient framework for 3D weakly supervised learning for clinical decision support and can help to reveal novel 3D morphological biomarkers for prognosis and therapeutic response.

Qian Da, Yijiang Chen, Min Ju et al.

Recent breakthroughs in artificial intelligence through foundation models and agents have accelerated the evolution of computational pathology. Demonstrated performance gains reported across academia in benchmarking datasets in predictive tasks such as diagnosis, prognosis, and treatment response have ignited substantial enthusiasm for clinical application. Despite this development momentum, real world adoption has lagged, as implementation faces economic, technical, and administrative challenges. Beyond existing discussions of technical architectures and comparative performance, this review considers how these emerging AI systems can be responsibly integrated into medical practice by connecting deployable clinical relevance with downstream analytical capabilities and their technical maturity, operational readiness, and economic and regulatory context. Drawing on perspectives from an international group, we provide a practical assessment of current capabilities and barriers to adoption in patient care settings.

Keyan Chen, Bowen Chen, Chenyang Liu et al.

Remote sensing image classification forms the foundation of various understanding tasks, serving a crucial function in remote sensing image interpretation. The recent advancements of Convolutional Neural Networks (CNNs) and Transformers have markedly enhanced classification accuracy. Nonetheless, remote sensing scene classification remains a significant challenge, especially given the complexity and diversity of remote sensing scenarios and the variability of spatiotemporal resolutions. The capacity for whole-image understanding can provide more precise semantic cues for scene discrimination. In this paper, we introduce RSMamba, a novel architecture for remote sensing image classification. RSMamba is based on the State Space Model (SSM) and incorporates an efficient, hardware-aware design known as the Mamba. It integrates the advantages of both a global receptive field and linear modeling complexity. To overcome the limitation of the vanilla Mamba, which can only model causal sequences and is not adaptable to two-dimensional image data, we propose a dynamic multi-path activation mechanism to augment Mamba's capacity to model non-causal data. Notably, RSMamba maintains the inherent modeling mechanism of the vanilla Mamba, yet exhibits superior performance across multiple remote sensing image classification datasets. This indicates that RSMamba holds significant potential to function as the backbone of future visual foundation models. The code will be available at \url{https://github.com/KyanChen/RSMamba}.

Haoyu Ji, Bowen Chen, Zhihao Yang et al.

Skeleton-based Temporal Action Segmentation (STAS) seeks to densely segment and classify diverse actions within long, untrimmed skeletal motion sequences. However, existing STAS methodologies face challenges of limited inter-class discriminability and blurred segmentation boundaries, primarily due to insufficient distinction of spatio-temporal patterns between adjacent actions. To address these limitations, we propose Spectral Scalpel, a frequency-selective filtering framework aimed at suppressing shared frequency components between adjacent distinct actions while amplifying their action-specific frequencies, thereby enhancing inter-action discrepancies and sharpening transition boundaries. Specifically, Spectral Scalpel employs adaptive multi-scale spectral filters as scalpels to edit frequency spectra, coupled with a discrepancy loss between adjacent actions serving as the surgical objective. This design amplifies representational disparities between neighboring actions, effectively mitigating boundary localization ambiguities and inter-class confusion. Furthermore, complementing long-term temporal modeling, we introduce a frequency-aware channel mixer to strengthen channel evolution by aggregating spectra across channels. This work presents a novel paradigm for STAS that extends conventional spatio-temporal modeling by incorporating frequency-domain analysis. Extensive experiments on five public datasets demonstrate that Spectral Scalpel achieves state-of-the-art performance. Code is available at https://github.com/HaoyuJi/SpecScalpel.

Yuan Xie, Jiaqi Song, Guang Qiu et al.

Integrating large language models (LLMs) into automatic speech recognition (ASR) has become a mainstream paradigm in recent years. Although existing LLM-based ASR models demonstrate impressive performance on public benchmarks, their training remains predominantly data-driven, leaving key practical challenges insufficiently addressed -- particularly limited downward scalability in resource-constrained deployments and hallucinations under acoustically challenging conditions. To address these issues, we present NIM4-ASR, a production-oriented LLM-based ASR framework optimized for both efficiency and robustness. Grounded in a principled delineation of functional roles between the encoder and the LLM, we redesign the multi-stage training paradigm to align each module with its intended capability boundary. Specifically, we reformulate the pre-training architecture and objective to mitigate the modality gap and improve parameter efficiency; introduce an iterative asynchronous SFT stage to preserve acoustic fidelity and constrain representation drift; and design an ASR-specialized reinforcement learning stage to further enhance recognition quality and robustness. We additionally incorporate a suite of production-oriented optimizations, including robustness under noisy and silent conditions, real-time streaming inference, and hotword customization via retrieval-augmented generation (RAG). Experiments show that NIM4-ASR achieves state-of-the-art performance on multiple public benchmarks with merely 2.3B parameters, while substantially outperforming larger-scale competitors on internal benchmarks -- particularly in entity-intensive real-world scenarios. NIM4-ASR further supports million-scale hotword customization via RAG with sub-millisecond retrieval latency, enabling efficient adaptation to emerging entities and personalized user requirements.

Chenyang Liu, Keyan Chen, Bowen Chen et al.

Remote Sensing Image Change Captioning (RSICC) aims to describe surface changes between multi-temporal remote sensing images in language, including the changed object categories, locations, and dynamics of changing objects (e.g., added or disappeared). This poses challenges to spatial and temporal modeling of bi-temporal features. Despite previous methods progressing in the spatial change perception, there are still weaknesses in joint spatial-temporal modeling. To address this, in this paper, we propose a novel RSCaMa model, which achieves efficient joint spatial-temporal modeling through multiple CaMa layers, enabling iterative refinement of bi-temporal features. To achieve efficient spatial modeling, we introduce the recently popular Mamba (a state space model) with a global receptive field and linear complexity into the RSICC task and propose the Spatial Difference-aware SSM (SD-SSM), overcoming limitations of previous CNN- and Transformer-based methods in the receptive field and computational complexity. SD-SSM enhances the model's ability to capture spatial changes sharply. In terms of efficient temporal modeling, considering the potential correlation between the temporal scanning characteristics of Mamba and the temporality of the RSICC, we propose the Temporal-Traversing SSM (TT-SSM), which scans bi-temporal features in a temporal cross-wise manner, enhancing the model's temporal understanding and information interaction. Experiments validate the effectiveness of the efficient joint spatial-temporal modeling and demonstrate the outstanding performance of RSCaMa and the potential of the Mamba in the RSICC task. Additionally, we systematically compare three different language decoders, including Mamba, GPT-style decoder, and Transformer decoder, providing valuable insights for future RSICC research. The code will be available at \emph{\url{https://github.com/Chen-Yang-Liu/RSCaMa}}

Bowen Chen, Xiao Ding, Li Du et al.

Given a task, human learns from easy to hard, whereas the model learns randomly. Undeniably, difficulty insensitive learning leads to great success in NLP, but little attention has been paid to the effect of text difficulty in NLP. In this research, we propose the Human Learning Matching Index (HLM Index) to investigate the effect of text difficulty. Experiment results show: (1) LSTM has more human-like learning behavior than BERT. (2) UID-SuperLinear gives the best evaluation of text difficulty among four text difficulty criteria. (3) Among nine tasks, some tasks' performance is related to text difficulty, whereas some are not. (4) Model trained on easy data performs best in easy and medium data, whereas trains on a hard level only perform well on hard data. (5) Training the model from easy to hard leads to fast convergence.

Shreshth Saini, Bowen Chen, Neil Birkbeck et al.

High Dynamic Range (HDR) user-generated (UGC) videos are rapidly proliferating across social platforms, yet most perceptual video quality assessment (VQA) systems remain tailored to Standard Dynamic Range (SDR). HDR has a higher bit depth, wide color gamut, and elevated luminance range, exposing distortions such as near-black crushing, highlight clipping, banding, and exposure flicker that amplify UGC artifacts and challenge SDR models. To catalyze progress, we curate Beyond8Bits, a large-scale subjective dataset of 44K videos from 6.5K sources with over 1.5M crowd ratings, spanning diverse scenes, capture conditions, and compression settings. We further introduce HDR-Q, the first Multimodal Large Language Model (MLLM) for HDR-UGC VQA. We propose (i) a novel HDR-aware vision encoder to produce HDR-sensitive embeddings, and (ii) HDR-Aware Policy Optimization (HAPO), an RL finetuning framework that anchors reasoning to HDR cues. HAPO augments GRPO via an HDR-SDR contrastive KL that encourages token reliance on HDR inputs and a Gaussian weighted regression reward for fine-grained MOS calibration. Across Beyond8Bits and public HDR-VQA benchmarks, HDR-Q delivers state-of-the-art performance.

Bowen Chen, Jayesh Gajbhar, Gregory Dusek et al.

Artificial intelligence is transforming the sciences, yet general conversational AI systems often generate unverified "hallucinations" undermining scientific rigor. We present OceanAI, a conversational platform that integrates the natural-language fluency of open-source large language models (LLMs) with real-time, parameterized access to authoritative oceanographic data streams hosted by the National Oceanic and Atmospheric Administration (NOAA). Each query such as "What was Boston Harbor's highest water level in 2024?" triggers real-time API calls that identify, parse, and synthesize relevant datasets into reproducible natural-language responses and data visualizations. In a blind comparison with three widely used AI chat-interface products, only OceanAI produced NOAA-sourced values with original data references; others either declined to answer or provided unsupported results. Designed for extensibility, OceanAI connects to multiple NOAA data products and variables, supporting applications in marine hazard forecasting, ecosystem assessment, and water-quality monitoring. By grounding outputs and verifiable observations, OceanAI advances transparency, reproducibility, and trust, offering a scalable framework for AI-enabled decision support within the oceans. A public demonstration is available at https://oceanai.ai4ocean.xyz.

Pan Lu, Bowen Chen, Sheng Liu et al. · stanford

Solving complex reasoning tasks may involve visual understanding, domain knowledge retrieval, numerical calculation, and multi-step reasoning. Existing methods augment large language models (LLMs) with external tools but are restricted to specialized domains, limited tool types, or require additional training data. In this paper, we introduce OctoTools, a training-free, user-friendly, and easily extensible open-source agentic framework designed to tackle complex reasoning across diverse domains. OctoTools introduces standardized tool cards to encapsulate tool functionality, a planner for both high-level and low-level planning, and an executor to carry out tool usage. We validate OctoTools' generality across 16 diverse tasks (including MathVista, MMLU-Pro, MedQA, and GAIA-Text), achieving substantial average accuracy gains of 9.3% over GPT-4o. Furthermore, OctoTools outperforms AutoGen, GPT-Functions and LangChain by up to 10.6% when given the same set of tools. Through comprehensive analysis and ablations, OctoTools demonstrates advantages in task planning, effective tool usage, and multi-step problem solving.

Zihao Wu, Steven Xu, Bowen Chen et al.

With the emergence of large language models (LLMs) and AI agent frameworks, the human-AI co-work paradigm known as Vibe Coding is changing how people code, making it more accessible and productive. In scientific research, where workflows are more complex and the burden of specialized labor limits independent researchers and those in low-resource areas, the potential impact is even greater, particularly in biomedicine, which involves heterogeneous data modalities and multi-step analytical pipelines. In this paper, we introduce Vibe Medicine, a co-work paradigm in which clinicians and researchers direct skill-augmented AI agents through natural language to execute complex, multi-step biomedical workflows, while retaining the role of research director who specifies objectives, reviews intermediate results, and makes domain-informed decisions. The enabling infrastructure consists of three layers: capable LLMs, agent frameworks such as OpenClaw and Hermes Agent, and the OpenClaw medical skills collection, which includes more than 1,000 curated skills from multiple open-source repositories. We analyze the architecture and skill categories of this collection across ten biomedical domains, and present case studies covering rare disease diagnosis, drug repurposing, and clinical trial design that demonstrate end-to-end workflows in practice. We also identify the principal risks, such as hallucination, data privacy, and over-reliance, and outline directions toward more reliable, trustworthy, and clinically integrated agent-assisted research that advances research and technological equity and reduces health care resource disparities.

Bowen Chen, Keyan Chen, Mohan Yang et al.

Remote sensing image super-resolution (SR) aims to reconstruct high-resolution remote sensing images from low-resolution inputs, thereby addressing limitations imposed by sensors and imaging conditions. However, the inherent characteristics of remote sensing images, including diverse ground object types and complex details, pose significant challenges to achieving high-quality reconstruction. Existing methods typically employ a uniform structure to process various types of ground objects without distinction, making it difficult to adapt to the complex characteristics of remote sensing images. To address this issue, we introduce a Mixture of Experts (MoE) model and design a set of heterogeneous experts. These experts are organized into multiple expert groups, where experts within each group are homogeneous while being heterogeneous across groups. This design ensures that specialized activation parameters can be employed to handle the diverse and intricate details of ground objects effectively. To better accommodate the heterogeneous experts, we propose a multi-level feature aggregation strategy to guide the routing process. Additionally, we develop a dual-routing mechanism to adaptively select the optimal expert for each pixel. Experiments conducted on the UCMerced and AID datasets demonstrate that our proposed method achieves superior SR reconstruction accuracy compared to state-of-the-art methods. The code will be available at https://github.com/Mr-Bamboo/MFG-HMoE.

Bowen Chen, Cheng-han Lee, Yixu Chen et al.

We introduce HDRSDR-VQA, a large-scale video quality assessment dataset designed to facilitate comparative analysis between High Dynamic Range (HDR) and Standard Dynamic Range (SDR) content under realistic viewing conditions. The dataset comprises 960 videos generated from 54 diverse source sequences, each presented in both HDR and SDR formats across nine distortion levels. To obtain reliable perceptual quality scores, we conducted a comprehensive subjective study involving 145 participants and six consumer-grade HDR-capable televisions. A total of over 22,000 pairwise comparisons were collected and scaled into Just-Objectionable-Difference (JOD) scores. Unlike prior datasets that focus on a single dynamic range format or use limited evaluation protocols, HDRSDR-VQA enables direct content-level comparison between HDR and SDR versions, supporting detailed investigations into when and why one format is preferred over the other. The open-sourced part of the dataset is publicly available to support further research in video quality assessment, content-adaptive streaming, and perceptual model development.

Keyan Chen, Chenyang Liu, Bowen Chen et al.

Referring Remote Sensing Image Segmentation provides a flexible and fine-grained framework for remote sensing scene analysis via vision-language collaborative interpretation. Current approaches predominantly utilize a three-stage pipeline encompassing dual-modal encoding, cross-modal interaction, and pixel decoding. These methods demonstrate significant limitations in managing complex semantic relationships and achieving precise cross-modal alignment, largely due to their coupled processing mechanism that conflates target localization with boundary delineation. This architectural coupling amplifies error propagation under semantic ambiguity while restricting model generalizability and interpretability. To address these issues, we propose RSRefSeg 2, a decoupling paradigm that reformulates the conventional workflow into a collaborative dual-stage framework: coarse localization followed by fine segmentation. RSRefSeg 2 integrates CLIP's cross-modal alignment strength with SAM's segmentation generalizability through strategic foundation model collaboration. Specifically, CLIP is employed as the dual-modal encoder to activate target features within its pre-aligned semantic space and generate localization prompts. To mitigate CLIP's misactivation challenges in multi-entity scenarios described by referring texts, a cascaded second-order prompter is devised, which enhances precision through implicit reasoning via decomposition of text embeddings into complementary semantic subspaces. These optimized semantic prompts subsequently direct the SAM to generate pixel-level refined masks, thereby completing the semantic transmission pipeline. Extensive experiments (RefSegRS, RRSIS-D, and RISBench) demonstrate that RSRefSeg 2 surpasses contemporary methods in segmentation accuracy (+~3% gIoU) and complex semantic interpretation. Code is available at: https://github.com/KyanChen/RSRefSeg2.

Kai Zhang, Bowen Chen

The unprecedented increase of commercial airlines and private jets over the next ten years presents a challenge for air traffic control. Precise flight trajectory prediction is of great significance in air transportation management, which contributes to the decision-making for safe and orderly flights. Existing research and application mainly focus on the sequence generation based on historical trajectories, while the aircraft-aircraft interactions in crowded airspace especially the airspaces near busy airports have been largely ignored. On the other hand, there are distinct characteristics of aerodynamics for different flight phases, and the trajectory may be affected by various uncertainties such as weather and advisories from air traffic controllers. However, there is no literature fully considers all these issues. Therefore, we proposed a phased flight trajectory prediction framework. Multi-source and multi-modal datasets have been analyzed and mined using variants of recurrent neural network (RNN) mixture. To be specific, we first introduce spatio temporal graphs into the low-altitude airway prediction problem, and the motion constraints of an aircraft are embedded to the inference process for reliable forecasting results. In the en-route phase, the dual attention mechanism is employed to adaptively extract much more important features from overall datasets to learn the hidden patterns in dynamical environments. The experimental results demonstrate our proposed framework can outperform state-of-the-art methods for flight trajectory prediction for large passenger/transport airplanes.

Bowen Chen, Namgi Han, Yusuke Miyao

Memorization is a fundamental component of intelligence for both humans and LLMs. However, while LLM performance scales rapidly, our understanding of memorization lags. Due to limited access to the pre-training data of LLMs, most previous studies focus on a single model series, leading to isolated observations among series, making it unclear which findings are general or specific. In this study, we collect multiple model series (Pythia, OpenLLaMa, StarCoder, OLMo1/2/3) and analyze their shared or unique memorization behavior at both the statistical and internal levels, connecting individual observations while showing new findings. At the statistical level, we reveal that the memorization rate scales log-linearly with model size, and memorized sequences can be further compressed. Further analysis demonstrated a shared frequency and domain distribution pattern for memorized sequences. However, different models also show individual features under the above observations. At the internal level, we find that LLMs can remove certain injected perturbations, while memorized sequences are more sensitive. By decoding middle layers and attention head ablation, we revealed the general decoding process and shared important heads for memorization. However, the distribution of those important heads differs between families, showing a unique family-level feature. Through bridging various experiments and revealing new findings, this study paves the way for a universal and fundamental understanding of memorization in LLM.

Powei Chang, Jinpeng Zhang, Bowen Chen et al.

Information-based data selection for instruction tuning is compelling: maximizing the log-determinant of the Fisher information yields a monotone submodular objective, enabling greedy algorithms to achieve a $(1-1/e)$ approximation under a cardinality budget. In practice, however, we identify alleviating gradient conflicts, misalignment between per-sample gradients, is a key factor that slows down the decay of marginal log-determinant information gains, thereby preventing significant loss of information. We formalize this via an $\varepsilon$-decomposition that quantifies the deviation from ideal submodularity as a function of conflict statistics, yielding data-dependent approximation factors that tighten as conflicts diminish. Guided by this analysis, we propose SPICE, a conflict-aware selector that maximizes information while penalizing misalignment, and that supports early stopping and proxy models for efficiency. Empirically, SPICE selects subsets with higher log-determinant information than original criteria, and these informational gains translate into performance improvements: across 8 benchmarks with LLaMA2-7B and Qwen2-7B, SPICE uses only 10% of the data, yet matches or exceeds 6 methods including full-data tuning. This achieves performance improvements with substantially lower training cost.

ZhaoYang Han, Qihan Lin, Hao Liang et al.

We introduce \textbf{LongInsightBench}, the first benchmark designed to assess models' ability to understand long videos, with a focus on human language, viewpoints, actions, and other contextual elements, while integrating \textbf{visual, audio, and text} modalities. Our benchmark excels in three key areas: \textbf{a) Long-Duration, Information-Dense Videos:} We carefully select approximately 1,000 videos from open-source datasets FineVideo based on duration limit and the information density of both visual and audio modalities, focusing on content like lectures, interviews, and vlogs, which contain rich language elements. \textbf{b) Diverse and Challenging Task Scenarios:} We have designed six challenging task scenarios, including both Intra-Event and Inter-Event Tasks. \textbf{c) Rigorous and Comprehensive Quality Assurance Pipelines:} We have developed a three-step, semi-automated data quality assurance pipeline to ensure the difficulty and validity of the synthesized questions and answer options. Based on LongInsightBench, we designed a series of experiments. Experimental results shows that Omni-modal models(OLMs) still face challenge in tasks requiring precise temporal localization (T-Loc) and long-range causal inference (CE-Caus). Extended experiments reveal the information loss and processing bias in multi-modal fusion of OLMs. Our dataset and code is available at https://anonymous.4open.science/r/LongInsightBench-910F/.

Tong Ding, Sophia J. Wagner, Andrew H. Song et al.

The field of computational pathology has been transformed with recent advances in foundation models that encode histopathology region-of-interests (ROIs) into versatile and transferable feature representations via self-supervised learning (SSL). However, translating these advancements to address complex clinical challenges at the patient and slide level remains constrained by limited clinical data in disease-specific cohorts, especially for rare clinical conditions. We propose TITAN, a multimodal whole slide foundation model pretrained using 335,645 WSIs via visual self-supervised learning and vision-language alignment with corresponding pathology reports and 423,122 synthetic captions generated from a multimodal generative AI copilot for pathology. Without any finetuning or requiring clinical labels, TITAN can extract general-purpose slide representations and generate pathology reports that generalize to resource-limited clinical scenarios such as rare disease retrieval and cancer prognosis. We evaluate TITAN on diverse clinical tasks and find that TITAN outperforms both ROI and slide foundation models across machine learning settings such as linear probing, few-shot and zero-shot classification, rare cancer retrieval and cross-modal retrieval, and pathology report generation.

Ming Y. Lu, Bowen Chen, Drew F. K. Williamson et al.

The field of computational pathology has witnessed remarkable progress in the development of both task-specific predictive models and task-agnostic self-supervised vision encoders. However, despite the explosive growth of generative artificial intelligence (AI), there has been limited study on building general purpose, multimodal AI assistants tailored to pathology. Here we present PathChat, a vision-language generalist AI assistant for human pathology using an in-house developed foundational vision encoder pretrained on 100 million histology images from over 100,000 patient cases and 1.18 million pathology image-caption pairs. The vision encoder is then combined with a pretrained large language model and the whole system is finetuned on over 250,000 diverse disease agnostic visual language instructions. We compare PathChat against several multimodal vision language AI assistants as well as GPT4V, which powers the commercially available multimodal general purpose AI assistant ChatGPT-4. When relevant clinical context is provided with the histology image, PathChat achieved a diagnostic accuracy of 87% on multiple-choice questions based on publicly available cases of diverse tissue origins and disease models. Additionally, using open-ended questions and human expert evaluation, we found that overall PathChat produced more accurate and pathologist-preferable responses to diverse queries related to pathology. As an interactive and general vision language AI assistant that can flexibly handle both visual and natural language inputs, PathChat can potentially find impactful applications in pathology education, research, and human-in-the-loop clinical decision making.

Bowen Chen, Jake Zuena, Alan C. Bovik et al.

Precise spatial control in diffusion-based style transfer remains challenging. This challenge arises because diffusion models treat style as a global feature and lack explicit spatial grounding of style representations, making it difficult to restrict style application to specific objects or regions. To our knowledge, existing diffusion models are unable to perform true localized style transfer, typically relying on handcrafted masks or multi-stage post-processing that introduce boundary artifacts and limit generalization. To address this, we propose an attention-supervised diffusion framework that explicitly teaches the model where to apply a given style by aligning the attention scores of style tokens with object masks during training. Two complementary objectives, a Focus loss based on KL divergence and a Cover loss using binary cross-entropy, jointly encourage accurate localization and dense coverage. A modular LoRA-MoE design further enables efficient and scalable multi-style adaptation. To evaluate localized stylization, we introduce the Regional Style Editing Score, which measures Regional Style Matching through CLIP-based similarity within the target region and Identity Preservation via masked LPIPS and pixel-level consistency on unedited areas. Experiments show that our method achieves mask-free, single-object style transfer at inference, producing regionally accurate and visually coherent results that outperform existing diffusion-based editing approaches.

Keyan Chen, Chenyang Liu, Bowen Chen et al.

The advancement of remote sensing technology has improved the spatial resolution of satellite imagery, facilitating more detailed visual representations for diverse interpretations. However, existing methods exhibit limited generalization capabilities across varied applications. While some contemporary foundation models demonstrate potential, they are hindered by insufficient cross-task adaptability and primarily process low-resolution imagery of restricted sizes, thus failing to fully exploit high-resolution data or leverage comprehensive large-scene semantics. Crucially, remote sensing imagery differs fundamentally from natural images, as key foreground targets (eg., maritime objects, artificial structures) often occupy minimal spatial proportions (~1%) and exhibit sparse distributions. Efficiently modeling cross-task generalizable knowledge from lengthy 2D tokens (~100,000) poses a significant challenge yet remains critical for remote sensing image understanding. Motivated by the selective attention mechanisms inherent to the human visual system, we propose DynamicVis, a dynamic visual perception foundation model for remote sensing imagery. The framework integrates a novel dynamic region perception backbone based on the selective state space model, which strategically balances localized detail extraction with global contextual integration, enabling computationally efficient encoding of large-scale data while maintaining architectural scalability. To enhance cross-task knowledge transferring, we introduce a multi-instance learning paradigm utilizing meta-embedding representations, trained on million-scale region-level annotations. Evaluations across nine downstream tasks demonstrate the model's versatility. DynamicVis achieves multi-level feature modeling with exceptional efficiency, processing (2048x2048) pixels with 97 ms latency (6% of ViT's) and 833 MB GPU memory (3% of ViT's).

Bowen Chen, Mengyi Zhao, Haomiao Sun et al.

Achieving fine-grained control over subject identity and semantic attributes (pose, style, lighting) in text-to-image generation, particularly for multiple subjects, often undermines the editability and coherence of Diffusion Transformers (DiTs). Many approaches introduce artifacts or suffer from attribute entanglement. To overcome these challenges, we propose a novel multi-subject controlled generation model XVerse. By transforming reference images into offsets for token-specific text-stream modulation, XVerse allows for precise and independent control for specific subject without disrupting image latents or features. Consequently, XVerse offers high-fidelity, editable multi-subject image synthesis with robust control over individual subject characteristics and semantic attributes. This advancement significantly improves personalized and complex scene generation capabilities.

Hejie Cui, Alyssa Unell, Bowen Chen et al. · stanford

Large language models (LLMs) have emerged as promising tools for assisting in medical tasks, yet processing Electronic Health Records (EHRs) presents unique challenges due to their longitudinal nature. While LLMs' capabilities to perform medical tasks continue to improve, their ability to reason over temporal dependencies across multiple patient visits and time frames remains unexplored. We introduce TIMER (Temporal Instruction Modeling and Evaluation for Longitudinal Clinical Records), a framework that incorporate instruction-response pairs grounding to different parts of a patient's record as a critical dimension in both instruction evaluation and tuning for longitudinal clinical records. We develop TIMER-Bench, the first time-aware benchmark that evaluates temporal reasoning capabilities over longitudinal EHRs, as well as TIMER-Instruct, an instruction-tuning methodology for LLMs to learn reasoning over time. We demonstrate that models fine-tuned with TIMER-Instruct improve performance by 7.3% on human-generated benchmarks and 9.2% on TIMER-Bench, indicating that temporal instruction-tuning improves model performance for reasoning over EHR.

Chengkuan Chen, Luca L. Weishaupt, Drew F. K. Williamson et al.

Pathology is experiencing rapid digital transformation driven by whole-slide imaging and artificial intelligence (AI). While deep learning-based computational pathology has achieved notable success, traditional models primarily focus on image analysis without integrating natural language instruction or rich, text-based context. Current multimodal large language models (MLLMs) in computational pathology face limitations, including insufficient training data, inadequate support and evaluation for multi-image understanding, and a lack of autonomous, diagnostic reasoning capabilities. To address these limitations, we introduce PathChat+, a new MLLM specifically designed for human pathology, trained on over 1 million diverse, pathology-specific instruction samples and nearly 5.5 million question answer turns. Extensive evaluations across diverse pathology benchmarks demonstrated that PathChat+ substantially outperforms the prior PathChat copilot, as well as both state-of-the-art (SOTA) general-purpose and other pathology-specific models. Furthermore, we present SlideSeek, a reasoning-enabled multi-agent AI system leveraging PathChat+ to autonomously evaluate gigapixel whole-slide images (WSIs) through iterative, hierarchical diagnostic reasoning, reaching high accuracy on DDxBench, a challenging open-ended differential diagnosis benchmark, while also capable of generating visually grounded, humanly-interpretable summary reports.

Cristina Almagro-Pérez, Andrew H. Song, Luca Weishaupt et al.

A comprehensive three-dimensional (3D) map of tissue architecture and gene expression is crucial for illuminating the complexity and heterogeneity of tissues across diverse biomedical applications. However, most spatial transcriptomics (ST) approaches remain limited to two-dimensional (2D) sections of tissue. Although current 3D ST methods hold promise, they typically require extensive tissue sectioning, are complex, are not compatible with non-destructive 3D tissue imaging technologies, and often lack scalability. Here, we present VOlumetrically Resolved Transcriptomics EXpression (VORTEX), an AI framework that leverages 3D tissue morphology and minimal 2D ST to predict volumetric 3D ST. By pretraining on diverse 3D morphology-transcriptomic pairs from heterogeneous tissue samples and then fine-tuning on minimal 2D ST data from a specific volume of interest, VORTEX learns both generic tissue-related and sample-specific morphological correlates of gene expression. This approach enables dense, high-throughput, and fast 3D ST, scaling seamlessly to large tissue volumes far beyond the reach of existing 3D ST techniques. By offering a cost-effective and minimally destructive route to obtaining volumetric molecular insights, we anticipate that VORTEX will accelerate biomarker discovery and our understanding of morphomolecular associations and cell states in complex tissues. Interactive 3D ST volumes can be viewed at https://vortex-demo.github.io/

Bowen Chen, Namgi Han, Yusuke Miyao

Large Language Models (LLMs), trained on massive corpora with billions of parameters, show unprecedented performance in various fields. Though surprised by their excellent performances, researchers also noticed some special behaviors of those LLMs. One of those behaviors is memorization, in which LLMs can generate the same content used to train them. Though previous research has discussed memorization, the memorization of LLMs still lacks explanation, especially the cause of memorization and the dynamics of generating them. In this research, we comprehensively discussed memorization from various perspectives and extended the discussion scope to not only just the memorized content but also less and unmemorized content. Through various studies, we found that: (1) Through experiments, we revealed the relation of memorization between model size, continuation size, and context size. Further, we showed how unmemorized sentences transition to memorized sentences. (2) Through embedding analysis, we showed the distribution and decoding dynamics across model size in embedding space for sentences with different memorization scores. The n-gram statistics analysis presents d (3) An analysis over n-gram and entropy decoding dynamics discovered a boundary effect when the model starts to generate memorized sentences or unmemorized sentences. (4)We trained a Transformer model to predict the memorization of different models, showing that it is possible to predict memorizations by context.

Zhao Wang, Bowen Chen, Yotaro Shimose et al.

Recent generative models such as GPT-4o have shown strong capabilities in producing high-quality images with accurate text rendering. However, commercial design tasks like advertising banners demand more than visual fidelity -- they require structured layouts, precise typography, consistent branding, and more. In this paper, we introduce MIMO (Mirror In-the-Model), an agentic refinement framework for automatic ad banner generation. MIMO combines a hierarchical multi-modal agent system (MIMO-Core) with a coordination loop (MIMO-Loop) that explores multiple stylistic directions and iteratively improves design quality. Requiring only a simple natural language based prompt and logo image as input, MIMO automatically detects and corrects multiple types of errors during generation. Experiments show that MIMO significantly outperforms existing diffusion and LLM-based baselines in real-world banner design scenarios.

Bowen Chen, Zhao Wang, Shingo Takamatsu

Keyword decision in Sponsored Search Advertising is critical to the success of ad campaigns. While LLM-based methods offer automated keyword generation, they face three major limitations: reliance on large-scale query-keyword pair data, lack of online multi-objective performance monitoring and optimization, and weak quality control in keyword selection. These issues hinder the agentic use of LLMs in fully automating keyword decisions by monitoring and reasoning over key performance indicators such as impressions, clicks, conversions, and CTA effectiveness. To overcome these challenges, we propose OMS, a keyword generation framework that is On-the-fly (requires no training data, monitors online performance, and adapts accordingly), Multi-objective (employs agentic reasoning to optimize keywords based on multiple performance metrics), and Self-reflective (agentically evaluates keyword quality). Experiments on benchmarks and real-world ad campaigns show that OMS outperforms existing methods; ablation and human evaluations confirm the effectiveness of each component and the quality of generated keywords.

Bowen Chen, Keyan Chen, Mohan Yang et al.

High-resolution (HR) remote sensing imagery plays a vital role in a wide range of applications, including urban planning and environmental monitoring. However, due to limitations in sensors and data transmission links, the images acquired in practice often suffer from resolution degradation. Remote Sensing Image Super-Resolution (RSISR) aims to reconstruct HR images from low-resolution (LR) inputs, providing a cost-effective and efficient alternative to direct HR image acquisition. Existing RSISR methods primarily focus on low-level characteristics in pixel space, while neglecting the high-level understanding of remote sensing scenes. This may lead to semantically inconsistent artifacts in the reconstructed results. Motivated by this observation, our work aims to explore the role of high-level semantic knowledge in improving RSISR performance. We propose a Semantic-Guided Super-Resolution framework, SeG-SR, which leverages Vision-Language Models (VLMs) to extract semantic knowledge from input images and uses it to guide the super resolution (SR) process. Specifically, we first design a Semantic Feature Extraction Module (SFEM) that utilizes a pretrained VLM to extract semantic knowledge from remote sensing images. Next, we propose a Semantic Localization Module (SLM), which derives a series of semantic guidance from the extracted semantic knowledge. Finally, we develop a Learnable Modulation Module (LMM) that uses semantic guidance to modulate the features extracted by the SR network, effectively incorporating high-level scene understanding into the SR pipeline. We validate the effectiveness and generalizability of SeG-SR through extensive experiments: SeG-SR achieves state-of-the-art performance on three datasets, and consistently improves performance across various SR architectures. Notably, for the x4 SR task on UCMerced dataset, it attained a PSNR of 29.3042 dB and an SSIM of 0.7961.

Peijin Guo, Minghui Li, Hewen Pan et al.

Accurate prediction of molecular metabolic stability (MS) is critical for drug research and development but remains challenging due to the complex interplay of molecular interactions. Despite recent advances in graph neural networks (GNNs) for MS prediction, current approaches face two critical limitations: (1) incomplete molecular modeling due to atom-centric message-passing mechanisms that disregard bond-level topological features, and (2) prediction frameworks that lack reliable uncertainty quantification. To address these challenges, we propose TrustworthyMS, a novel contrastive learning framework designed for uncertainty-aware metabolic stability prediction. First, a molecular graph topology remapping mechanism synchronizes atom-bond interactions through edge-induced feature propagation, capturing both localized electronic effects and global conformational constraints. Second, contrastive topology-bond alignment enforces consistency between molecular topology views and bond patterns via feature alignment, enhancing representation robustness. Third, uncertainty modeling through Beta-Binomial uncertainty quantification enables simultaneous prediction and confidence calibration under epistemic uncertainty. Through extensive experiments, our results demonstrate that TrustworthyMS outperforms current state-of-the-art methods in terms of predictive performance.

Bowen Chen, Namgi Han, Yusuke Miyao

The lack of data transparency in Large Language Models (LLMs) has highlighted the importance of Membership Inference Attack (MIA), which differentiates trained (member) and untrained (non-member) data. Though it shows success in previous studies, recent research reported a near-random performance in different settings, highlighting a significant performance inconsistency. We assume that a single setting doesn't represent the distribution of the vast corpora, causing members and non-members with different distributions to be sampled and causing inconsistency. In this study, instead of a single setting, we statistically revisit MIA methods from various settings with thousands of experiments for each MIA method, along with study in text feature, embedding, threshold decision, and decoding dynamics of members and non-members. We found that (1) MIA performance improves with model size and varies with domains, while most methods do not statistically outperform baselines, (2) Though MIA performance is generally low, a notable amount of differentiable member and non-member outliers exists and vary across MIA methods, (3) Deciding a threshold to separate members and non-members is an overlooked challenge, (4) Text dissimilarity and long text benefit MIA performance, (5) Differentiable or not is reflected in the LLM embedding, (6) Member and non-members show different decoding dynamics.

Bowen Chen, Zaixi Shang, Jae Won Chung et al.

Demand for streaming services, including satellite, continues to exhibit unprecedented growth. Internet Service Providers find themselves at the crossroads of technological advancements and rising customer expectations. To stay relevant and competitive, these ISPs must ensure their networks deliver optimal video streaming quality, a key determinant of user satisfaction. Towards this end, it is important to have accurate Quality of Experience prediction models in place. However, achieving robust performance by these models requires extensive data sets labeled by subjective opinion scores on videos impaired by diverse playback disruptions. To bridge this data gap, we introduce the LIVE-Viasat Real-World Satellite QoE Database. This database consists of 179 videos recorded from real-world streaming services affected by various authentic distortion patterns. We also conducted a comprehensive subjective study involving 54 participants, who contributed both continuous-time opinion scores and endpoint (retrospective) QoE scores. Our analysis sheds light on various determinants influencing subjective QoE, such as stall events, spatial resolutions, bitrate, and certain network parameters. We demonstrate the usefulness of this unique new resource by evaluating the efficacy of prevalent QoE-prediction models on it. We also created a new model that maps the network parameters to predicted human perception scores, which can be used by ISPs to optimize the video streaming quality of their networks. Our proposed model, which we call SatQA, is able to accurately predict QoE using only network parameters, without any access to pixel data or video-specific metadata, estimated by Spearman's Rank Order Correlation Coefficient (SROCC), Pearson Linear Correlation Coefficient (PLCC), and Root Mean Squared Error (RMSE), indicating high accuracy and reliability.

Fan Yang, Jianfeng Zhang, Yichun Shi et al.

Benefiting from the rapid development of 2D diffusion models, 3D content generation has witnessed significant progress. One promising solution is to finetune the pre-trained 2D diffusion models to produce multi-view images and then reconstruct them into 3D assets via feed-forward sparse-view reconstruction models. However, limited by the 3D inconsistency in the generated multi-view images and the low reconstruction resolution of the feed-forward reconstruction models, the generated 3d assets are still limited to incorrect geometries and blurry textures. To address this problem, we present a multi-view based refine method, named Magic-Boost, to further refine the generation results. In detail, we first propose a novel multi-view conditioned diffusion model which extracts 3d prior from the synthesized multi-view images to synthesize high-fidelity novel view images and then introduce a novel iterative-update strategy to adopt it to provide precise guidance to refine the coarse generated results through a fast optimization process. Conditioned on the strong 3d priors extracted from the synthesized multi-view images, Magic-Boost is capable of providing precise optimization guidance that well aligns with the coarse generated 3D assets, enriching the local detail in both geometry and texture within a short time ($\sim15$min). Extensive experiments show Magic-Boost greatly enhances the coarse generated inputs, generates high-quality 3D assets with rich geometric and textural details. (Project Page: https://magic-research.github.io/magic-boost/)

Bowen Chen, Qiaohui Gao, Shaowen Wan et al.

Medical image segmentation is fundamental to clinical workflows, yet models trained on a single dataset often fail to generalize across institutions, scanners, or patient populations. While vision foundation models have shown great promise in addressing this challenge, their deployment typically requires task-specific fine-tuning, which introduces substantial communication overhead in federated learning and prevents continuous knowledge evolution during deployment. In this work, we propose a memory-augmented segmentation agent (MemSeg-Agent) that shifts adaptation from weight space to memory space, enabling few-shot learning, federated supervised learning, and test-time adaptation within a unified architecture. MemSeg-Agent conditions a fixed backbone with lightweight static, few-shot, and test-time working memories, which are dynamically composed by an agentic controller. In federated settings, we update compact memory units instead of model parameters, substantially reducing communication overhead. Experiments on four public datasets demonstrate strong performance and robustness to domain shift: Static memory alone matches or surpasses strong supervised baselines with high parameter efficiency, and test-time working memory further improves in-domain and cross-domain performance without fine-tuning. Overall, MemSeg-Agent introduces a new paradigm for scalable and adaptive medical image segmentation in the era of agentic AI.

Han Guo, Chenyang Liu, Haotian Zhang et al.

Remote sensing change detection (RSCD) aims to identify surface changes across bi-temporal satellite images. Most previous methods rely solely on mask supervision, which effectively guides spatial localization but provides limited constraints on the temporal semantic transitions. Consequently, they often produce spatially coherent predictions while still suffering from unresolved semantic inconsistencies. To address this limitation, we propose TaCo, a spatio-temporal semantic consistent network, which enriches the existing mask-supervised framework with a spatio-temporal semantic joint constraint. TaCo conceptualizes change as a semantic transition between bi-temporal states, in which one temporal feature representation can be derived from the other via dedicated transition features. To realize this, we introduce a Text-guided Transition Generator that integrates textual semantics with bi-temporal visual features to construct the cross-temporal transition features. In addition, we propose a spatio-temporal semantic joint constraint consisting of bi-temporal reconstruct constraints and a transition constraint: the former enforces alignment between reconstructed and original features, while the latter enhances discrimination for changes. This design can yield substantial performance gains without introducing any additional computational overhead during inference. Extensive experiments on six public datasets, spanning both binary and semantic change detection tasks, demonstrate that TaCo consistently achieves SOTA performance.

Yixu Chen, Bowen Chen, Hai Wei et al.

This paper reports IEEE International Conference on Multimedia \& Expo (ICME) 2025 Grand Challenge on Generalizable HDR and SDR Video Quality Measurement. With the rapid development of video technology, especially High Dynamic Range (HDR) and Standard Dynamic Range (SDR) contents, the need for robust and generalizable Video Quality Assessment (VQA) methods has become increasingly demanded. Existing VQA models often struggle to deliver consistent performance across varying dynamic ranges, distortion types, and diverse content. This challenge was established to benchmark and promote VQA approaches capable of jointly handling HDR and SDR content. In the final evaluation phase, five teams submitted seven models along with technical reports to the Full Reference (FR) and No Reference (NR) tracks. Among them, four methods outperformed VMAF baseline, while the top-performing model achieved state-of-the-art performance, setting a new benchmark for generalizable video quality assessment.

Haoyu Ji, Bowen Chen, Weihong Ren et al.

Skeleton-based Temporal Action Segmentation (STAS) aims to segment and recognize various actions from long, untrimmed sequences of human skeletal movements. Current STAS methods typically employ spatio-temporal modeling to establish dependencies among joints as well as frames, and utilize one-hot encoding with cross-entropy loss for frame-wise classification supervision. However, these methods overlook the intrinsic correlations among joints and actions within skeletal features, leading to a limited understanding of human movements. To address this, we propose a Text-Derived Relational Graph-Enhanced Network (TRG-Net) that leverages prior graphs generated by Large Language Models (LLM) to enhance both modeling and supervision. For modeling, the Dynamic Spatio-Temporal Fusion Modeling (DSFM) method incorporates Text-Derived Joint Graphs (TJG) with channel- and frame-level dynamic adaptation to effectively model spatial relations, while integrating spatio-temporal core features during temporal modeling. For supervision, the Absolute-Relative Inter-Class Supervision (ARIS) method employs contrastive learning between action features and text embeddings to regularize the absolute class distributions, and utilizes Text-Derived Action Graphs (TAG) to capture the relative inter-class relationships among action features. Additionally, we propose a Spatial-Aware Enhancement Processing (SAEP) method, which incorporates random joint occlusion and axial rotation to enhance spatial generalization. Performance evaluations on four public datasets demonstrate that TRG-Net achieves state-of-the-art results.

Jianing Li, Bowen Chen, Zhiyong Wang et al.

Given an untrimmed video, repetitive actions counting aims to estimate the number of repetitions of class-agnostic actions. To handle the various length of videos and repetitive actions, also optimization challenges in end-to-end video model training, down-sampling is commonly utilized in recent state-of-the-art methods, leading to ignorance of several repetitive samples. In this paper, we attempt to understand repetitive actions from a full temporal resolution view, by combining offline feature extraction and temporal convolution networks. The former step enables us to train repetition counting network without down-sampling while preserving all repetition regardless of the video length and action frequency, and the later network models all frames in a flexible and dynamically expanding temporal receptive field to retrieve all repetitions with a global aspect. We experimentally demonstrate that our method achieves better or comparable performance in three public datasets, i.e., TransRAC, UCFRep and QUVA. We expect this work will encourage our community to think about the importance of full temporal resolution.

Sachini Herath, Saghar Irandoust, Bowen Chen et al.

The paper proposes a multi-modal sensor fusion algorithm that fuses WiFi, IMU, and floorplan information to infer an accurate and dense location history in indoor environments. The algorithm uses 1) an inertial navigation algorithm to estimate a relative motion trajectory from IMU sensor data; 2) a WiFi-based localization API in industry to obtain positional constraints and geo-localize the trajectory; and 3) a convolutional neural network to refine the location history to be consistent with the floorplan. We have developed a data acquisition app to build a new dataset with WiFi, IMU, and floorplan data with ground-truth positions at 4 university buildings and 3 shopping malls. Our qualitative and quantitative evaluations demonstrate that the proposed system is able to produce twice as accurate and a few orders of magnitude denser location history than the current standard, while requiring minimal additional energy consumption. We will publicly share our code, data and models.

Bowen Chen, Huan Ling, Xiaohui Zeng et al.

Manually labeling video datasets for segmentation tasks is extremely time consuming. In this paper, we introduce ScribbleBox, a novel interactive framework for annotating object instances with masks in videos. In particular, we split annotation into two steps: annotating objects with tracked boxes, and labeling masks inside these tracks. We introduce automation and interaction in both steps. Box tracks are annotated efficiently by approximating the trajectory using a parametric curve with a small number of control points which the annotator can interactively correct. Our approach tolerates a modest amount of noise in the box placements, thus typically only a few clicks are needed to annotate tracked boxes to a sufficient accuracy. Segmentation masks are corrected via scribbles which are efficiently propagated through time. We show significant performance gains in annotation efficiency over past work. We show that our ScribbleBox approach reaches 88.92% J&F on DAVIS2017 with 9.14 clicks per box track, and 4 frames of scribble annotation.