Zhuoran Zhang

Tengfei Liu, Yang Shi, Xuanyu Zhu et al.

Audio-visual generation is rapidly advancing from short clips to minute-long content, while existing evaluation protocols remain largely confined to short-form settings. Existing benchmarks primarily focus on 5--10 second text-conditioned generation and rarely support unified evaluation across text, image, and video conditioning modalities. Moreover, they provide limited insight into how identity consistency, narrative coherence, and audio-visual alignment degrade over extended temporal horizons. To bridge this gap, we introduce LongAV-Compass, a systematic benchmark for minute-long audio-visual generation. LongAV-Compass contains 284 curated test cases spanning text-to-audio-video (T2AV), image-to-audio-video (I2AV), and video-to-audio-video (V2AV), organized by application scenario and generation complexity. The benchmark combines taxonomy-guided benchmark construction with a unified evaluation framework that integrates MLLM-assisted assessment with complementary perceptual and multimodal metrics, including DINO-v2, ArcFace, CLIP, and ImageBind. The framework evaluates more than 20 fine-grained dimensions covering within-segment quality, cross-segment consistency, global narrative coherence, semantic alignment, and audio-visual synchronization. Through experiments on 11 representative models together with human-alignment validation, LongAV-Compass provides a diagnostic testbed for analyzing the limitations of current systems in sustaining coherent, semantically aligned, and temporally consistent minute-scale audio-visual generation across diverse input modalities.

Wenyuan Chen, Haocong Song, Changsheng Dai et al.

Traditional sperm morphology analysis is based on tedious manual annotation. Automated morphology analysis of a high number of sperm requires accurate segmentation of each sperm part and quantitative morphology evaluation. State-of-the-art instance-aware part segmentation networks follow a "detect-then-segment" paradigm. However, due to sperm's slim shape, their segmentation suffers from large context loss and feature distortion due to bounding box cropping and resizing during ROI Align. Moreover, morphology measurement of sperm tail is demanding because of the long and curved shape and its uneven width. This paper presents automated techniques to measure sperm morphology parameters automatically and quantitatively. A novel attention-based instance-aware part segmentation network is designed to reconstruct lost contexts outside bounding boxes and to fix distorted features, by refining preliminary segmented masks through merging features extracted by feature pyramid network. An automated centerline-based tail morphology measurement method is also proposed, in which an outlier filtering method and endpoint detection algorithm are designed to accurately reconstruct tail endpoints. Experimental results demonstrate that the proposed network outperformed the state-of-the-art top-down RP-R-CNN by 9.2% [AP]_vol^p, and the proposed automated tail morphology measurement method achieved high measurement accuracies of 95.34%,96.39%,91.2% for length, width and curvature, respectively.

Zhuoran Zhang, Tengyue Wang, Xilin Gong et al.

Multimodal large language models (MLLMs) must resolve conflicts when different modalities provide contradictory information, a process we term modality following. Prior work measured this behavior only with coarse dataset-level statistics, overlooking the influence of model's confidence in unimodal reasoning. In this paper, we introduce a new framework that decomposes modality following into two fundamental factors: relative reasoning uncertainty (the case-specific confidence gap between unimodal predictions) and inherent modality preference( a model's stable bias when uncertainties are balanced). To validate this framework, we construct a controllable dataset that systematically varies the reasoning difficulty of visual and textual inputs. Using entropy as a fine-grained uncertainty metric, we uncover a universal law: the probability of following a modality decreases monotonically as its relative uncertainty increases. At the relative difficulty level where the model tends to follow both modalities with comparable probability what we call the balance point, a practical indicator of the model's inherent preference. Unlike traditional macro-level ratios, this measure offers a more principled and less confounded way to characterize modality bias, disentangling it from unimodal capabilities and dataset artifacts. Further, by probing layer-wise predictions, we reveal the internal mechanism of oscillation: in ambiguous regions near the balance point, models vacillate between modalities across layers, explaining externally observed indecision. Together, these findings establish relative uncertainty and inherent preference as the two governing principles of modality following, offering both a quantitative framework and mechanistic insight into how MLLMs resolve conflicting information.

Yuqi Tang, Yang Shi, Zhuoran Zhang et al.

Recent video generative models have greatly improved the realism of AI-generated videos, yet their outputs still exhibit artifacts such as temporal inconsistencies, structural distortions, and semantic incoherence. While Multimodal Large Language Models (MLLMs) show strong visual understanding capabilities, their ability to perceive and reason about such artifacts remains unclear. Existing benchmarks often lack systematic evaluation of artifact-aware perception and fine-grained diagnostic reasoning, especially across diverse AI-generated video domains beyond photorealistic content. To address this gap, we introduce Artifact-Bench, a comprehensive benchmark for evaluating MLLMs on AI-generated video artifact detection and analysis. We first establish a three-level hierarchical taxonomy of realism artifacts, covering photorealistic, animated, and CG-style videos. Based on this taxonomy, Artifact-Bench defines three complementary tasks: real vs. AI-generated video classification, pairwise realism comparison, and fine-grained artifact identification. Experiments on 19 leading MLLMs reveal substantial limitations in artifact perception and reasoning, with many models approaching random or even below-random performance in challenging settings. We further observe significant misalignment between MLLM judgments and human perceptual preferences, highlighting their limited reliability as general evaluators for AI-generated video realism.

Keyuan Cheng, Zijian Kan, Zhixian He et al.

Knowledge Editing, which efficiently modifies the knowledge in large language models, has gathered great attention. Current benchmarks primarily use multi-hop question answering to assess and analyze newly injected or updated knowledge. However, we argue that these benchmarks fail to effectively evaluate how well the updated models apply this knowledge in real-life scenarios, particularly when questions require complex reasoning, involving one-to-many relationships or multi-step logical intersections. To fill in this gap, we introduce a new benchmark, COMPKE: Complex Question Answering under Knowledge Editing, which includes 11,924 complex questions that reflect real-life situations. We conduct an extensive evaluation of four knowledge editing methods on COMPKE, revealing that their effectiveness varies notably across different models. For instance, MeLLo attains an accuracy of 39.47 on GPT-4O-MINI, but this drops sharply to 3.83 on QWEN2.5-3B. We further investigate the underlying causes of these disparities from both methodological and model-specific perspectives. The datasets are available at https://github.com/kzjkzj666/CompKE.

Lin Zhang, Wenshuo Dong, Zhuoran Zhang et al.

Understanding the internal mechanisms of transformer-based language models remains challenging. Mechanistic interpretability based on circuit discovery aims to reverse engineer neural networks by analyzing their internal processes at the level of computational subgraphs. In this paper, we revisit existing gradient-based circuit identification methods and find that their performance is either affected by the zero-gradient problem or saturation effects, where edge attribution scores become insensitive to input changes, resulting in noisy and unreliable attribution evaluations for circuit components. To address the saturation effect, we propose Edge Attribution Patching with GradPath (EAP-GP), EAP-GP introduces an integration path, starting from the input and adaptively following the direction of the difference between the gradients of corrupted and clean inputs to avoid the saturated region. This approach enhances attribution reliability and improves the faithfulness of circuit identification. We evaluate EAP-GP on 6 datasets using GPT-2 Small, GPT-2 Medium, and GPT-2 XL. Experimental results demonstrate that EAP-GP outperforms existing methods in circuit faithfulness, achieving improvements up to 17.7%. Comparisons with manually annotated ground-truth circuits demonstrate that EAP-GP achieves precision and recall comparable to or better than previous approaches, highlighting its effectiveness in identifying accurate circuits.

Keyu Wang, Jin Li, Shu Yang et al.

Large Language Models (LLMs) often exhibit sycophantic behavior, agreeing with user-stated opinions even when those contradict factual knowledge. While prior work has documented this tendency, the internal mechanisms that enable such behavior remain poorly understood. In this paper, we provide a mechanistic account of how sycophancy arises within LLMs. We first systematically study how user opinions induce sycophancy across different model families. We find that simple opinion statements reliably induce sycophancy, whereas user expertise framing has a negligible impact. Through logit-lens analysis and causal activation patching, we identify a two-stage emergence of sycophancy: (1) a late-layer output preference shift and (2) deeper representational divergence. We also verify that user authority fails to influence behavior because models do not encode it internally. In addition, we examine how grammatical perspective affects sycophantic behavior, finding that first-person prompts (``I believe...'') consistently induce higher sycophancy rates than third-person framings (``They believe...'') by creating stronger representational perturbations in deeper layers. These findings highlight that sycophancy is not a surface-level artifact but emerges from a structural override of learned knowledge in deeper layers, with implications for alignment and truthful AI systems.

Yang Shi, Huanqian Wang, Wulin Xie et al. · pku

Multimodal Large Language Models (MLLMs) have achieved considerable accuracy in Optical Character Recognition (OCR) from static images. However, their efficacy in video OCR is significantly diminished due to factors such as motion blur, temporal variations, and visual effects inherent in video content. To provide clearer guidance for training practical MLLMs, we introduce the MME-VideoOCR benchmark, which encompasses a comprehensive range of video OCR application scenarios. MME-VideoOCR features 10 task categories comprising 25 individual tasks and spans 44 diverse scenarios. These tasks extend beyond text recognition to incorporate deeper comprehension and reasoning of textual content within videos. The benchmark consists of 1,464 videos with varying resolutions, aspect ratios, and durations, along with 2,000 meticulously curated, manually annotated question-answer pairs. We evaluate 18 state-of-the-art MLLMs on MME-VideoOCR, revealing that even the best-performing model (Gemini-2.5 Pro) achieves an accuracy of only 73.7%. Fine-grained analysis indicates that while existing MLLMs demonstrate strong performance on tasks where relevant texts are contained within a single or few frames, they exhibit limited capability in effectively handling tasks that demand holistic video comprehension. These limitations are especially evident in scenarios that require spatio-temporal reasoning, cross-frame information integration, or resistance to language prior bias. Our findings also highlight the importance of high-resolution visual input and sufficient temporal coverage for reliable OCR in dynamic video scenarios.

Yang Shi, Yuhao Dong, Yue Ding et al.

The integration of visual understanding and generation into unified multimodal models represents a significant stride toward general-purpose AI. However, a fundamental question remains unanswered by existing benchmarks: does this architectural unification actually enable synergetic interaction between the constituent capabilities? Existing evaluation paradigms, which primarily assess understanding and generation in isolation, are insufficient for determining whether a unified model can leverage its understanding to enhance its generation, or use generative simulation to facilitate deeper comprehension. To address this critical gap, we introduce RealUnify, a benchmark specifically designed to evaluate bidirectional capability synergy. RealUnify comprises 1,000 meticulously human-annotated instances spanning 10 categories and 32 subtasks. It is structured around two core axes: 1) Understanding Enhances Generation, which requires reasoning (e.g., commonsense, logic) to guide image generation, and 2) Generation Enhances Understanding, which necessitates mental simulation or reconstruction (e.g., of transformed or disordered visual inputs) to solve reasoning tasks. A key contribution is our dual-evaluation protocol, which combines direct end-to-end assessment with a diagnostic stepwise evaluation that decomposes tasks into distinct understanding and generation phases. This protocol allows us to precisely discern whether performance bottlenecks stem from deficiencies in core abilities or from a failure to integrate them. Through large-scale evaluations of 12 leading unified models and 6 specialized baselines, we find that current unified models still struggle to achieve effective synergy, indicating that architectural unification alone is insufficient. These results highlight the need for new training strategies and inductive biases to fully unlock the potential of unified modeling.

Keer Lu, Keshi Zhao, Zhuoran Zhang et al.

As demonstrated by the proprietary Large Language Models (LLMs) such as GPT and Claude series, LLMs have the potential to achieve remarkable proficiency across a wide range of domains, including law, medicine, finance, science, code, etc., all within a single model. These capabilities are further augmented during the Supervised Fine-Tuning (SFT) phase. Despite their potential, existing work mainly focuses on domain-specific enhancements during fine-tuning, the challenge of which lies in catastrophic forgetting of knowledge across other domains. In this study, we introduce **VersaTune**, a novel data composition framework designed for enhancing LLMs' overall multi-domain capabilities during training. We begin with detecting the distribution of domain-specific knowledge within the base model, followed by the training data composition that aligns with the model's existing knowledge distribution. During the subsequent training process, domain weights are dynamically adjusted based on their learnable potential and forgetting degree. Experimental results indicate that VersaTune is effective in multi-domain fostering, with an improvement of 35.21\% in the overall multi-ability performances compared to uniform domain weights. Furthermore, we find that Qwen-2.5-32B + VersaTune even surpasses frontier models, including GPT-4o, Claude3.5-Sonnet and DeepSeek-V3 by 0.86\%, 4.76\% and 4.60\%. Additionally, in scenarios where flexible expansion of a specific domain is required, VersaTune reduces the performance degradation in other domains by 38.77\%, while preserving the training efficacy of the target domain.

Fei Yu, Zhe Xiang, Nan Che et al.

Multimodal semantic communication, which integrates various data modalities such as text, images, and audio, significantly enhances communication efficiency and reliability. It has broad application prospects in fields such as artificial intelligence, autonomous driving, and smart homes. However, current research primarily relies on analog channels and assumes constant channel states (perfect CSI), which is inadequate for addressing dynamic physical channels and noise in real-world scenarios. Existing methods often focus on single modality tasks and fail to handle multimodal stream data, such as video and audio, and their corresponding tasks. Furthermore, current semantic encoding and decoding modules mainly transmit single modality features, neglecting the need for multimodal semantic enhancement and recognition tasks. To address these challenges, this paper proposes a pilot-guided framework for multimodal semantic communication specifically tailored for audio-visual event localization tasks. This framework utilizes digital pilot codes and channel modules to guide the state of analog channels in real-wold scenarios and designs Euler-based multimodal semantic encoding and decoding that consider time-frequency characteristics based on dynamic channel state. This approach effectively handles multimodal stream source data, especially for audio-visual event localization tasks. Extensive numerical experiments demonstrate the robustness of the proposed framework in channel changes and its support for various communication scenarios. The experimental results show that the framework outperforms existing benchmark methods in terms of Signal-to-Noise Ratio (SNR), highlighting its advantage in semantic communication quality.

Yiwei Wang, Tao Yang, Hailin Huang et al.

This paper presents a data-driven electrical machine design (EMD) framework using wound-rotor synchronous generator (WRSG) as a design example. Unlike traditional preliminary EMD processes that heavily rely on expertise, this framework leverages an artificial-intelligence based expert database, to provide preliminary designs directly from user specifications. Initial data is generated using 2D finite element (FE) machine models by sweeping fundamental design variables including machine length and diameter, enabling scalable machine geometry with machine performance for each design is recorded. This data trains a Metamodel of Optimal Prognosis (MOP)-based surrogate model, which maps design variables to key performance indicators (KPIs). Once trained, guided by metaheuristic algorithms, the surrogate model can generate thousands of geometric scalable designs, covering a wide power range, forming an AI expert database to guide future preliminary design. The framework is validated with a 30kVA WRSG design case. A prebuilt WRSG database, covering power from 10 to 60kVA, is validated by FE simulation. Design No.1138 is selected from database and compared with conventional design. Results show No.1138 achieves a higher power density of 2.21 kVA/kg in just 5 seconds, compared to 2.02 kVA/kg obtained using traditional method, which take several days. The developed AI expert database also serves as a high-quality data source for further developing AI models for automatic electrical machine design.