Wei Song

Wen Wang, Shunda Hu, Shiqiang Zhu et al.

A service robot serving safely and politely needs to track the surrounding people robustly, especially for Tour-Guide Robot (TGR). However, existing multi-object tracking (MOT) or multi-person tracking (MPT) methods are not applicable to TGR for the following reasons: 1. lacking relevant large-scale datasets; 2. lacking applicable metrics to evaluate trackers. In this work, we target the visual perceptual tasks for TGR and present the TGRDB dataset, a novel large-scale multi-person tracking dataset containing roughly 5.6 hours of annotated videos and over 450 long-term trajectories. Besides, we propose a more applicable metric to evaluate trackers using our dataset. As part of our work, we present TGRMPT, a novel MPT system that incorporates information from head shoulder and whole body, and achieves state-of-the-art performance. We have released our codes and dataset in https://github.com/wenwenzju/TGRMPT.

Tingxu Han, Yi Zhang, Wei Song et al.

Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real utility in end-to-end development settings remains unclear. We present SWE-Skills-Bench, the first requirement-driven benchmark that isolates the marginal utility of agent skills in real-world software engineering (SWE). It pairs 49 public SWE skills with authentic GitHub repositories pinned at fixed commits and requirement documents with explicit acceptance criteria, yielding approximately 565 task instances across six SWE subdomains. We introduce a deterministic verification framework that maps each task's acceptance criteria to execution-based tests, enabling controlled paired evaluation with and without the skill. Our results show that skill injection benefits are far more limited than rapid adoption suggests: 39 of 49 skills yield zero pass-rate improvement, and the average gain is only +1.2%. Token overhead varies from modest savings to a 451% increase while pass rates remain unchanged. Only seven specialized skills produce meaningful gains (up to +30%), while three degrade performance (up to -10%) due to version-mismatched guidance conflicting with project context. These findings suggest that agent skills are a narrow intervention whose utility depends strongly on domain fit, abstraction level, and contextual compatibility. SWE-Skills-Bench provides a testbed for evaluating the design, selection, and deployment of skills in software engineering agents. SWE-Skills-Bench is available at https://github.com/GeniusHTX/SWE-Skills-Bench.

Yike Wu, Nan Hu, Sheng Bi et al.

Despite their competitive performance on knowledge-intensive tasks, large language models (LLMs) still have limitations in memorizing all world knowledge especially long tail knowledge. In this paper, we study the KG-augmented language model approach for solving the knowledge graph question answering (KGQA) task that requires rich world knowledge. Existing work has shown that retrieving KG knowledge to enhance LLMs prompting can significantly improve LLMs performance in KGQA. However, their approaches lack a well-formed verbalization of KG knowledge, i.e., they ignore the gap between KG representations and textual representations. To this end, we propose an answer-sensitive KG-to-Text approach that can transform KG knowledge into well-textualized statements most informative for KGQA. Based on this approach, we propose a KG-to-Text enhanced LLMs framework for solving the KGQA task. Experiments on several KGQA benchmarks show that the proposed KG-to-Text augmented LLMs approach outperforms previous KG-augmented LLMs approaches regarding answer accuracy and usefulness of knowledge statements.

Yan Wang, Shaoqi Yan, Yang Liu et al.

Facial expression recognition (FER) aims to analyze emotional states from static images and dynamic sequences, which is pivotal in enhancing anthropomorphic communication among humans, robots, and digital avatars by leveraging AI technologies. As the FER field evolves from controlled laboratory environments to more complex in-the-wild scenarios, advanced methods have been rapidly developed and new challenges and apporaches are encounted, which are not well addressed in existing reviews of FER. This paper offers a comprehensive survey of both image-based static FER (SFER) and video-based dynamic FER (DFER) methods, analyzing from model-oriented development to challenge-focused categorization. We begin with a critical comparison of recent reviews, an introduction to common datasets and evaluation criteria, and an in-depth workflow on FER to establish a robust research foundation. We then systematically review representative approaches addressing eight main challenges in SFER (such as expression disturbance, uncertainties, compound emotions, and cross-domain inconsistency) as well as seven main challenges in DFER (such as key frame sampling, expression intensity variations, and cross-modal alignment). Additionally, we analyze recent advancements, benchmark performances, major applications, and ethical considerations. Finally, we propose five promising future directions and development trends to guide ongoing research. The project page for this paper can be found at https://github.com/wangyanckxx/SurveyFER.

Mario Di Mauro, Giovanni Galatro, Fabio Postiglione et al.

Predicting the behavior of real-time traffic (e.g., VoIP) in mobility scenarios could help the operators to better plan their network infrastructures and to optimize the allocation of resources. Accordingly, in this work the authors propose a forecasting analysis of crucial QoS/QoE descriptors (some of which neglected in the technical literature) of VoIP traffic in a real mobile environment. The problem is formulated in terms of a multivariate time series analysis. Such a formalization allows to discover and model the temporal relationships among various descriptors and to forecast their behaviors for future periods. Techniques such as Vector Autoregressive models and machine learning (deep-based and tree-based) approaches are employed and compared in terms of performance and time complexity, by reframing the multivariate time series problem into a supervised learning one. Moreover, a series of auxiliary analyses (stationarity, orthogonal impulse responses, etc.) are performed to discover the analytical structure of the time series and to provide deep insights about their relationships. The whole theoretical analysis has an experimental counterpart since a set of trials across a real-world LTE-Advanced environment has been performed to collect, post-process and analyze about 600,000 voice packets, organized per flow and differentiated per codec.

Fiseha B. Tesema, Zheyuan Lin, Shiqiang Zhu et al.

Active speaker detection plays a vital role in human-machine interaction. Recently, a few end-to-end audiovisual frameworks emerged. However, these models' inference time was not explored and are not applicable for real-time applications due to their complexity and large input size. In addition, they explored a similar feature extraction strategy that employs the ConvNet on audio and visual inputs. This work presents a novel two-stream end-to-end framework fusing features extracted from images via VGG-M with raw Mel Frequency Cepstrum Coefficients features extracted from the audio waveform. The network has two BiGRU layers attached to each stream to handle each stream's temporal dynamic before fusion. After fusion, one BiGRU layer is attached to model the joint temporal dynamics. The experiment result on the AVA-ActiveSpeaker dataset indicates that our new feature extraction strategy shows more robustness to noisy signals and better inference time than models that employed ConvNet on both modalities. The proposed model predicts within 44.41 ms, which is fast enough for real-time applications. Our best-performing model attained 88.929% accuracy, nearly the same detection result as state-of-the-art -work.

Wei Song, Jun Zhou, Mingjie Wang et al.

This paper focuses on the recently popular task of point cloud completion guided by multimodal information. Although existing methods have achieved excellent performance by fusing auxiliary images, there are still some deficiencies, including the poor generalization ability of the model and insufficient fine-grained semantic information for extracted features. In this work, we propose a novel multimodal fusion network for point cloud completion, which can simultaneously fuse visual and textual information to predict the semantic and geometric characteristics of incomplete shapes effectively. Specifically, to overcome the lack of prior information caused by the small-scale dataset, we employ a pre-trained vision-language model that is trained with a large amount of image-text pairs. Therefore, the textual and visual encoders of this large-scale model have stronger generalization ability. Then, we propose a multi-stage feature fusion strategy to fuse the textual and visual features into the backbone network progressively. Meanwhile, to further explore the effectiveness of fine-grained text descriptions for point cloud completion, we also build a text corpus with fine-grained descriptions, which can provide richer geometric details for 3D shapes. The rich text descriptions can be used for training and evaluating our network. Extensive quantitative and qualitative experiments demonstrate the superior performance of our method compared to state-of-the-art point cloud completion networks.

Wei Song, Tianhang Wang, Yitong Chen et al.

We present Channel-wise Vector Quantization (CVQ), a novel image tokenization paradigm that replaces patch-wise tokens with channel-wise tokens. Unlike conventional vector quantization, which assigns a discrete token to each patch feature vector, CVQ quantizes each channel of the feature map. This formulation represents an image as discrete levels of visual details, rather than as a grid of spatial patches. Based on CVQ, we introduce a new visual autoregressive framework with "next-channel prediction". Instead of rendering images patch by patch in raster order, our Channel-wise Autoregressive (CAR) model predicts image channels sequentially, producing progressively enriched visual details. Specifically, it first sketches global structure and then refines fine-grained attributes, akin to a human artist's workflow. Empirically, we show that: (1) CVQ achieves 100% codebook utilization with a 16K+ codebook size without any bells and whistles, and substantially improves reconstruction quality over conventional VQ; and (2) CAR attains a DPG score of 86.7 and a GenEval score of 0.79, demonstrating strong effectiveness for text-to-image generation.

Kimi Team, Angang Du, Bohong Yin et al. · pku, tsinghua

We present Kimi-VL, an efficient open-source Mixture-of-Experts (MoE) vision-language model (VLM) that offers advanced multimodal reasoning, long-context understanding, and strong agent capabilities - all while activating only 2.8B parameters in its language decoder (Kimi-VL-A3B). Kimi-VL demonstrates strong performance across challenging domains: as a general-purpose VLM, Kimi-VL excels in multi-turn agent tasks (e.g., OSWorld), matching flagship models. Furthermore, it exhibits remarkable capabilities across diverse challenging vision language tasks, including college-level image and video comprehension, OCR, mathematical reasoning, and multi-image understanding. In comparative evaluations, it effectively competes with cutting-edge efficient VLMs such as GPT-4o-mini, Qwen2.5-VL-7B, and Gemma-3-12B-IT, while surpassing GPT-4o in several key domains. Kimi-VL also advances in processing long contexts and perceiving clearly. With a 128K extended context window, Kimi-VL can process diverse long inputs, achieving impressive scores of 64.5 on LongVideoBench and 35.1 on MMLongBench-Doc. Its native-resolution vision encoder, MoonViT, further allows it to see and understand ultra-high-resolution visual inputs, achieving 83.2 on InfoVQA and 34.5 on ScreenSpot-Pro, while maintaining lower computational cost for common tasks. Building upon Kimi-VL, we introduce an advanced long-thinking variant: Kimi-VL-Thinking-2506. Developed through long chain-of-thought (CoT) supervised fine-tuning (SFT) and reinforcement learning (RL), the latest model exhibits strong long-horizon reasoning capabilities (64.0 on MMMU, 46.3 on MMMU-Pro, 56.9 on MathVision, 80.1 on MathVista, 65.2 on VideoMMMU) while obtaining robust general abilities. Code and models are publicly accessible at https://github.com/MoonshotAI/Kimi-VL.

Wei Song, Zhenchang Xing, Liming Zhu et al.

The rapid proliferation of realistic deepfakes has raised urgent concerns over their misuse, motivating the use of defensive watermarks in synthetic images for reliable detection and provenance tracking. However, this defense paradigm assumes such watermarks are inherently resistant to removal. We challenge this assumption with DeMark, a query-free black-box attack framework that targets defensive image watermarking schemes for deepfakes. DeMark exploits latent-space vulnerabilities in encoder-decoder watermarking models through a compressive sensing based sparsification process, suppressing watermark signals while preserving perceptual and structural realism appropriate for deepfakes. Across eight state-of-the-art watermarking schemes, DeMark reduces watermark detection accuracy from 100% to 32.9% on average while maintaining natural visual quality, outperforming existing attacks. We further evaluate three defense strategies, including image super resolution, sparse watermarking, and adversarial training, and find them largely ineffective. These results demonstrate that current encoder decoder watermarking schemes remain vulnerable to latent-space manipulations, underscoring the need for more robust watermarking methods to safeguard against deepfakes.

Sirong Piao, Ying Ming, Ruijie Zhao et al.

To characterize lobar and segmental airway volume differences between systemic lupus erythematosus (SLE) patients with interstitial lung disease (ILD) and those without ILD (non-ILD) using a deep learning-based approach on non-contrast chest high-resolution CT (HRCT). Methods: A retrospective analysis was conducted on 106 SLE patients (27 SLE-ILD, 79 SLE-non-ILD) who underwent HRCT. A customized deep learning framework based on the U-Net architecture was developed to automatically segment airway structures at the lobar and segmental levels via HRCT. Volumetric measurements of lung lobes and segments derived from the segmentations were statistically compared between the two groups using two-sample t-tests (significance threshold: p < 0.05). Results: At lobar level, significant airway volume enlargement in SLE-ILD patients was observed in the right upper lobe (p=0.009) and left upper lobe (p=0.039) compared to SLE-non-ILD. At the segmental level, significant differences were found in segments including R1 (p=0.016), R3 (p<0.001), and L3 (p=0.038), with the most marked changes in the upper lung zones, while lower zones showed non-significant trends. Conclusion: Our study demonstrates that an automated deep learning-based approach can effectively quantify airway volumes on HRCT scans and reveal significant, region-specific airway dilation in patients with SLE-ILD compared to those without ILD. The pattern of involvement, predominantly affecting the upper lobes and specific segments, highlights a distinct topographic phenotype of SLE-ILD and implicates airway structural alterations as a potential biomarker for disease presence. This AI-powered quantitative imaging biomarker holds promise for enhancing the early detection and monitoring of ILD in the SLE population, ultimately contributing to more personalized patient management.

Yaqi Wang, Yifan Zhang, Xiaodiao Chen et al.

Computer-aided design (CAD) tools are increasingly popular in modern dental practice, particularly for treatment planning or comprehensive prognosis evaluation. In particular, the 2D panoramic X-ray image efficiently detects invisible caries, impacted teeth and supernumerary teeth in children, while the 3D dental cone beam computed tomography (CBCT) is widely used in orthodontics and endodontics due to its low radiation dose. However, there is no open-access 2D public dataset for children's teeth and no open 3D dental CBCT dataset, which limits the development of automatic algorithms for segmenting teeth and analyzing diseases. The Semi-supervised Teeth Segmentation (STS) Challenge, a pioneering event in tooth segmentation, was held as a part of the MICCAI 2023 ToothFairy Workshop on the Alibaba Tianchi platform. This challenge aims to investigate effective semi-supervised tooth segmentation algorithms to advance the field of dentistry. In this challenge, we provide two modalities including the 2D panoramic X-ray images and the 3D CBCT tooth volumes. In Task 1, the goal was to segment tooth regions in panoramic X-ray images of both adult and pediatric teeth. Task 2 involved segmenting tooth sections using CBCT volumes. Limited labelled images with mostly unlabelled ones were provided in this challenge prompt using semi-supervised algorithms for training. In the preliminary round, the challenge received registration and result submission by 434 teams, with 64 advancing to the final round. This paper summarizes the diverse methods employed by the top-ranking teams in the STS MICCAI 2023 Challenge.

KimiTeam, Ding Ding, Zeqian Ju et al.

We present Kimi-Audio, an open-source audio foundation model that excels in audio understanding, generation, and conversation. We detail the practices in building Kimi-Audio, including model architecture, data curation, training recipe, inference deployment, and evaluation. Specifically, we leverage a 12.5Hz audio tokenizer, design a novel LLM-based architecture with continuous features as input and discrete tokens as output, and develop a chunk-wise streaming detokenizer based on flow matching. We curate a pre-training dataset that consists of more than 13 million hours of audio data covering a wide range of modalities including speech, sound, and music, and build a pipeline to construct high-quality and diverse post-training data. Initialized from a pre-trained LLM, Kimi-Audio is continual pre-trained on both audio and text data with several carefully designed tasks, and then fine-tuned to support a diverse of audio-related tasks. Extensive evaluation shows that Kimi-Audio achieves state-of-the-art performance on a range of audio benchmarks including speech recognition, audio understanding, audio question answering, and speech conversation. We release the codes, model checkpoints, as well as the evaluation toolkits in https://github.com/MoonshotAI/Kimi-Audio.

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.

Dianyi Wang, Chaofan Ma, Feng Han et al.

Unified multimodal models often struggle with complex synthesis tasks that demand deep reasoning, and typically treat text-to-image generation and image editing as isolated capabilities rather than interconnected reasoning steps. To address this, we propose UniReason, a unified framework that harmonizes these two tasks through a dual reasoning paradigm. We formulate generation as world knowledge-enhanced planning to inject implicit constraints, and leverage editing capabilities for fine-grained visual refinement to further correct visual errors via self-reflection. This approach unifies generation and editing within a shared representation, mirroring the human cognitive process of planning followed by refinement. We support this framework by systematically constructing a large-scale reasoning-centric dataset (~300k samples) covering five major knowledge domains (e.g., cultural commonsense, physics, etc.) for planning, alongside an agent-generated corpus for visual self-correction. Extensive experiments demonstrate that UniReason achieves advanced performance on reasoning-intensive benchmarks such as WISE, KrisBench and UniREditBench, while maintaining superior general synthesis capabilities.

Haonan Zhong, Wei Song, Tingxu Han et al.

Text-to-video (T2V) diffusion models have achieved rapid progress, yet their demographic biases, particularly gender bias, remain largely unexplored. We present FairT2V, a training-free debiasing framework for text-to-video generation that mitigates encoder-induced bias without finetuning. We first analyze demographic bias in T2V models and show that it primarily originates from pretrained text encoders, which encode implicit gender associations even for neutral prompts. We quantify this effect with a gender-leaning score that correlates with bias in generated videos. Based on this insight, FairT2V mitigates demographic bias by neutralizing prompt embeddings via anchor-based spherical geodesic transformations while preserving semantics. To maintain temporal coherence, we apply debiasing only during early identity-forming steps through a dynamic denoising schedule. We further propose a video-level fairness evaluation protocol combining VideoLLM-based reasoning with human verification. Experiments on the modern T2V model Open-Sora show that FairT2V substantially reduces demographic bias across occupations with minimal impact on video quality.

Yuxin Cao, Wei Song, Shangzhi Xu et al.

Video Large Language Models (VideoLLMs) have recently achieved strong performance in video understanding tasks. However, we identify a previously underexplored generation failure: severe output repetition, where models degenerate into self-reinforcing loops of repeated phrases or sentences. This failure mode is not captured by existing VideoLLM benchmarks, which focus primarily on task accuracy and factual correctness. We introduce VideoSTF, the first framework for systematically measuring and stress-testing output repetition in VideoLLMs. VideoSTF formalizes repetition using three complementary n-gram-based metrics and provides a standardized testbed of 10,000 diverse videos together with a library of controlled temporal transformations. Using VideoSTF, we conduct pervasive testing, temporal stress testing, and adversarial exploitation across 10 advanced VideoLLMs. We find that output repetition is widespread and, critically, highly sensitive to temporal perturbations of video inputs. Moreover, we show that simple temporal transformations can efficiently induce repetitive degeneration in a black-box setting, exposing output repetition as an exploitable security vulnerability. Our results reveal output repetition as a fundamental stability issue in modern VideoLLMs and motivate stability-aware evaluation for video-language systems. Our evaluation code and scripts are available at: https://github.com/yuxincao22/VideoSTF_benchmark.

Tianhang Wang, Yitong Chen, Wei Song et al.

Representation Autoencoders (RAEs) leverage frozen vision foundation models (VFMs) as tokenizer encoders, providing robust high-level representations that facilitate fast convergence and high-quality generation in latent diffusion models. However, freezing the VFM inherently constrains its spatial reconstruction capacity, limiting fine-grained generation and image editing; in contrast, incorporating reconstruction-oriented signals via fine-tuning disrupts the pretrained semantic space and degrades generative fidelity. To address this trade-off, we propose DecQ, a simple yet effective framework for RAEs. Specifically, DecQ introduces lightweight detail-condensing queries that extract fine-grained information from intermediate VFM features through condenser modules. These queries are incorporated into the decoder to support reconstruction and are jointly generated with patch tokens during generative modeling. By aggregating information from both shallow and deep layers, DecQ effectively mitigates the reconstruction--generation trade-off, improving both reconstruction quality and generative performance. Our experiments demonstrate that: (1) with only 8 additional queries and 3.9% extra computation, DecQ improves reconstruction over the frozen DINOv2-based RAE, increasing PSNR from 19.13 dB to 22.76 dB; and (2) for generative modeling, DecQ achieves 3.3$\times$ faster convergence than RAE, attaining an FID of 1.41 without guidance and 1.05 with guidance.

Tingxu Han, Wei Song, Weisong Sun et al.

With the development of deep learning, Neural Code Models (NCMs) such as CodeBERT and CodeLlama are widely used for code understanding tasks, including defect detection and code classification. However, recent studies have revealed that NCMs are vulnerable to adversarial examples, inputs with subtle perturbations that induce incorrect predictions while remaining difficult to detect. Existing defenses address this issue via data augmentation to empirically improve robustness, but they are costly, offer no theoretical robustness guarantees, and typically require white-box access to model internals, such as gradients. To address the above challenges, we propose ENBECOME, a novel black-box training-free and lightweight adversarial defense. ENBECOME is designed to both enhance empirical robustness and report certified robustness boundaries for NCMs. ENBECOME operates solely during inference, introducing random, semantics-preserving perturbations to input code snippets to smooth the NCM's decision boundaries. This smoothing enables ENBECOME to formally certify a robustness radius within which adversarial examples can never induce misclassification, a property known as certified robustness. We conduct comprehensive experiments across multiple NCM architectures and tasks. Results show that ENBECOME significantly reduces attack success rates while maintaining high accuracy. For example, in defect detection, it reduces the average ASR from 42.43% to 9.74% with only a 0.29% drop in accuracy. Results show that ENBECOME significantly reduces attack success rates while maintaining high accuracy. For example, in defect detection, it reduces the average ASR from 42.43% to 9.74% with only a 0.29% drop in accuracy. Furthermore, ENBECOME achieves an average certified robustness radius of 1.63, meaning that adversarial modifications to no more than 1.63 identifiers are provably ineffective.

Yadong Li, Haoze Sun, Mingan Lin et al.

The salient multimodal capabilities and interactive experience of GPT-4o highlight its critical role in practical applications, yet it lacks a high-performing open-source counterpart. In this paper, we introduce Baichuan-omni, the first open-source 7B Multimodal Large Language Model (MLLM) adept at concurrently processing and analyzing modalities of image, video, audio, and text, while delivering an advanced multimodal interactive experience and strong performance. We propose an effective multimodal training schema starting with 7B model and proceeding through two stages of multimodal alignment and multitask fine-tuning across audio, image, video, and text modal. This approach equips the language model with the ability to handle visual and audio data effectively. Demonstrating strong performance across various omni-modal and multimodal benchmarks, we aim for this contribution to serve as a competitive baseline for the open-source community in advancing multimodal understanding and real-time interaction.

Qiong Feng, Xiaotian Ma, Yongqiang Tian et al.

Program reduction is a technique for simplifying large, failure-inducing programs into minimal reproducible test cases. Language-specific tools such as CReduce achieve strong performance by leveraging deep semantic knowledge of C/C++, but are tightly coupled to a single language family. Language-agnostic reducers such as Perses address this by applying syntax-guided search across any grammar, yet share a fundamental limitation: deleting a node or subtree in isolation often breaks semantic coherence causing the property checker to reject the deletion and forcing the reducer to backtrack, limiting overall reduction effectiveness and efficiency. In this paper, we propose DRReduce, a framework that bridges this gap by augmenting language-agnostic syntactic reduction with a lightweight semantic layer: dependency reconstruction, which repairs program dependencies broken by a deletion in order to preserve the semantic validity of intermediate programs and increase the acceptance rate of the property checker. DRReduce constructs a semantic dependency graph from the input program, performs semantically coherent deletions with dependency reconstruction, and delegates further minimization to a syntax-guided reducer. We implement DRReduce for C and Java and evaluate it on real-world bug-triggering programs. Compared to SOTA syntax-guided reducers, DRReduce achieves average size reductions of 51.9%, 14.9%, and 19.8% over Perses, WDD, and CDD respectively, while completing reduction faster on the majority of programs. Compared to language-specific tools, DRReduce achieves results comparable to CReduce and Latra without any language-specific transformation rules, at 3.3x and 1.2x higher efficiency than CReduce and Latra on average, respectively. An ablation study confirms that dependency reconstruction reduces query invocations by 80.2%, reduction time by 58.7%, and final token count by over 55.1%.

Nuo Xu, Wen Wang, Rong Yang et al.

Object-goal navigation is a challenging task that requires guiding an agent to specific objects based on first-person visual observations. The ability of agent to comprehend its surroundings plays a crucial role in achieving successful object finding. However, existing knowledge-graph-based navigators often rely on discrete categorical one-hot vectors and vote counting strategy to construct graph representation of the scenes, which results in misalignment with visual images. To provide more accurate and coherent scene descriptions and address this misalignment issue, we propose the Aligning Knowledge Graph with Visual Perception (AKGVP) method for object-goal navigation. Technically, our approach introduces continuous modeling of the hierarchical scene architecture and leverages visual-language pre-training to align natural language description with visual perception. The integration of a continuous knowledge graph architecture and multimodal feature alignment empowers the navigator with a remarkable zero-shot navigation capability. We extensively evaluate our method using the AI2-THOR simulator and conduct a series of experiments to demonstrate the effectiveness and efficiency of our navigator. Code available: https://github.com/nuoxu/AKGVP.

Zhenchen Zhu, Ge Hu, Weixiong Tan et al.

The widespread adoption of CT has notably increased the number of detected lung nodules. However, current deep learning methods for classifying benign and malignant nodules often fail to comprehensively integrate global and local features, and most of them have not been validated through clinical trials. To address this, we developed DeepFAN, a transformer-based model trained on over 10K pathology-confirmed nodules and further conducted a multi-reader, multi-case clinical trial to evaluate its efficacy in assisting junior radiologists. DeepFAN achieved diagnostic area under the curve (AUC) of 0.939 (95% CI 0.930-0.948) on an internal test set and 0.954 (95% CI 0.934-0.973) on the clinical trial dataset involving 400 cases across three independent medical institutions. Explainability analysis indicated higher contributions from global than local features. Twelve readers' average performance significantly improved by 10.9% (95% CI 8.3%-13.5%) in AUC, 10.0% (95% CI 8.9%-11.1%) in accuracy, 7.6% (95% CI 6.1%-9.2%) in sensitivity, and 12.6% (95% CI 10.9%-14.3%) in specificity (P<0.001 for all). Nodule-level inter-reader diagnostic consistency improved from fair to moderate (overall k: 0.313 vs. 0.421; P=0.019). In conclusion, DeepFAN effectively assisted junior radiologists and may help homogenize diagnostic quality and reduce unnecessary follow-up of indeterminate pulmonary nodules. Chinese Clinical Trial Registry: ChiCTR2400084624.

Zehong Wang, Zheyuan Liu, Tianyi Ma et al.

Graph-structured data pervades domains such as social networks, biological systems, knowledge graphs, and recommender systems. While foundation models have transformed natural language processing, vision, and multimodal learning through large-scale pretraining and generalization, extending these capabilities to graphs -- characterized by non-Euclidean structures and complex relational semantics -- poses unique challenges and opens new opportunities. To this end, Graph Foundation Models (GFMs) aim to bring scalable, general-purpose intelligence to structured data, enabling broad transfer across graph-centric tasks and domains. This survey provides a comprehensive overview of GFMs, unifying diverse efforts under a modular framework comprising three key components: backbone architectures, pretraining strategies, and adaptation mechanisms. We categorize GFMs by their generalization scope -- universal, task-specific, and domain-specific -- and review representative methods, key innovations, and theoretical insights within each category. Beyond methodology, we examine theoretical foundations including transferability and emergent capabilities, and highlight key challenges such as structural alignment, heterogeneity, scalability, and evaluation. Positioned at the intersection of graph learning and general-purpose AI, GFMs are poised to become foundational infrastructure for open-ended reasoning over structured data. This survey consolidates current progress and outlines future directions to guide research in this rapidly evolving field. Resources are available at https://github.com/Zehong-Wang/Awesome-Foundation-Models-on-Graphs.

Zhifei Chen, Lata Yi, Liming Nie et al.

Software development relies heavily on traceability links between various software artifacts to ensure quality and facilitate maintenance. While automated traceability recovery techniques have advanced for different artifact pairs, the field remains fragmented with an incomplete overview of artifact associations, ambiguous linking techniques, and fragmented knowledge of application scenarios. To bridge these gaps, we conducted a systematic literature review on software traceability recovery to synthesize the linked artifacts, recovery tools, and usage scenarios across the traceability ecosystem. First, we constructed the first global artifacts traceability graph of 23 associations among 22 artifact types, exposing a severe research imbalance that heavily favors code-related links. Second, while recovery techniques are shifting toward deep semantic models, a reproducibility crisis persists (e.g., only 37% of studies released code); to address this, we provided a comprehensive evaluation framework including a technical decision map and standardized benchmarks. Finally, we quantified an industrial adoption gap (i.e., 95% of tools remain confined to academia) and proposed a role-centric framework to dynamically align artifact paths with concrete engineering activities. This review contributes a coherent knowledge framework for artifacts traceability research, identifies current trends, and provides directions for future work.

Wei Song, Zhenya Huang, Cheng Cheng et al.

Large language models (LLMs) have demonstrated exceptional performance across a wide range of natural language tasks. However, selecting the optimal LLM to respond to a user query often necessitates a delicate balance between performance and cost. While powerful models deliver better results, they come at a high cost, whereas smaller models are more cost-effective but less capable. To address this trade-off, we propose IRT-Router, a multi-LLM routing framework that efficiently routes user queries to the most suitable LLM. Inspired by Item Response Theory (IRT), a psychological measurement methodology, IRT-Router explicitly models the relationship between LLM capabilities and user query attributes. This not only enables accurate prediction of response performance but also provides interpretable insights, such as LLM abilities and query difficulty. Additionally, we design an online query warm-up technique based on semantic similarity, further enhancing the online generalization capability of IRT-Router. Extensive experiments on 20 LLMs and 12 datasets demonstrate that IRT-Router outperforms most baseline methods in terms of effectiveness and interpretability. Its superior performance in cold-start scenarios further confirms the reliability and practicality of IRT-Router in real-world applications. Code is available at https://github.com/Mercidaiha/IRT-Router.

Xingyi Wang, Chenyun Zhang, Weiji Xie et al.

Humanoid robots deployed in real-world scenarios often need to carry unknown payloads, which introduce significant mismatch and degrade the effectiveness of simulation-to-reality reinforcement learning methods. To address this challenge, we propose a two-stage gradient-based system identification framework built on the differentiable simulator MuJoCo XLA. The first stage calibrates the nominal robot model using real-world data to reduce intrinsic sim-to-real discrepancies, while the second stage further identifies the mass distribution of the unknown payload. By explicitly reducing structured model bias prior to policy training, our approach enables zero-shot transfer of reinforcement learning policies to hardware under heavy-load conditions. Extensive simulation and real-world experiments demonstrate more precise parameter identification, improved motion tracking accuracy, and substantially enhanced agility and robustness compared to existing baselines. Project Page: https://mwondering.github.io/halo-humanoid/

Zhen Liu, Yuhan Liu, Jinjun Wang et al.

Vision-and-Language Navigation requires agents to follow natural-language instructions in visually changing environments. A central challenge is the dynamic entanglement between language and observations: the meaning of instruction shifts as the agent's field of view and spatial context evolve. However, many existing models encode the instruction as a static global representation, limiting their ability to adapt instruction meaning to the current visual context. We therefore model instruction understanding as an Instruction-as-State variable: a decision-relevant, token-level instruction state that evolves step by step conditioned on the agent's perceptual state, where the perceptual state denotes the observation-grounded navigation context at each step. To realize this principle, we introduce State-Entangled Environment-Guided Instruction Understanding (S-EGIU), a coarse-to-fine framework for state-conditioned segment activation and token-level semantic refinement. At the coarse level, S-EGIU activates the instruction segment whose semantics align with the current observation. At the fine level, it refines the activated segment through observation-guided token grounding and contextual modeling, sharpening its internal semantics under the current observation. Together, these stages maintain an instruction state that is continuously updated according to the agent's perceptual state during navigation. S-EGIU delivers strong performance on several key metrics, including a +2.68% SPL gain on REVERIE Test Unseen, and demonstrates consistent efficiency gains across multiple VLN benchmarks, underscoring the value of dynamic instruction--perception entanglement.

Xinyue Li, Jian Wang, Wei Song et al.

The mainstream researche in deep metric learning can be divided into two genres: proxy-based and pair-based methods. Proxy-based methods have attracted extensive attention due to the lower training complexity and fast network convergence. However, these methods have limitations as the poxy optimization is done by network, which makes it challenging for the proxy to accurately represent the feature distrubtion of the real class of data. In this paper, we propose a Calibrate Proxy (CP) structure, which uses the real sample information to improve the similarity calculation in proxy-based loss and introduces a calibration loss to constraint the proxy optimization towards the center of the class features. At the same time, we set a small number of proxies for each class to alleviate the impact of intra-class differences on retrieval performance. The effectiveness of our method is evaluated by extensive experiments on three public datasets and multiple synthetic label-noise datasets. The results show that our approach can effectively improve the performance of commonly used proxy-based losses on both regular and noisy datasets.

Yuan Xiao, Jiaming Wang, Yuchen Chen et al.

The widespread availability of large-scale code datasets has accelerated the development of code large language models (CodeLLMs), raising concerns about unauthorized dataset usage. Dataset poisoning offers a proactive defense by reducing the utility of such unauthorized training. However, existing poisoning methods often require full dataset poisoning and introduce transformations that break code compilability. In this paper, we introduce FunPoison, a functionality-preserving poisoning approach that injects short, compilable weak-use fragments into executed code paths. FunPoison leverages reusable statement-level templates with automatic repair and conservative safety checking to ensure side-effect freedom, while a type-aware synthesis module suppresses static analysis warnings and enhances stealth. Extensive experiments show that FunPoison achieves effective poisoning by contaminating only 10% of the dataset, while maintaining 100% compilability and functional correctness, and remains robust against various advanced code sanitization techniques.

Haoxuan Li, Wei song, Peiwu Qin et al.

Breast cancer lesion segmentation in DCE-MRI remains challenging due to heterogeneous tumor morphology and indistinct boundaries. To address these challenges, this study proposes a novel hybrid segmentation network, HCMA-UNet, for lesion segmentation of breast cancer. Our network consists of a lightweight CNN backbone and a Multi-view Axial Self-Attention Mamba (MISM) module. The MISM module integrates Visual State Space Block (VSSB) and Axial Self-Attention (ASA) mechanism, effectively reducing parameters through Asymmetric Split Channel (ASC) strategy to achieve efficient tri-directional feature extraction. Our lightweight model achieves superior performance with 2.87M parameters and 126.44 GFLOPs. A Feature-guided Region-aware loss function (FRLoss) is proposed to enhance segmentation accuracy. Extensive experiments on one private and two public DCE-MRI breast cancer datasets demonstrate that our approach achieves state-of-the-art performance while maintaining computational efficiency. FRLoss also exhibits good cross-architecture generalization capabilities. The source code is available at https://github.com/Haoxuanli-Thu/HCMA-UNet.

Dianyi Wang, Wei Song, Yikun Wang et al.

Typical large vision-language models (LVLMs) apply autoregressive supervision solely to textual sequences, without fully incorporating the visual modality into the learning process. This results in three key limitations: (1) an inability to utilize images without accompanying captions, (2) the risk that captions omit critical visual details, and (3) the challenge that certain vision-centric content cannot be adequately conveyed through text. As a result, current LVLMs often prioritize vision-to-language alignment while potentially overlooking fine-grained visual information. While some prior works have explored autoregressive image generation, effectively leveraging autoregressive visual supervision to enhance image understanding remains an open challenge. In this paper, we introduce Autoregressive Semantic Visual Reconstruction (ASVR), which enables joint learning of visual and textual modalities within a unified autoregressive framework. We show that autoregressively reconstructing the raw visual appearance of images does not enhance and may even impair multimodal understanding. In contrast, autoregressively reconstructing the semantic representation of images consistently improves comprehension. Notably, we find that even when models are given continuous image features as input, they can effectively reconstruct discrete semantic tokens, resulting in stable and consistent improvements across a wide range of multimodal understanding benchmarks. Our approach delivers significant performance gains across varying data scales (556k-2M) and types of LLM bacbones. Specifically, ASVR improves LLaVA-1.5 by 5% in average scores across 14 multimodal benchmarks. The code is available at https://github.com/AlenjandroWang/ASVR.

Yuxuan Lin, Yang Chang, Xuan Tong et al.

In the advancement of industrial informatization, unsupervised anomaly detection technology effectively overcomes the scarcity of abnormal samples and significantly enhances the automation and reliability of smart manufacturing. As an important branch, industrial image anomaly detection focuses on automatically identifying visual anomalies in industrial scenarios (such as product surface defects, assembly errors, and equipment appearance anomalies) through computer vision techniques. With the rapid development of Unsupervised industrial Image Anomaly Detection (UIAD), excellent detection performance has been achieved not only in RGB setting but also in 3D and multimodal (RGB and 3D) settings. However, existing surveys primarily focus on UIAD tasks in RGB setting, with little discussion in 3D and multimodal settings. To address this gap, this artical provides a comprehensive review of UIAD tasks in the three modal settings. Specifically, we first introduce the task concept and process of UIAD. We then overview the research on UIAD in three modal settings (RGB, 3D, and multimodal), including datasets and methods, and review multimodal feature fusion strategies in multimodal setting. Finally, we summarize the main challenges faced by UIAD tasks in the three modal settings, and offer insights into future development directions, aiming to provide researchers with a comprehensive reference and offer new perspectives for the advancement of industrial informatization. Corresponding resources are available at https://github.com/Sunny5250/Awesome-Multi-Setting-UIAD.

Suyang Sun, Weifei Jin, Yuxin Cao et al.

Modern Voice Control Systems (VCS) rely on the collaboration of Automatic Speech Recognition (ASR) and Speaker Recognition (SR) for secure interaction. However, prior adversarial attacks typically target these tasks in isolation, overlooking the coupled decision pipeline in real-world scenarios. Consequently, single-task attacks often fail to pose a practical threat. To fill this gap, we first utilize gradient analysis to reveal that ASR and SR exhibit no inherent conflicts. Building on this, we propose Dual-task Universal Adversarial Perturbation (DUAP). Specifically, DUAP employs a targeted surrogate objective to effectively disrupt ASR transcription and introduces a Dynamic Normalized Ensemble (DNE) strategy to enhance transferability across diverse SR models. Furthermore, we incorporate psychoacoustic masking to ensure perturbation imperceptibility. Extensive evaluations across five ASR and six SR models demonstrate that DUAP achieves high simultaneous attack success rates and superior imperceptibility, significantly outperforming existing single-task baselines.

Haoxuan Li, Wei Song, Aofan Liu et al.

Document Visual Question Answering (Document VQA) faces significant challenges when processing long documents in low-resource environments due to context limitations and insufficient training data. This paper presents AdaDocVQA, a unified adaptive framework addressing these challenges through three core innovations: a hybrid text retrieval architecture for effective document segmentation, an intelligent data augmentation pipeline that automatically generates high-quality reasoning question-answer pairs with multi-level verification, and adaptive ensemble inference with dynamic configuration generation and early stopping mechanisms. Experiments on Japanese document VQA benchmarks demonstrate substantial improvements with 83.04\% accuracy on Yes/No questions, 52.66\% on factual questions, and 44.12\% on numerical questions in JDocQA, and 59\% accuracy on LAVA dataset. Ablation studies confirm meaningful contributions from each component, and our framework establishes new state-of-the-art results for Japanese document VQA while providing a scalable foundation for other low-resource languages and specialized domains. Our code available at: https://github.com/Haoxuanli-Thu/AdaDocVQA.

Bingyu Nan, Feng Liu, Xuezhong Qian et al.

Facial expression recognition is an important research direction in the field of artificial intelligence. Although new breakthroughs have been made in recent years, the uneven distribution of datasets and the similarity between different categories of facial expressions, as well as the differences within the same category among different subjects, remain challenges. This paper proposes a visual facial expression signal feature processing network based on truncated ConvNeXt approach(Conv-cut), to improve the accuracy of FER under challenging conditions. The network uses a truncated ConvNeXt-Base as the feature extractor, and then we designed a Detail Extraction Block to extract detailed features, and introduced a Self-Attention mechanism to enable the network to learn the extracted features more effectively. To evaluate the proposed Conv-cut approach, we conducted experiments on the RAF-DB and FERPlus datasets, and the results show that our model has achieved state-of-the-art performance. Our code could be accessed at Github.

Wei Song, Yadong Li, Jianhua Xu et al.

As recent multi-modality large language models (MLLMs) have shown formidable proficiency on various complex tasks, there has been increasing attention on debating whether these models could eventually mirror human intelligence. However, existing benchmarks mainly focus on evaluating solely on task performance, such as the accuracy of identifying the attribute of an object. Combining well-developed cognitive science to understand the intelligence of MLLMs beyond superficial achievements remains largely unexplored. To this end, we introduce the first cognitive-driven multi-lingual and multi-modal benchmark to evaluate the general intelligence ability of MLLMs, dubbed M3GIA. Specifically, we identify five key cognitive factors based on the well-recognized Cattell-Horn-Carrol (CHC) model of intelligence and propose a novel evaluation metric. In addition, since most MLLMs are trained to perform in different languages, a natural question arises: is language a key factor influencing the cognitive ability of MLLMs? As such, we go beyond English to encompass other languages based on their popularity, including Chinese, French, Spanish, Portuguese and Korean, to construct our M3GIA. We make sure all the data relevant to the cultural backgrounds are collected from their native context to avoid English-centric bias. We collected a significant corpus of data from human participants, revealing that the most advanced MLLM reaches the lower boundary of human intelligence in English. Yet, there remains a pronounced disparity in the other five languages assessed. We also reveals an interesting winner takes all phenomenon that are aligned with the discovery in cognitive studies. Our benchmark will be open-sourced, with the aspiration of facilitating the enhancement of cognitive capabilities in MLLMs.

Haoxuan Li, Wei Song, Aofan Liu et al.

Medical image analysis faces significant challenges due to limited annotation data, particularly in three-dimensional carotid artery segmentation tasks, where existing datasets exhibit spatially discontinuous slice annotations with only a small portion of expert-labeled slices in complete 3D volumetric data. To address this challenge, we propose a two-stage segmentation framework. First, we construct continuous vessel centerlines by interpolating between annotated slice centroids and propagate labels along these centerlines to generate interpolated annotations for unlabeled slices. The slices with expert annotations are used for fine-tuning SAM-Med2D, while the interpolated labels on unlabeled slices serve as prompts to guide segmentation during inference. In the second stage, we propose a novel Dense Bidirectional Feature Fusion UNet (DBF-UNet). This lightweight architecture achieves precise segmentation of complete 3D vascular structures. The network incorporates bidirectional feature fusion in the encoder and integrates multi-scale feature aggregation with dense connectivity for effective feature reuse. Experimental validation on public datasets demonstrates that our proposed method effectively addresses the sparse annotation challenge in carotid artery segmentation while achieving superior performance compared to existing approaches. The source code is available at https://github.com/Haoxuanli-Thu/DBF-UNet.

Qiong Feng, Xiaotian Ma, Jiayi Sheng et al.

LLMs have garnered considerable attention for their potential to streamline Automated Program Repair (APR). LLM-based approaches can either insert the correct code or directly generate patches when provided with buggy methods. However, most of LLM-based APR methods rely on a single type of software information, without fully leveraging different software artifacts. Despite this, many LLM-based approaches do not explore which specific types of information best assist in APR. Addressing this gap is crucial for advancing LLM-based APR techniques. We propose DEVLoRe to use issue content (description and message) and stack error traces to localize buggy methods, then rely on debug information in buggy methods and issue content and stack error to localize buggy lines and generate plausible patches which can pass all unit tests. The results show that while issue content is particularly effective in assisting LLMs with fault localization and program repair, different types of software artifacts complement each other. By incorporating different artifacts, DEVLoRe successfully locates 49.3% and 47.6% of single and non-single buggy methods and generates 56.0% and 14.5% plausible patches for the Defects4J v2.0 dataset, respectively. This outperforms current state-of-the-art APR methods. Furthermore, we re-implemented and evaluated our framework, demonstrating its effectiveness in its effectiveness in resolving 9 unique issues compared to other state-of-the-art frameworks using the same or more advanced models on SWE-bench Lite.We also discussed whether a leading framework for Python code can be directly applied to Java code, or vice versa. The source code and experimental results of this work for replication are available at https://github.com/XYZboom/DEVLoRe.

Wei Song, Jiameng Ying, Sihao Shen et al.

Memory safety remains a critical and widely violated property in reality. Numerous defense techniques have been proposed and developed but most of them are not applied or enabled by default in production-ready environment due to their substantial running cost. The situation might change in the near future because the hardware supported defenses against these attacks are finally beginning to be adopted by commercial processors, operating systems and compilers. We then face a question as there is currently no suitable test suite to measure the memory safety extensions supported on different processors. In fact, the issue is not constrained only for memory safety but all aspect of processor security. All of the existing test suites related to processor security lack some of the key properties, such as comprehensiveness, distinguishability and portability. As an initial step, we propose an expandable test framework for measuring the processor security and open source a memory safety test suite utilizing this framework. The framework is deliberately designed to be flexible so it can be gradually extended to all types of hardware supported security extensions in processors. The initial test suite for memory safety currently contains 160 test cases covering spatial and temporal safety of memory, memory access control, pointer integrity and control-flow integrity. Each type of vulnerabilities and their related defenses have been individually evaluated by one or more test cases. The test suite has been ported to three different instruction set architectures (ISAs) and experimented on six different platforms. We have also utilized the test suite to explore the security benefits of applying different sets of compiler flags available on the latest GNU GCC and LLVM compilers.

Yan Wang, Wei Song, Giancarlo Fortino et al.

Underwater images play a key role in ocean exploration, but often suffer from severe quality degradation due to light absorption and scattering in water medium. Although major breakthroughs have been made recently in the general area of image enhancement and restoration, the applicability of new methods for improving the quality of underwater images has not specifically been captured. In this paper, we review the image enhancement and restoration methods that tackle typical underwater image impairments, including some extreme degradations and distortions. Firstly, we introduce the key causes of quality reduction in underwater images, in terms of the underwater image formation model (IFM). Then, we review underwater restoration methods, considering both the IFM-free and the IFM-based approaches. Next, we present an experimental-based comparative evaluation of state-of-the-art IFM-free and IFM-based methods, considering also the prior-based parameter estimation algorithms of the IFM-based methods, using both subjective and objective analysis (the used code is freely available at https://github.com/wangyanckxx/Single-Underwater-Image-Enhancement-and-Color-Restoration). Starting from this study, we pinpoint the key shortcomings of existing methods, drawing recommendations for future research in this area. Our review of underwater image enhancement and restoration provides researchers with the necessary background to appreciate challenges and opportunities in this important field.

Yadong Li, Jun Liu, Tao Zhang et al.

We introduce Baichuan-Omni-1.5, an omni-modal model that not only has omni-modal understanding capabilities but also provides end-to-end audio generation capabilities. To achieve fluent and high-quality interaction across modalities without compromising the capabilities of any modality, we prioritized optimizing three key aspects. First, we establish a comprehensive data cleaning and synthesis pipeline for multimodal data, obtaining about 500B high-quality data (text, audio, and vision). Second, an audio-tokenizer (Baichuan-Audio-Tokenizer) has been designed to capture both semantic and acoustic information from audio, enabling seamless integration and enhanced compatibility with MLLM. Lastly, we designed a multi-stage training strategy that progressively integrates multimodal alignment and multitask fine-tuning, ensuring effective synergy across all modalities. Baichuan-Omni-1.5 leads contemporary models (including GPT4o-mini and MiniCPM-o 2.6) in terms of comprehensive omni-modal capabilities. Notably, it achieves results comparable to leading models such as Qwen2-VL-72B across various multimodal medical benchmarks.

Wang Xing, Wei Song, Siyu Lin et al.

Reasoning over temporal knowledge graphs (TKGs) is fundamental to improving the efficiency and reliability of intelligent decision-making systems and has become a key technological foundation for future artificial intelligence applications. Despite recent progress, existing TKG reasoning models typically rely on large parameter sizes and intensive computation, leading to high hardware costs and energy consumption. These constraints hinder their deployment on resource-constrained, low-power, and distributed platforms that require real-time inference. Moreover, most existing model compression and distillation techniques are designed for static knowledge graphs and fail to adequately capture the temporal dependencies inherent in TKGs, often resulting in degraded reasoning performance. To address these challenges, we propose a distillation framework specifically tailored for temporal knowledge graph reasoning. Our approach leverages large language models as teacher models to guide the distillation process, enabling effective transfer of both structural and temporal reasoning capabilities to lightweight student models. By integrating large-scale public knowledge with task-specific temporal information, the proposed framework enhances the student model's ability to model temporal dynamics while maintaining a compact and efficient architecture. Extensive experiments on multiple publicly available benchmark datasets demonstrate that our method consistently outperforms strong baselines, achieving a favorable trade-off between reasoning accuracy, computational efficiency, and practical deployability.

Marcos V. Conde, Radu Timofte, Zihao Lu et al.

This paper reviews the NTIRE 2025 RAW Image Restoration and Super-Resolution Challenge, highlighting the proposed solutions and results. New methods for RAW Restoration and Super-Resolution could be essential in modern Image Signal Processing (ISP) pipelines, however, this problem is not as explored as in the RGB domain. The goal of this challenge is two fold, (i) restore RAW images with blur and noise degradations, (ii) upscale RAW Bayer images by 2x, considering unknown noise and blur. In the challenge, a total of 230 participants registered, and 45 submitted results during thee challenge period. This report presents the current state-of-the-art in RAW Restoration.

Wei Song, Yuxin Cao, Ziqi Ding et al.

Video large language models (VideoLLMs) are increasingly trained or instruction-tuned on large-scale video--text corpora collected from heterogeneous sources, raising an immediate privacy question: can an external auditor determine whether a particular video was used during training? While membership inference attacks (MIAs) have been studied extensively for classifiers and, more recently, for text and image generation models, the VideoLLM setting remains unexplored. This setting is challenging because black-box auditors observe only generated text, whereas the membership signal is entangled with video-specific factors such as motion complexity and temporal span. In this paper, we present a black-box MIA targeting VideoLLMs that couples temperature-perturbed generation with video-aware difficulty features. Our key intuition is that member samples tend to induce sharper, more brittle generation behavior across decoding temperatures, and that this signal should be interpreted jointly with the intrinsic difficulty of the queried video. Concretely, we query the target model at low and high temperatures, measure the semantic drift between the resulting texts. We evaluate the attack against \texttt{LLaVA-Video-7B-Qwen2-Video-Only} and achieve a member inference AUC of 0.68 and accuracy of 0.63. These results demonstrate that Video-LLMs are vulnerable to black-box membership inference attacks, highlighting an urgent need for the community to systematically evaluate and mitigate privacy risks in VideoLLMs.

Wei Song, Yuran Wang, Zijia Song et al.

The differing representation spaces required for visual understanding and generation pose a challenge in unifying them within the autoregressive paradigm of large language models. A vision tokenizer trained for reconstruction excels at capturing low-level perceptual details, making it well-suited for visual generation but lacking high-level semantic representations for understanding tasks. Conversely, a vision encoder trained via contrastive learning aligns well with language but struggles to decode back into the pixel space for generation tasks. To bridge this gap, we propose DualToken, a method that unifies representations for both understanding and generation within a single tokenizer. However, directly integrating reconstruction and semantic objectives in a single tokenizer creates conflicts, leading to degraded performance in both reconstruction quality and semantic performance. Instead of forcing a single codebook to handle both semantic and perceptual information, DualToken disentangles them by introducing separate codebooks for high and low-level features, effectively transforming their inherent conflict into a synergistic relationship. As a result, DualToken achieves state-of-the-art performance in both reconstruction and semantic tasks while demonstrating remarkable effectiveness in downstream MLLM understanding and generation tasks. Notably, we also show that DualToken, as a unified tokenizer, surpasses the naive combination of two distinct types vision encoders, providing superior performance within a unified MLLM.

Wang Xing, Wei Song, Siyu Lin et al.

Temporal knowledge graphs (TKGs) support reasoning over time-evolving facts, yet state-of-the-art models are often computationally heavy and costly to deploy. Existing compression and distillation techniques are largely designed for static graphs; directly applying them to temporal settings may overlook time-dependent interactions and lead to performance degradation. We propose an LLM-assisted distillation framework specifically designed for temporal knowledge graph reasoning. Beyond a conventional high-capacity temporal teacher, we incorporate a large language model as an auxiliary instructor to provide enriched supervision. The LLM supplies broad background knowledge and temporally informed signals, enabling a lightweight student to better model event dynamics without increasing inference-time complexity. Training is conducted by jointly optimizing supervised and distillation objectives, using a staged alignment strategy to progressively integrate guidance from both teachers. Extensive experiments on multiple public TKG benchmarks with diverse backbone architectures demonstrate that the proposed approach consistently improves link prediction performance over strong distillation baselines, while maintaining a compact and efficient student model. The results highlight the potential of large language models as effective teachers for transferring temporal reasoning capability to resource-efficient TKG systems.

Zhen Liu, Yuhan Liu, Jinjun Wang et al.

In vision-and-language navigation (VLN), self-improvement from policy-induced experience, using only standard VLN action supervision, critically depends on balancing behavioral diversity and learning stability, which governs whether the agent can extract a reliable learning signal for improvement. Increasing behavioral diversity is necessary to expose alternative action hypotheses but can destabilize policy-induced learning signals, whereas overly conservative stability constraints suppress exploration and induce early commitment, making reliable self-improvement difficult. To address this challenge, we propose Stability-Diversity Balance (SDB), a plug-and-play mechanism for balanced self-improvement in VLN. SDB expands each decision step into multiple latent behavioral hypotheses by applying controlled shifts in the instruction-conditioned hidden states, and then performs reliability-aware soft evaluation and aggregation to retain diverse yet instruction-consistent alternatives during learning. An explicit regularizer further constrains hypothesis interactions, preventing excessive drift or premature collapse of hypothesis diversity and stabilizing self-improvement without discarding training signals. Experiments on R2R, SOON, and REVERIE show consistent improvements; for example, on REVERIE val-unseen, SDB improves SPL from 33.73 to 35.93 and OSR from 51.07 to 54.25.

Junxiong Lin, Yan Wang, Zeng Tao et al.

Pre-trained diffusion models utilized for image generation encapsulate a substantial reservoir of a priori knowledge pertaining to intricate textures. Harnessing the potential of leveraging this a priori knowledge in the context of image super-resolution presents a compelling avenue. Nonetheless, prevailing diffusion-based methodologies presently overlook the constraints imposed by degradation information on the diffusion process. Furthermore, these methods fail to consider the spatial variability inherent in the estimated blur kernel, stemming from factors such as motion jitter and out-of-focus elements in open-environment scenarios. This oversight results in a notable deviation of the image super-resolution effect from fundamental realities. To address these concerns, we introduce a framework known as Adaptive Multi-modal Fusion of \textbf{S}patially Variant Kernel Refinement with Diffusion Model for Blind Image \textbf{S}uper-\textbf{R}esolution (SSR). Within the SSR framework, we propose a Spatially Variant Kernel Refinement (SVKR) module. SVKR estimates a Depth-Informed Kernel, which takes the depth information into account and is spatially variant. Additionally, SVKR enhance the accuracy of depth information acquired from LR images, allowing for mutual enhancement between the depth map and blur kernel estimates. Finally, we introduce the Adaptive Multi-Modal Fusion (AMF) module to align the information from three modalities: low-resolution images, depth maps, and blur kernels. This alignment can constrain the diffusion model to generate more authentic SR results.

Yanfang Ye, Zheyuan Zhang, Tianyi Ma et al.

Cutting-edge Artificial Intelligence (AI) techniques keep reshaping our view of the world. For example, Large Language Models (LLMs) based applications such as ChatGPT have shown the capability of generating human-like conversation on extensive topics. Due to the impressive performance on a variety of language-related tasks (e.g., open-domain question answering, translation, and document summarization), one can envision the far-reaching impacts that can be brought by the LLMs with broader real-world applications (e.g., customer service, education and accessibility, and scientific discovery). Inspired by their success, this paper will offer an overview of state-of-the-art LLMs and their integration into a wide range of academic disciplines, including: (1) arts, letters, and law (e.g., history, philosophy, political science, arts and architecture, law), (2) economics and business (e.g., finance, economics, accounting, marketing), and (3) science and engineering (e.g., mathematics, physics and mechanical engineering, chemistry and chemical engineering, life sciences and bioengineering, earth sciences and civil engineering, computer science and electrical engineering). Integrating humanity and technology, in this paper, we will explore how LLMs are shaping research and practice in these fields, while also discussing key limitations, open challenges, and future directions in the era of generative AI. The review of how LLMs are engaged across disciplines-along with key observations and insights-can help researchers and practitioners interested in exploiting LLMs to advance their works in diverse real-world applications.