Yi Xin

Dongyang Liu, Shitian Zhao, Le Zhuo et al.

We present Lumina-mGPT, a family of multimodal autoregressive models capable of various vision and language tasks, particularly excelling in generating flexible photorealistic images from text descriptions. By initializing from multimodal Generative PreTraining (mGPT), we demonstrate that decoder-only Autoregressive (AR) model can achieve image generation performance comparable to modern diffusion models with high efficiency through Flexible Progressive Supervised Fine-tuning (FP-SFT). Equipped with our proposed Unambiguous image Representation (UniRep), Lumina-mGPT can flexibly generate high-quality images of varying aspect ratios. Building on the strong image generation capabilities, we further explore Ominiponent Supervised Fine-tuning (Omni-SFT), an initial attempt to elevate Lumina-mGPT into a unified multi-modal generalist. The resulting model demonstrates versatile multimodal capabilities, including visual generation tasks like text-to-image/multiview generation and controllable generation, visual recognition tasks like segmentation and depth estimation, and vision-language tasks like multi-turn visual question answering, showing the rosy potential of the technical direction. Codes and checkpoints are available at https://github.com/Alpha-VLLM/Lumina-mGPT.

Luyang Luo, Mingxiang Wu, Mei Li et al.

Breast Magnetic Resonance Imaging (MRI) demonstrates the highest sensitivity for breast cancer detection among imaging modalities and is standard practice for high-risk women. Interpreting the multi-sequence MRI is time-consuming and prone to subjective variation. We develop a large mixture-of-modality-experts model (MOME) that integrates multiparametric MRI information within a unified structure, leveraging breast MRI scans from 5,205 female patients in China for model development and validation. MOME matches four senior radiologists' performance in identifying breast cancer and outperforms a junior radiologist. The model is able to reduce unnecessary biopsies in Breast Imaging-Reporting and Data System (BI-RADS) 4 patients, classify triple-negative breast cancer, and predict pathological complete response to neoadjuvant chemotherapy. MOME further supports inference with missing modalities and provides decision explanations by highlighting lesions and measuring modality contributions. To summarize, MOME exemplifies an accurate and robust multimodal model for noninvasive, personalized management of breast cancer patients via multiparametric MRI. Code is available at https://github.com/LLYXC/MOME/tree/main.

Xuyang Liu, Ting Liu, Siteng Huang et al.

Referring expression comprehension (REC) is a vision-language task to locate a target object in an image based on a language expression. Fully fine-tuning general-purpose pre-trained vision-language foundation models for REC yields impressive performance but becomes increasingly costly. Parameter-efficient transfer learning (PETL) methods have shown strong performance with fewer tunable parameters. However, directly applying PETL to REC faces two challenges: (1) insufficient multi-modal interaction between pre-trained vision-language foundation models, and (2) high GPU memory usage due to gradients passing through the heavy vision-language foundation models. To this end, we present M2IST: Multi-Modal Interactive Side-Tuning with M3ISAs: Mixture of Multi-Modal Interactive Side-Adapters. During fine-tuning, we fix the pre-trained uni-modal encoders and update M3ISAs to enable efficient vision-language alignment for REC. Empirical results reveal that M2IST achieves better performance-efficiency trade-off than full fine-tuning and other PETL methods, requiring only 2.11\% tunable parameters, 39.61\% GPU memory, and 63.46\% training time while maintaining competitive performance. Our code is released at https://github.com/xuyang-liu16/M2IST.

Zhongying Deng, Cheng Tang, Ziyan Huang et al. · pku

Foundation models have demonstrated remarkable success across diverse domains and tasks, primarily due to the thrive of large-scale, diverse, and high-quality datasets. However, in the field of medical imaging, the curation and assembling of such medical datasets are highly challenging due to the reliance on clinical expertise and strict ethical and privacy constraints, resulting in a scarcity of large-scale unified medical datasets and hindering the development of powerful medical foundation models. In this work, we present the largest survey to date of medical image datasets, covering over 1,000 open-access datasets with a systematic catalog of their modalities, tasks, anatomies, annotations, limitations, and potential for integration. Our analysis exposes a landscape that is modest in scale, fragmented across narrowly scoped tasks, and unevenly distributed across organs and modalities, which in turn limits the utility of existing medical image datasets for developing versatile and robust medical foundation models. To turn fragmentation into scale, we propose a metadata-driven fusion paradigm (MDFP) that integrates public datasets with shared modalities or tasks, thereby transforming multiple small data silos into larger, more coherent resources. Building on MDFP, we release an interactive discovery portal that enables end-to-end, automated medical image dataset integration, and compile all surveyed datasets into a unified, structured table that clearly summarizes their key characteristics and provides reference links, offering the community an accessible and comprehensive repository. By charting the current terrain and offering a principled path to dataset consolidation, our survey provides a practical roadmap for scaling medical imaging corpora, supporting faster data discovery, more principled dataset creation, and more capable medical foundation models.

Qi Fan, Yutong Li, Yi Xin et al.

The Multimodal Emotion Recognition challenge MER2024 focuses on recognizing emotions using audio, language, and visual signals. In this paper, we present our submission solutions for the Semi-Supervised Learning Sub-Challenge (MER2024-SEMI), which tackles the issue of limited annotated data in emotion recognition. Firstly, to address the class imbalance, we adopt an oversampling strategy. Secondly, we propose a modality representation combinatorial contrastive learning (MR-CCL) framework on the trimodal input data to establish robust initial models. Thirdly, we explore a self-training approach to expand the training set. Finally, we enhance prediction robustness through a multi-classifier weighted soft voting strategy. Our proposed method is validated to be effective on the MER2024-SEMI Challenge, achieving a weighted average F-score of 88.25% and ranking 6th on the leaderboard. Our project is available at https://github.com/WooyoohL/MER2024-SEMI.

Yongyang Pan, Xiaohong Liu, Siqi Luo et al.

Rapid advancements in multimodal large language models have enabled the creation of hyper-realistic images from textual descriptions. However, these advancements also raise significant concerns about unauthorized use, which hinders their broader distribution. Traditional watermarking methods often require complex integration or degrade image quality. To address these challenges, we introduce a novel framework Towards Effective user Attribution for latent diffusion models via Watermark-Informed Blending (TEAWIB). TEAWIB incorporates a unique ready-to-use configuration approach that allows seamless integration of user-specific watermarks into generative models. This approach ensures that each user can directly apply a pre-configured set of parameters to the model without altering the original model parameters or compromising image quality. Additionally, noise and augmentation operations are embedded at the pixel level to further secure and stabilize watermarked images. Extensive experiments validate the effectiveness of TEAWIB, showcasing the state-of-the-art performance in perceptual quality and attribution accuracy.

Yi Xin, Siqi Luo, Qi Qin et al.

Diffusion Multi-modal Large Language Models (dMLLMs) have recently emerged as a novel architecture unifying image generation and understanding. However, developing effective and efficient Test-Time Scaling (TTS) methods to unlock their full generative potential remains an underexplored challenge. To address this, we propose dMLLM-TTS, a novel framework operating on two complementary scaling axes: (1) trajectory exploration scaling to enhance the diversity of generated hypotheses, and (2) iterative refinement scaling for stable generation. Conventional TTS approaches typically perform linear search across these two dimensions, incurring substantial computational costs of O(NT) and requiring an external verifier for best-of-N selection. To overcome these limitations, we propose two innovations. First, we design an efficient hierarchical search algorithm with O(N+T) complexity that adaptively expands and prunes sampling trajectories. Second, we introduce a self-verified feedback mechanism that leverages the dMLLMs' intrinsic image understanding capabilities to assess text-image alignment, eliminating the need for external verifier. Extensive experiments on the GenEval benchmark across three representative dMLLMs (e.g., Lumina-DiMOO, MMaDA, Muddit) show that our framework substantially improves generation quality while achieving up to 6x greater efficiency than linear search. Project page: https://github.com/Alpha-VLLM/Lumina-DiMOO.

Jinbin Bai, Yixuan Li, Yuchen Zhu et al.

Inference-time compute has re-emerged as a practical way to improve LLM reasoning. Most test-time scaling (TTS) algorithms rely on autoregressive decoding, which is ill-suited to discrete diffusion language models (dLLMs) due to their parallel decoding over the entire sequence. As a result, developing effective and efficient TTS methods to unlock dLLMs' full generative potential remains an underexplored challenge. To address this, we propose Prism (Pruning, Remasking, and Integrated Self-verification Method), an efficient TTS framework for dLLMs that (i) performs Hierarchical Trajectory Search (HTS) which dynamically prunes and reallocates compute in an early-to-mid denoising window, (ii) introduces Local branching with partial remasking to explore diverse implementations while preserving high-confidence tokens, and (iii) replaces external verifiers with Self-Verified Feedback (SVF) obtained via self-evaluation prompts on intermediate completions. Across four mathematical reasoning and code generation benchmarks on three dLLMs, including LLaDA 8B Instruct, Dream 7B Instruct, and LLaDA 2.0-mini, our Prism achieves a favorable performance-efficiency trade-off, matching best-of-N performance with substantially fewer function evaluations (NFE). The code is released at https://github.com/viiika/Prism.

Xiaomin Yu, Yi Xin, Yuhui Zhang et al.

Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modality Gap, remains: embeddings of distinct modalities expressing identical semantics occupy systematically offset regions. Prior approaches to bridge this gap are largely limited by oversimplified isotropic assumptions, hindering their application in large-scale scenarios. In this paper, we address these limitations by precisely characterizing the geometric shape of the modality gap and leveraging it for efficient model scaling. First, we propose the Fixed-frame Modality Gap Theory, which decomposes the modality gap within a frozen reference frame into stable biases and anisotropic residuals. Guided by this precise modeling, we introduce ReAlign, a training-free modality alignment strategy. Utilizing statistics from massive unpaired data, ReAlign aligns text representation into the image representation distribution via a three-step process comprising Anchor, Trace, and Centroid Alignment, thereby explicitly rectifying geometric misalignment. Building on ReAlign, we propose ReVision, a scalable training paradigm for Multimodal Large Language Models~(MLLMs). ReVision integrates ReAlign into the pretraining stage, enabling the model to learn the distribution of visual representations from unpaired text before visual instruction tuning, without the need for large-scale, high-quality image-text pairs. Our framework demonstrates that statistically aligned unpaired data can effectively substitute for expensive image-text pairs, offering a robust path for the efficient scaling of MLLMs.

Siqi Luo, Yi Xin, Yuntao Du et al.

Deep neural networks often encounter significant performance drops while facing with domain shifts between training (source) and test (target) data. To address this issue, Test Time Adaptation (TTA) methods have been proposed to adapt pre-trained source model to handle out-of-distribution streaming target data. Although these methods offer some relief, they lack a reliable mechanism for domain shift correction, which can often be erratic in real-world applications. In response, we develop Few-Shot Test Time Adaptation (FS-TTA), a novel and practical setting that utilizes a few-shot support set on top of TTA. Adhering to the principle of few inputs, big gains, FS-TTA reduces blind exploration in unseen target domains. Furthermore, we propose a two-stage framework to tackle FS-TTA, including (i) fine-tuning the pre-trained source model with few-shot support set, along with using feature diversity augmentation module to avoid overfitting, (ii) implementing test time adaptation based on prototype memory bank guidance to produce high quality pseudo-label for model adaptation. Through extensive experiments on three cross-domain classification benchmarks, we demonstrate the superior performance and reliability of our FS-TTA and framework.

Jianbo Lin, Xiaomin Yu, Yi Xin et al.

Large language model-based agents make mistakes, yet critique can often guide the same model toward correct behavior. However, when critique is removed, the model may fail again on the same query, indicating that it has not internalized the critique's guidance into its underlying capability. Meanwhile, a frozen critic cannot improve its feedback quality over time, limiting the potential for iterative self-improvement. To address this, we propose learning to internalize self-critique with reinforcement learning(ICRL), a novel framework that jointly trains a solver and a critic from a shared backbone to convert critique-induced success into unassisted solver ability. The critic is rewarded based on the solver's subsequent performance gain, incentivizing actionable feedback. To address the distribution shift between critique-conditioned and critique-free behavior, ICRL introduces a distribution-calibration re-weighting ratio that selectively transfers critique-guided improvements compatible with the solver's own prompt distribution. Additionally, a role-wise group advantage estimation stabilizes joint optimization across the two roles. Together, these mechanisms ensure that the solver learns to improve itself without external critique, rather than becoming dependent on critique-conditioned behavior. We evaluate ICRL on diverse benchmarks spanning agentic and mathematical reasoning tasks, using Qwen3-4B and Qwen3-8B as backbones. Results show consistent improvements, with average gains of 6.4 points over GRPO on agentic tasks, and 7.0 points on mathematical reasoning. Notably, the learned 8B critic is comparable to 32B critics while using substantially fewer tokens. The code is available at https://github.com/brick-pid/ICRL.

Wenhui Liao, Hongliang Li, Pengyu Xie et al.

Document parsing is a fundamental task in multimodal understanding, supporting a wide range of downstream applications such as information extraction and intelligent document analysis. Benefiting from strong semantic modeling and robust generalization, VLM-based end-to-end approaches have emerged as the mainstream paradigm in recent years. However, these models often suffer from substantial inference latency, as they must auto-regressively generate long token sequences when processing long-form documents. In this work, motivated by the extremely long outputs and complex layout structures commonly found in document parsing, we propose a training-free and highly efficient acceleration method. Inspired by speculative decoding, we employ a lightweight document parsing pipeline as a draft model to predict batches of future tokens, while the more accurate VLM verifies these draft predictions in parallel. Moreover, we further exploit the layout-structured nature of documents by partitioning each page into independent regions, enabling parallel decoding of each region using the same draft-verify strategy. The final predictions are then assembled according to the natural reading order. Experimental results demonstrate the effectiveness of our approach: on the general-purpose OmniDocBench, our method provides a 2.42x lossless acceleration for the dots.ocr model, and achieves up to 4.89x acceleration on long-document parsing tasks. We will release our code to facilitate reproducibility and future research.

Dianyi Wang, Ruihang Li, Feng Han et al.

Current unified multimodal models for image generation and editing typically rely on massive parameter scales (e.g., >10B), entailing prohibitive training costs and deployment footprints. In this work, we present DeepGen 1.0, a lightweight 5B unified model that achieves comprehensive capabilities competitive with or surpassing much larger counterparts. To overcome the limitations of compact models in semantic understanding and fine-grained control, we introduce Stacked Channel Bridging (SCB), a deep alignment framework that extracts hierarchical features from multiple VLM layers and fuses them with learnable 'think tokens' to provide the generative backbone with structured, reasoning-rich guidance. We further design a data-centric training strategy spanning three progressive stages: (1) Alignment Pre-training on large-scale image-text pairs and editing triplets to synchronize VLM and DiT representations, (2) Joint Supervised Fine-tuning on a high-quality mixture of generation, editing, and reasoning tasks to foster omni-capabilities, and (3) Reinforcement Learning with MR-GRPO, which leverages a mixture of reward functions and supervision signals, resulting in substantial gains in generation quality and alignment with human preferences, while maintaining stable training progress and avoiding visual artifacts. Despite being trained on only ~50M samples, DeepGen 1.0 achieves leading performance across diverse benchmarks, surpassing the 80B HunyuanImage by 28% on WISE and the 27B Qwen-Image-Edit by 37% on UniREditBench. By open-sourcing our training code, weights, and datasets, we provide an efficient, high-performance alternative to democratize unified multimodal research.

Changyao Tian, Danni Yang, Guanzhou Chen et al.

Unified multimodal models (UMMs) that integrate understanding, reasoning, generation, and editing face inherent trade-offs between maintaining strong semantic comprehension and acquiring powerful generation capabilities. In this report, we present InternVL-U, a lightweight 4B-parameter UMM that democratizes these capabilities within a unified framework. Guided by the principles of unified contextual modeling and modality-specific modular design with decoupled visual representations, InternVL-U integrates a state-of-the-art Multimodal Large Language Model (MLLM) with a specialized MMDiT-based visual generation head. To further bridge the gap between aesthetic generation and high-level intelligence, we construct a comprehensive data synthesis pipeline targeting high-semantic-density tasks, such as text rendering and scientific reasoning, under a reasoning-centric paradigm that leverages Chain-of-Thought (CoT) to better align abstract user intent with fine-grained visual generation details. Extensive experiments demonstrate that InternVL-U achieves a superior performance - efficiency balance. Despite using only 4B parameters, it consistently outperforms unified baseline models with over 3x larger scales such as BAGEL (14B) on various generation and editing tasks, while retaining strong multimodal understanding and reasoning capabilities.

Qi Qin, Le Zhuo, Yi Xin et al.

We introduce Lumina-Image 2.0, an advanced text-to-image generation framework that achieves significant progress compared to previous work, Lumina-Next. Lumina-Image 2.0 is built upon two key principles: (1) Unification - it adopts a unified architecture (Unified Next-DiT) that treats text and image tokens as a joint sequence, enabling natural cross-modal interactions and allowing seamless task expansion. Besides, since high-quality captioners can provide semantically well-aligned text-image training pairs, we introduce a unified captioning system, Unified Captioner (UniCap), specifically designed for T2I generation tasks. UniCap excels at generating comprehensive and accurate captions, accelerating convergence and enhancing prompt adherence. (2) Efficiency - to improve the efficiency of our proposed model, we develop multi-stage progressive training strategies and introduce inference acceleration techniques without compromising image quality. Extensive evaluations on academic benchmarks and public text-to-image arenas show that Lumina-Image 2.0 delivers strong performances even with only 2.6B parameters, highlighting its scalability and design efficiency. We have released our training details, code, and models at https://github.com/Alpha-VLLM/Lumina-Image-2.0.

Guimin Hu, Yi Xin, Weimin Lyu et al.

Multimodal affective computing (MAC) has garnered increasing attention due to its broad applications in analyzing human behaviors and intentions, especially in text-dominated multimodal affective computing field. This survey presents the recent trends of multimodal affective computing from NLP perspective through four hot tasks: multimodal sentiment analysis, multimodal emotion recognition in conversation, multimodal aspect-based sentiment analysis and multimodal multi-label emotion recognition. The goal of this survey is to explore the current landscape of multimodal affective research, identify development trends, and highlight the similarities and differences across various tasks, offering a comprehensive report on the recent progress in multimodal affective computing from an NLP perspective. This survey covers the formalization of tasks, provides an overview of relevant works, describes benchmark datasets, and details the evaluation metrics for each task. Additionally, it briefly discusses research in multimodal affective computing involving facial expressions, acoustic signals, physiological signals, and emotion causes. Additionally, we discuss the technical approaches, challenges, and future directions in multimodal affective computing. To support further research, we released a repository that compiles related works in multimodal affective computing, providing detailed resources and references for the community.

Inclusion AI, Tiwei Bie, Haoxing Chen et al.

We present LLaDA2.0-Uni, a unified discrete diffusion large language model (dLLM) that supports multimodal understanding and generation within a natively integrated framework. Its architecture combines a fully semantic discrete tokenizer, a MoE-based dLLM backbone, and a diffusion decoder. By discretizing continuous visual inputs via SigLIP-VQ, the model enables block-level masked diffusion for both text and vision inputs within the backbone, while the decoder reconstructs visual tokens into high-fidelity images. Inference efficiency is enhanced beyond parallel decoding through prefix-aware optimizations in the backbone and few-step distillation in the decoder. Supported by carefully curated large-scale data and a tailored multi-stage training pipeline, LLaDA2.0-Uni matches specialized VLMs in multimodal understanding while delivering strong performance in image generation and editing. Its native support for interleaved generation and reasoning establishes a promising and scalable paradigm for next-generation unified foundation models. Codes and models are available at https://github.com/inclusionAI/LLaDA2.0-Uni.

Ting Liu, Xuyang Liu, Siteng Huang et al. · tsinghua

Parameter-efficient fine-tuning (PEFT) has emerged as a popular solution for adapting pre-trained Vision Transformer (ViT) models to downstream applications. While current PEFT methods have achieved parameter efficiency, they overlook the efficiency of computation and GPU memory during both fine-tuning and inference, falling short of practical requirements. In this paper, we propose \textbf{Sparse-Tuning}, a novel PEFT method that accounts for the information redundancy in images and videos to boost the above efficiency. By sparsely preserving the semantic-relevant tokens and merging irrelevant ones, Sparse-Tuning minimizes the quantity of tokens processed at each layer, leading to a quadratic reduction in computational and memory overhead. To align our token sparsification strategy suitably with fine-tuning purposes, we further design Dense Adapters that establish dense connections from shallow layers to deeper layers. These Dense Adapters integrate multi-level local features to enrich the current tokens, improving both token preservation and model adaptation. Empirical results on VTAB-1K, three image datasets, and two video datasets show that our Sparse-Tuning reduces GFLOPs to \textbf{62\%-70\%} of the original ViT-B while achieving state-of-the-art performance. Source code is available at \url{https://github.com/liuting20/Sparse-Tuning}.

Jinbin Bai, Yu Lei, Qingyu Shi et al.

Aligning large visual generative models with human feedback is often performed through pairwise preference optimization. While such approaches are conceptually simple, they fundamentally rely on annotated pairs, limiting scalability in settings where feedback is collected as independent scalar ratings. In this work, we revisit the KL-regularized alignment objective and show that the optimal policy implicitly compares each sample's reward to an instance-specific baseline that is generally intractable. We propose a threshold-guided alignment framework that replaces this oracle baseline with a data-driven global threshold estimated from empirical score statistics. This formulation turns alignment into a binary decision task on unpaired data, enabling effective optimization directly from scalar feedback. We also incorporate a confidence weighting term to emphasize samples whose scores deviate strongly from the threshold, improving sample efficiency. Experiments across both diffusion and masked generative paradigms, spanning three test sets and five reward models, show that our method consistently improves preference alignment over previous methods. These results position our threshold-guided framework as a simple yet principled alternative for aligning visual generative models without paired comparisons.

Yi Xin, Juncheng Yan, Qi Qin et al.

We present Lumina-mGPT 2.0, a stand-alone, decoder-only autoregressive model that revisits and revitalizes the autoregressive paradigm for high-quality image generation and beyond. Unlike existing approaches that rely on pretrained components or hybrid architectures, Lumina-mGPT 2.0 is trained entirely from scratch, enabling unrestricted architectural design and licensing freedom. It achieves generation quality on par with state-of-the-art diffusion models such as DALL-E 3 and SANA, while preserving the inherent flexibility and compositionality of autoregressive modeling. Our unified tokenization scheme allows the model to seamlessly handle a wide spectrum of tasks-including subject-driven generation, image editing, controllable synthesis, and dense prediction-within a single generative framework. To further boost usability, we incorporate efficient decoding strategies like inference-time scaling and speculative Jacobi sampling to improve quality and speed, respectively. Extensive evaluations on standard text-to-image benchmarks (e.g., GenEval, DPG) demonstrate that Lumina-mGPT 2.0 not only matches but in some cases surpasses diffusion-based models. Moreover, we confirm its multi-task capabilities on the Graph200K benchmark, with the native Lumina-mGPT 2.0 performing exceptionally well. These results position Lumina-mGPT 2.0 as a strong, flexible foundation model for unified multimodal generation. We have released our training details, code, and models at https://github.com/Alpha-VLLM/Lumina-mGPT-2.0.

Dongyang Liu, Shicheng Li, Yutong Liu et al.

Recent advancements have established Diffusion Transformers (DiTs) as a dominant framework in generative modeling. Building on this success, Lumina-Next achieves exceptional performance in the generation of photorealistic images with Next-DiT. However, its potential for video generation remains largely untapped, with significant challenges in modeling the spatiotemporal complexity inherent to video data. To address this, we introduce Lumina-Video, a framework that leverages the strengths of Next-DiT while introducing tailored solutions for video synthesis. Lumina-Video incorporates a Multi-scale Next-DiT architecture, which jointly learns multiple patchifications to enhance both efficiency and flexibility. By incorporating the motion score as an explicit condition, Lumina-Video also enables direct control of generated videos' dynamic degree. Combined with a progressive training scheme with increasingly higher resolution and FPS, and a multi-source training scheme with mixed natural and synthetic data, Lumina-Video achieves remarkable aesthetic quality and motion smoothness at high training and inference efficiency. We additionally propose Lumina-V2A, a video-to-audio model based on Next-DiT, to create synchronized sounds for generated videos. Codes are released at https://www.github.com/Alpha-VLLM/Lumina-Video.

Siyeop Yoon, Yujin Oh, Xiang Li et al.

Acute respiratory distress syndrome (ARDS) is a severe condition characterized by lung inflammation and respiratory failure, with a high mortality rate of approximately 40%. Traditional imaging methods, such as chest X-rays, provide only two-dimensional views, limiting their effectiveness in fully assessing lung pathology. Three-dimensional (3D) computed tomography (CT) offers a more comprehensive visualization, enabling detailed analysis of lung aeration, atelectasis, and the effects of therapeutic interventions. However, the routine use of CT in ARDS management is constrained by practical challenges and risks associated with transporting critically ill patients to remote scanners. In this study, we synthesize high-fidelity 3D lung CT from 2D generated X-ray images with associated physiological parameters using a score-based 3D residual diffusion model. Our preliminary results demonstrate that this approach can produce high-quality 3D CT images that are validated with ground truth, offering a promising solution for enhancing ARDS management.

Yi Xin, Qi Qin, Siqi Luo et al.

We introduce Lumina-DiMOO, an open-source foundational model for seamless multi-modal generation and understanding. Lumina-DiMOO sets itself apart from prior unified models by utilizing a fully discrete diffusion modeling to handle inputs and outputs across various modalities. This innovative approach allows Lumina-DiMOO to achieve higher sampling efficiency compared to previous autoregressive (AR) or hybrid AR-Diffusion paradigms and adeptly support a broad spectrum of multi-modal tasks, including text-to-image generation, image-to-image generation (e.g., image editing, subject-driven generation, and image inpainting, etc.), as well as image understanding. Lumina-DiMOO achieves state-of-the-art performance on multiple benchmarks, surpassing existing open-source unified multi-modal models. To foster further advancements in multi-modal and discrete diffusion model research, we release our code and checkpoints to the community. Project Page: https://synbol.github.io/Lumina-DiMOO.

Shuo Cao, Jiayang Li, Xiaohui Li et al.

Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks such as visual grounding, segmentation, and captioning. However, their ability to perceive perceptual-level image features remains limited. In this work, we present UniPercept-Bench, a unified framework for perceptual-level image understanding across three key domains: Aesthetics, Quality, Structure and Texture. We establish a hierarchical definition system and construct large-scale datasets to evaluate perceptual-level image understanding. Based on this foundation, we develop a strong baseline UniPercept trained via Domain-Adaptive Pre-Training and Task-Aligned RL, enabling robust generalization across both Visual Rating (VR) and Visual Question Answering (VQA) tasks. UniPercept outperforms existing MLLMs on perceptual-level image understanding and can serve as a plug-and-play reward model for text-to-image generation. This work defines Perceptual-Level Image Understanding in the era of MLLMs and, through the introduction of a comprehensive benchmark together with a strong baseline, provides a solid foundation for advancing perceptual-level multimodal image understanding.

Yi Xin, Le Zhuo, Qi Qin et al.

AutoRegressive (AR) models have made notable progress in image generation, with Masked AutoRegressive (MAR) models gaining attention for their efficient parallel decoding. However, MAR models have traditionally underperformed when compared to standard AR models. This study refines the MAR architecture to improve image generation quality. We begin by evaluating various image tokenizers to identify the most effective one. Subsequently, we introduce an improved Bidirectional LLaMA architecture by replacing causal attention with bidirectional attention and incorporating 2D RoPE, which together form our advanced model, MaskGIL. Scaled from 111M to 1.4B parameters, MaskGIL achieves a FID score of 3.71, matching state-of-the-art AR models in the ImageNet 256x256 benchmark, while requiring only 8 inference steps compared to the 256 steps of AR models. Furthermore, we develop a text-driven MaskGIL model with 775M parameters for generating images from text at various resolutions. Beyond image generation, MaskGIL extends to accelerate AR-based generation and enable real-time speech-to-image conversion. Our codes and models are available at https://github.com/synbol/MaskGIL.

Siqi Luo, Jianghan Shen, Yi Xin et al.

Diffusion Multi-Modal Large Language Models (dMLLMs) are powerful for image generation, but optimizing them through reinforcement learning (RL) remains a major challenge. One primary difficulty is that a single image can be generated through many different unmasking sequences, which makes calculating importance ratios often intractable. Additionally, existing methods tend to ignore the hierarchical generation process of dMLLMs, where early tokens define the global layout and later tokens focus on local details. By assigning uniform rewards to all tokens, these current methods fail to reflect the actual contribution of each token to the final image. To address these issues, we propose Hierarchical Token GRPO (HT-GRPO), which integrates this hierarchy directly into the policy optimization process. Our approach features a Sketch-Then-Paint training scheme that organizes updates into three distinct stages: global, structure, and refinement. We also use a prompt-conditioned estimator to calculate importance ratios starting from a fully masked state. Furthermore, we introduce a Hierarchical Credit Assignment mechanism that prioritizes key structural tokens to ensure accurate reward propagation. Experiments using two popular dMLLM backbones, MMaDA and Lumina-DiMOO, demonstrate that HT-GRPO achieves substantial gains on the GenEval and DPG benchmarks. Evaluations across six additional metrics confirm significant improvements in image quality, aesthetics, and human preference.

Yi Xin, Jianjiang Yang, Siqi Luo et al.

Pre-trained vision models (PVMs) have demonstrated remarkable adaptability across a wide range of downstream vision tasks, showcasing exceptional performance. However, as these models scale to billions or even trillions of parameters, conventional full fine-tuning has become increasingly impractical due to its high computational and storage demands. To address these challenges, parameter-efficient fine-tuning (PEFT) has emerged as a promising alternative, aiming to achieve performance comparable to full fine-tuning while making minimal adjustments to the model parameters. This paper presents a comprehensive survey of the latest advancements in the visual PEFT field, systematically reviewing current methodologies and categorizing them into four primary categories: addition-based, partial-based, unified-based, and multi-task tuning. In addition, this paper offers an in-depth analysis of widely used visual datasets and real-world applications where PEFT methods have been successfully applied. Furthermore, this paper introduces the V-PEFT Bench, a unified benchmark designed to standardize the evaluation of PEFT methods across a diverse set of vision tasks, ensuring consistency and fairness in comparison. Finally, the paper outlines potential directions for future research to propel advances in the PEFT field. A comprehensive collection of resources is available at https://github.com/synbol/Awesome-Parameter-Efficient-Transfer-Learning.

Jaemoo Choi, Yuchen Zhu, Wei Guo et al.

Reinforcement learning has been widely applied to diffusion and flow models for visual tasks such as text-to-image generation. However, these tasks remain challenging because diffusion models have intractable likelihoods, which creates a barrier for directly applying popular policy-gradient type methods. Existing approaches primarily focus on crafting new objectives built on already heavily engineered LLM objectives, using ad hoc estimators for likelihood, without a thorough investigation into how such estimation affects overall algorithmic performance. In this work, we provide a systematic analysis of the RL design space by disentangling three factors: i) policy-gradient objectives, ii) likelihood estimators, and iii) rollout sampling schemes. We show that adopting an evidence lower bound (ELBO) based model likelihood estimator, computed only from the final generated sample, is the dominant factor enabling effective, efficient, and stable RL optimization, outweighing the impact of the specific policy-gradient loss functional. We validate our findings across multiple reward benchmarks using SD 3.5 Medium, and observe consistent trends across all tasks. Our method improves the GenEval score from 0.24 to 0.95 in 90 GPU hours, which is $4.6\times$ more efficient than FlowGRPO and $2\times$ more efficient than the SOTA method DiffusionNFT without reward hacking.

Siqi Luo, Haoran Yang, Yi Xin et al.

Large pre-trained models achieve remarkable performance in vision tasks but are impractical for fine-tuning due to high computational and storage costs. Parameter-Efficient Fine-Tuning (PEFT) methods mitigate this issue by updating only a subset of parameters; however, most existing approaches are task-agnostic, failing to fully exploit task-specific adaptations, which leads to suboptimal efficiency and performance. To address this limitation, we propose Task-Relevant Parameter and Token Selection (TR-PTS), a task-driven framework that enhances both computational efficiency and accuracy. Specifically, we introduce Task-Relevant Parameter Selection, which utilizes the Fisher Information Matrix (FIM) to identify and fine-tune only the most informative parameters in a layer-wise manner, while keeping the remaining parameters frozen. Simultaneously, Task-Relevant Token Selection dynamically preserves the most informative tokens and merges redundant ones, reducing computational overhead. By jointly optimizing parameters and tokens, TR-PTS enables the model to concentrate on task-discriminative information. We evaluate TR-PTS on benchmark, including FGVC and VTAB-1k, where it achieves state-of-the-art performance, surpassing full fine-tuning by 3.40% and 10.35%, respectively. The code are available at https://github.com/synbol/TR-PTS.

Junzhi Ning, Wei Li, Cheng Tang et al.

Medical diagnostic applications require models that can process multimodal medical inputs (images, patient histories, lab results) and generate diverse outputs including both textual reports and visual content (annotations, segmentation masks, and images). Despite this need, existing medical AI systems disrupt this unified process: medical image understanding models interpret images but cannot generate visual outputs, while medical image generation models synthesize images but cannot provide textual explanations. This leads to gaps in data representation, feature integration, and task-level multimodal capabilities. To this end, we propose a multi-level framework that draws inspiration from diagnostic workflows through the Observation-Knowledge-Analysis (OKA) paradigm. Specifically, at the observation level, we construct UniMed-5M, a dataset comprising over 5.6M samples that reformat diverse unimodal data into multimodal pairs for foundational observation. At the knowledge level, we propose Progressive Curriculum Learning that systematically introduces medical multimodal knowledge. At the analysis level, we introduce UniMedVL, the first medical unified multimodal model for the simultaneous analysis of image understanding and generation tasks within a single architecture. UniMedVL achieves superior performance on five medical image understanding benchmarks, while matching specialized models in generation quality across eight medical imaging modalities. Crucially, our unified architecture enables bidirectional knowledge sharing: generation tasks enhance visual understanding features, demonstrating that integrating traditionally separate capabilities within a single medical framework unlocks improvements across diverse medical vision-language tasks. Code is available at https://github.com/uni-medical/UniMedVL.

Yifan Jia, Kailin Jiang, Yuyang Liang et al.

Large Multimodal Models(LMMs) face notable challenges when encountering multimodal knowledge conflicts, particularly under retrieval-augmented generation(RAG) frameworks where the contextual information from external sources may contradict the model's internal parametric knowledge, leading to unreliable outputs. However, existing benchmarks fail to reflect such realistic conflict scenarios. Most focus solely on intra-memory conflicts, while context-memory and inter-context conflicts remain largely investigated. Furthermore, commonly used factual knowledge-based evaluations are often overlooked, and existing datasets lack a thorough investigation into conflict detection capabilities. To bridge this gap, we propose MMKC-Bench, a benchmark designed to evaluate factual knowledge conflicts in both context-memory and inter-context scenarios. MMKC-Bench encompasses three types of multimodal knowledge conflicts and includes 1,573 knowledge instances and 3,381 images across 23 broad types, collected through automated pipelines with human verification. We evaluate three representative series of LMMs on both model behavior analysis and conflict detection tasks. Our findings show that while current LMMs are capable of recognizing knowledge conflicts, they tend to favor internal parametric knowledge over external evidence. We hope MMKC-Bench will foster further research in multimodal knowledge conflict and enhance the development of multimodal RAG systems. The source code is available at https://github.com/MLLMKCBENCH/MLLMKC.

Yi Xin, Junlong Du, Qiang Wang et al.

Multi-Task Learning (MTL) is designed to train multiple correlated tasks simultaneously, thereby enhancing the performance of individual tasks. Typically, a multi-task network structure consists of a shared backbone and task-specific decoders. However, the complexity of the decoders increases with the number of tasks. To tackle this challenge, we integrate the decoder-free vision-language model CLIP, which exhibits robust zero-shot generalization capability. Recently, parameter-efficient transfer learning methods have been extensively explored with CLIP for adapting to downstream tasks, where prompt tuning showcases strong potential. Nevertheless, these methods solely fine-tune a single modality (text or visual), disrupting the modality structure of CLIP. In this paper, we first propose Multi-modal Alignment Prompt (MmAP) for CLIP, which aligns text and visual modalities during fine-tuning process. Building upon MmAP, we develop an innovative multi-task prompt learning framework. On the one hand, to maximize the complementarity of tasks with high similarity, we utilize a gradient-driven task grouping method that partitions tasks into several disjoint groups and assign a group-shared MmAP to each group. On the other hand, to preserve the unique characteristics of each task, we assign an task-specific MmAP to each task. Comprehensive experiments on two large multi-task learning datasets demonstrate that our method achieves significant performance improvements compared to full fine-tuning while only utilizing approximately 0.09% of trainable parameters.

Yi Xin, Junlong Du, Qiang Wang et al.

Large-scale pre-trained models have achieved remarkable success in various computer vision tasks. A standard approach to leverage these models is to fine-tune all model parameters for downstream tasks, which poses challenges in terms of computational and storage costs. Recently, inspired by Natural Language Processing (NLP), parameter-efficient transfer learning has been successfully applied to vision tasks. However, most existing techniques primarily focus on single-task adaptation, and despite limited research on multi-task adaptation, these methods often exhibit suboptimal training and inference efficiency. In this paper, we first propose an once-for-all Vision Multi-Task Adapter (VMT-Adapter), which strikes approximately O(1) training and inference efficiency w.r.t task number. Concretely, VMT-Adapter shares the knowledge from multiple tasks to enhance cross-task interaction while preserves task-specific knowledge via independent knowledge extraction modules. Notably, since task-specific modules require few parameters, VMT-Adapter can handle an arbitrary number of tasks with a negligible increase of trainable parameters. We also propose VMT-Adapter-Lite, which further reduces the trainable parameters by learning shared parameters between down- and up-projections. Extensive experiments on four dense scene understanding tasks demonstrate the superiority of VMT-Adapter(-Lite), achieving a 3.96%(1.34%) relative improvement compared to single-task full fine-tuning, while utilizing merely ~1% (0.36%) trainable parameters of the pre-trained model.

Qiang Yi, Yangfan He, Jianhui Wang et al.

Large Language Models (LLMs) can generate creative and engaging narratives from user-specified input, but maintaining coherence and emotional depth throughout these AI-generated stories remains a challenge. In this work, we propose SCORE, a framework for Story Coherence and Retrieval Enhancement, designed to detect and resolve narrative inconsistencies. By tracking key item statuses and generating episode summaries, SCORE uses a Retrieval-Augmented Generation (RAG) approach to identify related episodes and enhance the overall story structure. Experimental results from testing multiple LLM-generated stories demonstrate that SCORE significantly improves the consistency and stability of narrative coherence compared to baseline GPT models, providing a more robust method for evaluating and refining AI-generated narratives.

Yingxue Xu, Zhengyu Zhang, Xiuming Zhang et al.

Pathology foundation models have shown strong retrospective performance, but whether such systems can support clinically relevant use remains unclear. This challenge is particularly important in breast cancer, where pathological assessment serves as the gold standard for diagnosis and guides treatment planning, surgical decision-making and risk stratification across pre-, intra- and post-operative stages. Here we present \textbf{BRAVE}, a breast-adaptive pathology foundation model developed and evaluated using a total resource of 101,638 breast whole-slide images from 32 sources across Asia, Europe and North America. We assessed BRAVE across 34 tasks in 82 cohorts spanning pre-operative biopsy, intra-operative frozen section and post-operative resection, using an evidence chain comprising retrospective benchmarking, clinically challenging scenarios, workflow-oriented clinical impact simulations, prospective observational validation with the thresholds locked in the retrospective cohorts and crossover pathologist-AI interaction studies. Across these settings, BRAVE supported practical roles in the clinical workflow, including safe exclusion of low-risk cases from routine review, AI-assisted second-review rescue of initially missed positives and prioritization of cases for further assessment. In prospective validation across three centres, BRAVE excluded 76.9% of negative biopsy cases (NPV 0.953) and 70.1% of negative frozen-section cases (NPV 0.973), and triaged 78.8% of post-operative subtyping cases as high-confidence clear-cut cases (NPV 1.000). In reader studies, AI assistance improved balanced accuracy from 88.5% to 95.1% (OR 3.14, P<0.001), with better efficiency, confidence and inter-rater agreement. BRAVE-derived scores also independently predicted disease-free survival (adjusted HR 4.79, P<0.001) and overall survival (adjusted HR 8.14, P<0.001).

Yangfan He, Sida Li, Jianhui Wang et al.

Recent advancements in text-to-image (T2I) generation using diffusion models have enabled cost-effective video-editing applications by leveraging pre-trained models, eliminating the need for resource-intensive training. However, the frame-independence of T2I generation often results in poor temporal consistency. Existing methods address this issue through temporal layer fine-tuning or inference-based temporal propagation, but these approaches suffer from high training costs or limited temporal coherence. To address these challenges, we propose a General and Efficient Adapter (GE-Adapter) that integrates temporal-spatial and semantic consistency with Baliteral DDIM inversion. This framework introduces three key components: (1) Frame-based Temporal Consistency Blocks (FTC Blocks) to capture frame-specific features and enforce smooth inter-frame transitions via temporally-aware loss functions; (2) Channel-dependent Spatial Consistency Blocks (SCD Blocks) employing bilateral filters to enhance spatial coherence by reducing noise and artifacts; and (3) Token-based Semantic Consistency Module (TSC Module) to maintain semantic alignment using shared prompt tokens and frame-specific tokens. Our method significantly improves perceptual quality, text-image alignment, and temporal coherence, as demonstrated on the MSR-VTT dataset. Additionally, it achieves enhanced fidelity and frame-to-frame coherence, offering a practical solution for T2V editing.

Zhongwei Wan, Zhihao Dou, Che Liu et al.

Multimodal large language models (MLLMs) have shown promising capabilities in reasoning tasks, yet still struggle with complex problems requiring explicit self-reflection and self-correction, especially compared to their unimodal text-based counterparts. Existing reflection methods are simplistic and struggle to generate meaningful and instructive feedback, as the reasoning ability and knowledge limits of pre-trained models are largely fixed during initial training. To overcome these challenges, we propose Multimodal Self-Reflection enhanced reasoning with Group Relative Policy Optimization (SRPO), a two-stage reflection-aware reinforcement learning (RL) framework explicitly designed to enhance multimodal LLM reasoning. In the first stage, we construct a high-quality, reflection-focused dataset under the guidance of an advanced MLLM, which generates reflections based on initial responses to help the policy model learn both reasoning and self-reflection. In the second stage, we introduce a novel reward mechanism within the GRPO framework that encourages concise and cognitively meaningful reflection while avoiding redundancy. Extensive experiments across multiple multimodal reasoning benchmarks, including MathVista, MathVision, MathVerse, and MMMU-Pro, using Qwen-2.5-VL-7B and Qwen-2.5-VL-32B demonstrate that SRPO significantly outperforms state-of-the-art models, achieving notable improvements in both reasoning accuracy and reflection quality.

Mingyang Yi, Aoxue Li, Yi Xin et al.

Recently, the strong latent Diffusion Probabilistic Model (DPM) has been applied to high-quality Text-to-Image (T2I) generation (e.g., Stable Diffusion), by injecting the encoded target text prompt into the gradually denoised diffusion image generator. Despite the success of DPM in practice, the mechanism behind it remains to be explored. To fill this blank, we begin by examining the intermediate statuses during the gradual denoising generation process in DPM. The empirical observations indicate, the shape of image is reconstructed after the first few denoising steps, and then the image is filled with details (e.g., texture). The phenomenon is because the low-frequency signal (shape relevant) of the noisy image is not corrupted until the final stage in the forward process (initial stage of generation) of adding noise in DPM. Inspired by the observations, we proceed to explore the influence of each token in the text prompt during the two stages. After a series of experiments of T2I generations conditioned on a set of text prompts. We conclude that in the earlier generation stage, the image is mostly decided by the special token [\texttt{EOS}] in the text prompt, and the information in the text prompt is already conveyed in this stage. After that, the diffusion model completes the details of generated images by information from themselves. Finally, we propose to apply this observation to accelerate the process of T2I generation by properly removing text guidance, which finally accelerates the sampling up to 25\%+.

Yangfan He, Jianhui Wang, Yijin Wang et al.

Current image generation systems produce high-quality images but struggle with ambiguous user prompts, making interpretation of actual user intentions difficult. Many users must modify their prompts several times to ensure the generated images meet their expectations. While some methods focus on enhancing prompts to make the generated images fit user needs, the model is still hard to understand users' real needs, especially for non-expert users. In this research, we aim to enhance the visual parameter-tuning process, making the model user-friendly for individuals without specialized knowledge and better understand user needs. We propose a human-machine co-adaption strategy using mutual information between the user's prompts and the pictures under modification as the optimizing target to make the system better adapt to user needs. We find that an improved model can reduce the necessity for multiple rounds of adjustments. We also collect multi-round dialogue datasets with prompts and images pairs and user intent. Various experiments demonstrate the effectiveness of the proposed method in our proposed dataset. Our dataset and annotation tools will be available.

Le Zhuo, Liangbing Zhao, Sayak Paul et al.

Recent text-to-image diffusion models achieve impressive visual quality through extensive scaling of training data and model parameters, yet they often struggle with complex scenes and fine-grained details. Inspired by the self-reflection capabilities emergent in large language models, we propose ReflectionFlow, an inference-time framework enabling diffusion models to iteratively reflect upon and refine their outputs. ReflectionFlow introduces three complementary inference-time scaling axes: (1) noise-level scaling to optimize latent initialization; (2) prompt-level scaling for precise semantic guidance; and most notably, (3) reflection-level scaling, which explicitly provides actionable reflections to iteratively assess and correct previous generations. To facilitate reflection-level scaling, we construct GenRef, a large-scale dataset comprising 1 million triplets, each containing a reflection, a flawed image, and an enhanced image. Leveraging this dataset, we efficiently perform reflection tuning on state-of-the-art diffusion transformer, FLUX.1-dev, by jointly modeling multimodal inputs within a unified framework. Experimental results show that ReflectionFlow significantly outperforms naive noise-level scaling methods, offering a scalable and compute-efficient solution toward higher-quality image synthesis on challenging tasks.

Wenze Liu, Le Zhuo, Yi Xin et al.

We introduce a new paradigm for AutoRegressive (AR) image generation, termed Set AutoRegressive Modeling (SAR). SAR generalizes the conventional AR to the next-set setting, i.e., splitting the sequence into arbitrary sets containing multiple tokens, rather than outputting each token in a fixed raster order. To accommodate SAR, we develop a straightforward architecture termed Fully Masked Transformer. We reveal that existing AR variants correspond to specific design choices of sequence order and output intervals within the SAR framework, with AR and Masked AR (MAR) as two extreme instances. Notably, SAR facilitates a seamless transition from AR to MAR, where intermediate states allow for training a causal model that benefits from both few-step inference and KV cache acceleration, thus leveraging the advantages of both AR and MAR. On the ImageNet benchmark, we carefully explore the properties of SAR by analyzing the impact of sequence order and output intervals on performance, as well as the generalization ability regarding inference order and steps. We further validate the potential of SAR by training a 900M text-to-image model capable of synthesizing photo-realistic images with any resolution. We hope our work may inspire more exploration and application of AR-based modeling across diverse modalities.

Ming Hu, Chenglong Ma, Wei Li et al. · pku

Scientific Large Language Models (Sci-LLMs) are transforming how knowledge is represented, integrated, and applied in scientific research, yet their progress is shaped by the complex nature of scientific data. This survey presents a comprehensive, data-centric synthesis that reframes the development of Sci-LLMs as a co-evolution between models and their underlying data substrate. We formulate a unified taxonomy of scientific data and a hierarchical model of scientific knowledge, emphasizing the multimodal, cross-scale, and domain-specific challenges that differentiate scientific corpora from general natural language processing datasets. We systematically review recent Sci-LLMs, from general-purpose foundations to specialized models across diverse scientific disciplines, alongside an extensive analysis of over 270 pre-/post-training datasets, showing why Sci-LLMs pose distinct demands -- heterogeneous, multi-scale, uncertainty-laden corpora that require representations preserving domain invariance and enabling cross-modal reasoning. On evaluation, we examine over 190 benchmark datasets and trace a shift from static exams toward process- and discovery-oriented assessments with advanced evaluation protocols. These data-centric analyses highlight persistent issues in scientific data development and discuss emerging solutions involving semi-automated annotation pipelines and expert validation. Finally, we outline a paradigm shift toward closed-loop systems where autonomous agents based on Sci-LLMs actively experiment, validate, and contribute to a living, evolving knowledge base. Collectively, this work provides a roadmap for building trustworthy, continually evolving artificial intelligence (AI) systems that function as a true partner in accelerating scientific discovery.

Tianyu Fu, Anyang Su, Chenxu Zhao et al.

Graphical user interfaces (GUIs) are the primary medium for human-computer interaction, yet automating GUI interactions remains challenging due to the complexity of visual elements, dynamic environments, and the need for multi-step reasoning. Existing methods based on vision-language models (VLMs) often suffer from limited resolution, domain mismatch, and insufficient sequential decisionmaking capability. To address these issues, we propose Mano, a robust GUI agent built upon a multi-modal foundation model pre-trained on extensive web and computer system data. Our approach integrates a novel simulated environment for high-fidelity data generation, a three-stage training pipeline (supervised fine-tuning, offline reinforcement learning, and online reinforcement learning), and a verification module for error recovery. Mano demonstrates state-of-the-art performance on multiple GUI benchmarks, including Mind2Web and OSWorld, achieving significant improvements in success rate and operational accuracy. Our work provides new insights into the effective integration of reinforcement learning with VLMs for practical GUI agent deployment, highlighting the importance of domain-specific data, iterative training, and holistic reward design.

Victor Shea-Jay Huang, Le Zhuo, Yi Xin et al.

Diffusion Transformers (DiTs) are a powerful yet underexplored class of generative models compared to U-Net-based diffusion architectures. We propose TIDE-Temporal-aware sparse autoencoders for Interpretable Diffusion transformErs-a framework designed to extract sparse, interpretable activation features across timesteps in DiTs. TIDE effectively captures temporally-varying representations and reveals that DiTs naturally learn hierarchical semantics (e.g., 3D structure, object class, and fine-grained concepts) during large-scale pretraining. Experiments show that TIDE enhances interpretability and controllability while maintaining reasonable generation quality, enabling applications such as safe image editing and style transfer.

Jian Yu, Fei Shen, Cong Wang et al.

Diffusion models have driven remarkable advancements in fashion image generation, yet prior works usually treat garment generation and virtual dressing as separate problems, limiting their flexibility in real-world fashion workflows. Moreover, fashion image synthesis under multi-source heterogeneous conditions remains challenging, as existing methods typically rely on simple feature concatenation or static layer-wise injection, which often causes attribute entanglement and semantic interference. To address these issues, we propose VersaVogue, a unified framework for multi-condition controllable fashion synthesis that jointly supports garment generation and virtual dressing, corresponding to the design and showcase stages of the fashion lifecycle. Specifically, we introduce a trait-routing attention (TA) module that leverages a mixture-of-experts mechanism to dynamically route condition features to the most compatible experts and generative layers, enabling disentangled injection of visual attributes such as texture, shape, and color. To further improve realism and controllability, we develop an automated multi-perspective preference optimization (MPO) pipeline that constructs preference data without human annotation or task-specific reward models. By combining evaluators of content fidelity, textual alignment, and perceptual quality, MPO identifies reliable preference pairs, which are then used to optimize the model via direct preference optimization (DPO). Extensive experiments on both garment generation and virtual dressing benchmarks demonstrate that VersaVogue consistently outperforms existing methods in visual fidelity, semantic consistency, and fine-grained controllability.

Jinbin Bai, Yu Lei, Hecong Wu et al.

This is not a typical survey of world models; it is a guide for those who want to build worlds. We do not aim to catalog every paper that has ever mentioned a ``world model". Instead, we follow one clear road: from early masked models that unified representation learning across modalities, to unified architectures that share a single paradigm, then to interactive generative models that close the action-perception loop, and finally to memory-augmented systems that sustain consistent worlds over time. We bypass loosely related branches to focus on the core: the generative heart, the interactive loop, and the memory system. We show that this is the most promising path towards true world models.

Yibin Wang, Zhimin Li, Yuhang Zang et al.

Recent progress in text-to-image (T2I) generation underscores the importance of reliable benchmarks in evaluating how accurately generated images reflect the semantics of their textual prompt. However, (1) existing benchmarks lack the diversity of prompt scenarios and multilingual support, both essential for real-world applicability; (2) they offer only coarse evaluations across primary dimensions, covering a narrow range of sub-dimensions, and fall short in fine-grained sub-dimension assessment. To address these limitations, we introduce UniGenBench++, a unified semantic assessment benchmark for T2I generation. Specifically, it comprises 600 prompts organized hierarchically to ensure both coverage and efficiency: (1) spans across diverse real-world scenarios, i.e., 5 main prompt themes and 20 subthemes; (2) comprehensively probes T2I models' semantic consistency over 10 primary and 27 sub evaluation criteria, with each prompt assessing multiple testpoints. To rigorously assess model robustness to variations in language and prompt length, we provide both English and Chinese versions of each prompt in short and long forms. Leveraging the general world knowledge and fine-grained image understanding capabilities of a closed-source Multi-modal Large Language Model (MLLM), i.e., Gemini-2.5-Pro, an effective pipeline is developed for reliable benchmark construction and streamlined model assessment. Moreover, to further facilitate community use, we train a robust evaluation model that enables offline assessment of T2I model outputs. Through comprehensive benchmarking of both open- and closed-sourced T2I models, we systematically reveal their strengths and weaknesses across various aspects.

Siyi Wu, Junqiao Wang, Zhaoyang Guan et al.

Cryptocurrency trading is a challenging task requiring the integration of heterogeneous data from multiple modalities. Traditional deep learning and reinforcement learning approaches typically demand large training datasets and encode diverse inputs into numerical representations, often at the cost of interpretability. Recent progress in large language model (LLM)-based agents has demonstrated the capacity to process multi-modal data and support complex investment decision-making. Building on these advances, we present \textbf{MountainLion}, a multi-modal, multi-agent system for financial trading that coordinates specialized LLM-based agents to interpret financial data and generate investment strategies. MountainLion processes textual news, candlestick charts, and trading signal charts to produce high-quality financial reports, while also enabling modification of reports and investment recommendations through data-driven user interaction and question answering. A central reflection module analyzes historical trading signals and outcomes to continuously refine decision processes, and the system is capable of real-time report analysis, summarization, and dynamic adjustment of investment strategies. Empirical results confirm that MountainLion systematically enriches technical price triggers with contextual macroeconomic and capital flow signals, providing a more interpretable, robust, and actionable investment framework that improves returns and strengthens investor confidence.

Kangrui Cen, Baixuan Zhao, Yi Xin et al.

Controlling object motion trajectories in Text-to-Video (T2V) generation is a challenging and relatively under-explored area, particularly in scenarios involving multiple moving objects. Most community models and datasets in the T2V domain are designed for single-object motion, limiting the performance of current generative models in multi-object tasks. Additionally, existing motion control methods in T2V either lack support for multi-object motion scenes or experience severe performance degradation when object trajectories intersect, primarily due to the semantic conflicts in colliding regions. To address these limitations, we introduce LayerT2V, the first approach for generating video by compositing background and foreground objects layer by layer. This layered generation enables flexible integration of multiple independent elements within a video, positioning each element on a distinct "layer" and thus facilitating coherent multi-object synthesis while enhancing control over the generation process. Extensive experiments demonstrate the superiority of LayerT2V in generating complex multi-object scenarios, showcasing 1.4x and 4.5x improvements in mIoU and AP50 metrics over state-of-the-art (SOTA) methods. Project page and code are available at https://kr-panghu.github.io/LayerT2V/ .

Jianhui Wang, Yinda Chen, Yangfan He et al.

Video editing is a critical component of content creation that transforms raw footage into coherent works aligned with specific visual and narrative objectives. Existing approaches face two major challenges: temporal inconsistencies due to failure in capturing complex motion patterns, and overfitting to simple prompts arising from limitations in UNet backbone architectures. While learning-based methods can enhance editing quality, they typically demand substantial computational resources and are constrained by the scarcity of high-quality annotated data. In this paper, we present Vid-TTA, a lightweight test-time adaptation framework that personalizes optimization for each test video during inference through self-supervised auxiliary tasks. Our approach incorporates a motion-aware frame reconstruction mechanism that identifies and preserves crucial movement regions, alongside a prompt perturbation and reconstruction strategy that strengthens model robustness to diverse textual descriptions. These innovations are orchestrated by a meta-learning driven dynamic loss balancing mechanism that adaptively adjusts the optimization process based on video characteristics. Extensive experiments demonstrate that Vid-TTA significantly improves video temporal consistency and mitigates prompt overfitting while maintaining low computational overhead, offering a plug-and-play performance boost for existing video editing models.