Zikai Song

Ying Tang, Dong Li, Youjia Zhang et al.

Unifying the complementary strengths of diverse Vision Foundation Models (VFMs) into a single efficient model is highly desirable but challenged by the negative transfer inherent in monolithic distillation. To address these feature conflicts, we introduce \textbf{PRISM}, a novel dual-stream Mixture-of-Experts (MoE) framework that synergizes VFMs via modular specialization. We propose a two-stage paradigm: (1) expertise deconstruction, where a teacher-conditional router guides experts to specialize in distinct representational subspaces to mitigate interference, followed by (2) dynamic recomposition, where the router learns to assemble these experts into tailored computational pathways for downstream tasks. Experiments on PASCAL-Context and NYUD-v2 show that \textbf{PRISM} establishes a new state of the art, validating that sparse, emergent specialization is a scalable approach for integrating diverse visual knowledge.

Zikai Song, Run Luo, Junqing Yu et al.

Transformer framework has been showing superior performances in visual object tracking for its great strength in information aggregation across the template and search image with the well-known attention mechanism. Most recent advances focus on exploring attention mechanism variants for better information aggregation. We find these schemes are equivalent to or even just a subset of the basic self-attention mechanism. In this paper, we prove that the vanilla self-attention structure is sufficient for information aggregation, and structural adaption is unnecessary. The key is not the attention structure, but how to extract the discriminative feature for tracking and enhance the communication between the target and search image. Based on this finding, we adopt the basic vision transformer (ViT) architecture as our main tracker and concatenate the template and search image for feature embedding. To guide the encoder to capture the invariant feature for tracking, we attach a lightweight correlative masked decoder which reconstructs the original template and search image from the corresponding masked tokens. The correlative masked decoder serves as a plugin for the compact transform tracker and is skipped in inference. Our compact tracker uses the most simple structure which only consists of a ViT backbone and a box head, and can run at 40 fps. Extensive experiments show the proposed compact transform tracker outperforms existing approaches, including advanced attention variants, and demonstrates the sufficiency of self-attention in tracking tasks. Our method achieves state-of-the-art performance on five challenging datasets, along with the VOT2020, UAV123, LaSOT, TrackingNet, and GOT-10k benchmarks. Our project is available at https://github.com/HUSTDML/CTTrack.

Xinglang Zhang, Yunyao Zhang, ZeLiang Chen et al.

Symbolic logical reasoning is a critical yet underexplored capability of large language models (LLMs), providing reliable and verifiable decision-making in high-stakes domains such as mathematical reasoning and legal judgment. In this study, we present a systematic analysis of logical reasoning under controlled increases in logical complexity, and reveal a previously unrecognized phenomenon, which we term Logical Phase Transitions: rather than degrading smoothly, logical reasoning performance remains stable within a regime but collapses abruptly beyond a critical logical depth, mirroring physical phase transitions such as water freezing beyond a critical temperature threshold. Building on this insight, we propose Neuro-Symbolic Curriculum Tuning, a principled framework that adaptively aligns natural language with logical symbols to establish a shared representation, and reshapes training dynamics around phase-transition boundaries to progressively strengthen reasoning at increasing logical depths. Experiments on five benchmarks show that our approach effectively mitigates logical reasoning collapse at high complexity, yielding average accuracy gains of +1.26 in naive prompting and +3.95 in CoT, while improving generalization to unseen logical compositions. Code and data are available at https://github.com/AI4SS/Logical-Phase-Transitions.

Zikai Song, Junqing Yu, Yi-Ping Phoebe Chen et al.

Transformer architecture has been showing its great strength in visual object tracking, for its effective attention mechanism. Existing transformer-based approaches adopt the pixel-to-pixel attention strategy on flattened image features and unavoidably ignore the integrity of objects. In this paper, we propose a new transformer architecture with multi-scale cyclic shifting window attention for visual object tracking, elevating the attention from pixel to window level. The cross-window multi-scale attention has the advantage of aggregating attention at different scales and generates the best fine-scale match for the target object. Furthermore, the cyclic shifting strategy brings greater accuracy by expanding the window samples with positional information, and at the same time saves huge amounts of computational power by removing redundant calculations. Extensive experiments demonstrate the superior performance of our method, which also sets the new state-of-the-art records on five challenging datasets, along with the VOT2020, UAV123, LaSOT, TrackingNet, and GOT-10k benchmarks.

Yunyao Zhang, Yihao Ai, Zuocheng Ying et al.

Social network simulation aims to model collective opinion dynamics in large populations, but existing LLM-based simulators mainly focus on aggregate dynamics while largely ignoring individual internal states. This limits their ability to capture opinion reversals driven by gradual individual shifts and makes them unreliable in long-horizon simulations. We propose MF-MDP, a social simulation framework that tightly couples macro-level collective dynamics with micro-level individual states. MF-MDP explicitly models per-agent latent opinion states with a state transition mechanism, combining individual Markov Decision Processes at the micro level with a mean-field collective framework at the macro level. This allows individual behaviors to change internal states gradually rather than trigger instant reactions, enabling the simulator to distinguish agents that are close to switching from those that are far from switching, capture opinion reversals, and maintain accuracy over long horizons. Across real-world events, MF-MDP supports stable simulation of long-horizon social processes with up to 40,000 interactions, compared with about 300 in the baseline MF-LLM, while reducing long-horizon KL divergence by 75.3% (1.2490 to 0.3089) and reversal KL by 66.9% (1.6425 to 0.5434), significantly mitigating the drift observed in MF-LLM. Code is available at github.com/AI4SS/MF-MDP.

Yuteng Ye, Guanwen Li, Hang Zhou et al.

Image-to-image translation (I2I), and particularly its subfield of appearance transfer, which seeks to alter the visual appearance between images while maintaining structural coherence, presents formidable challenges. Despite significant advancements brought by diffusion models, achieving fine-grained transfer remains complex, particularly in terms of retaining detailed structural elements and ensuring information fidelity. This paper proposes an innovative framework designed to surmount these challenges by integrating various aspects of semantic matching, appearance transfer, and latent deviation. A pivotal aspect of our approach is the strategic use of the predicted $x_0$ space by diffusion models within the latent space of diffusion processes. This is identified as a crucial element for the precise and natural transfer of fine-grained details. Our framework exploits this space to accomplish semantic alignment between source and target images, facilitating mask-wise appearance transfer for improved feature acquisition. A significant advancement of our method is the seamless integration of these features into the latent space, enabling more nuanced latent deviations without necessitating extensive model retraining or fine-tuning. The effectiveness of our approach is demonstrated through extensive experiments, which showcase its ability to adeptly handle fine-grained appearance transfers across a wide range of categories and domains. We provide our code at https://github.com/babahui/Fine-grained-Appearance-Transfer

Run Luo, Zikai Song, Lintao Ma et al.

Multi-object tracking (MOT) is a challenging vision task that aims to detect individual objects within a single frame and associate them across multiple frames. Recent MOT approaches can be categorized into two-stage tracking-by-detection (TBD) methods and one-stage joint detection and tracking (JDT) methods. Despite the success of these approaches, they also suffer from common problems, such as harmful global or local inconsistency, poor trade-off between robustness and model complexity, and lack of flexibility in different scenes within the same video. In this paper we propose a simple but robust framework that formulates object detection and association jointly as a consistent denoising diffusion process from paired noise boxes to paired ground-truth boxes. This novel progressive denoising diffusion strategy substantially augments the tracker's effectiveness, enabling it to discriminate between various objects. During the training stage, paired object boxes diffuse from paired ground-truth boxes to random distribution, and the model learns detection and tracking simultaneously by reversing this noising process. In inference, the model refines a set of paired randomly generated boxes to the detection and tracking results in a flexible one-step or multi-step denoising diffusion process. Extensive experiments on three widely used MOT benchmarks, including MOT17, MOT20, and Dancetrack, demonstrate that our approach achieves competitive performance compared to the current state-of-the-art methods.

Zikai Song, Junqing Yu, Yi-Ping Phoebe Chen et al.

Motion reasoning serves as the cornerstone of multi-object tracking (MOT), as it enables consistent association of targets across frames. However, existing motion estimation approaches face two major limitations: (1) instability caused by noisy or probabilistic predictions, and (2) vulnerability under occlusion, where trajectories often fragment once visual cues disappear. To overcome these issues, we propose a collaborative reasoning framework that enhances motion estimation through joint inference among multiple correlated objects. By allowing objects with similar motion states to mutually constrain and refine each other, our framework stabilizes noisy trajectories and infers plausible motion continuity even when target is occluded. To realize this concept, we design HyperSSM, an architecture that integrates Hypergraph computation and a State Space Model (SSM) for unified spatial-temporal reasoning. The Hypergraph module captures spatial motion correlations through dynamic hyperedges, while the SSM enforces temporal smoothness via structured state transitions. This synergistic design enables simultaneous optimization of spatial consensus and temporal coherence, resulting in robust and stable motion estimation. Extensive experiments on four mainstream and diverse benchmarks(MOT17, MOT20, DanceTrack, and SportsMOT) covering various motion patterns and scene complexities, demonstrate that our approach achieves state-of-the-art performance across a wide range of tracking scenarios.

Wenbing Li, Zikai Song, Jielei Zhang et al.

In this paper, we establish the novel insight that an off-the-shelf LLM can function as an excellent token compressor and decompressor. To demonstrate, we design a self-expressive autoencoding learning framework fine-tunes a pretrained LLM to translate long texts into a compact internal language of discrete, variable-length latent codes, termed Z-tokens, and to reconstruct the original text exactly from them. The resulting representation is content-adaptive: semantically dense segments receive more Z-tokens, while redundant or predictable regions are aggressively compressed, via lightweight LoRA-based adapter heads. Empirically, our method achieves up to 18 times token reduction on Wikipedia, CNN/DailyMail, HotpotQA, and Qulac-style long-query datasets, while preserving reconstruction fidelity and downstream performance. This simple yet effective design supports applications including prompt compression and autoregressive generation directly in the Z-token space, offering a potential pathway toward token-efficient long-context reasoning.

Zikai Song, Ying Tang, Run Luo et al.

Point tracking is a challenging task in computer vision, aiming to establish point-wise correspondence across long video sequences. Recent advancements have primarily focused on temporal modeling techniques to improve local feature similarity, often overlooking the valuable semantic consistency inherent in tracked points. In this paper, we introduce a novel approach leveraging language embeddings to enhance the coherence of frame-wise visual features related to the same object. Our proposed method, termed autogenic language embedding for visual feature enhancement, strengthens point correspondence in long-term sequences. Unlike existing visual-language schemes, our approach learns text embeddings from visual features through a dedicated mapping network, enabling seamless adaptation to various tracking tasks without explicit text annotations. Additionally, we introduce a consistency decoder that efficiently integrates text tokens into visual features with minimal computational overhead. Through enhanced visual consistency, our approach significantly improves tracking trajectories in lengthy videos with substantial appearance variations. Extensive experiments on widely-used tracking benchmarks demonstrate the superior performance of our method, showcasing notable enhancements compared to trackers relying solely on visual cues.

YuTeng Ye, Jiale Cai, Hang Zhou et al.

In spite of the rapidly evolving landscape of text-to-image generation, the synthesis and manipulation of multiple entities while adhering to specific relational constraints pose enduring challenges. This paper introduces an innovative progressive synthesis and editing operation that systematically incorporates entities into the target image, ensuring their adherence to spatial and relational constraints at each sequential step. Our key insight stems from the observation that while a pre-trained text-to-image diffusion model adeptly handles one or two entities, it often falters when dealing with a greater number. To address this limitation, we propose harnessing the capabilities of a Large Language Model (LLM) to decompose intricate and protracted text descriptions into coherent directives adhering to stringent formats. To facilitate the execution of directives involving distinct semantic operations-namely insertion, editing, and erasing-we formulate the Stimulus, Response, and Fusion (SRF) framework. Within this framework, latent regions are gently stimulated in alignment with each operation, followed by the fusion of the responsive latent components to achieve cohesive entity manipulation. Our proposed framework yields notable advancements in object synthesis, particularly when confronted with intricate and lengthy textual inputs. Consequently, it establishes a new benchmark for text-to-image generation tasks, further elevating the field's performance standards.

Dali Wang, Yunyao Zhang, Junqing Yu et al.

Micro-video popularity prediction (MVPP) aims to forecast the future popularity of videos on online media, which is essential for applications such as content recommendation and traffic allocation. In real-world scenarios, it is critical for MVPP approaches to understand both the temporal dynamics of a given video (temporal) and its historical relevance to other videos (spatial). However, existing approaches sufer from limitations in both dimensions: temporally, they rely on sparse short-range sampling that restricts content perception; spatially, they depend on flat retrieval memory with limited capacity and low efficiency, hindering scalable knowledge utilization. To overcome these limitations, we propose a unified framework that achieves joint spatio-temporal enlargement, enabling precise perception of extremely long video sequences while supporting a scalable memory bank that can infinitely expand to incorporate all relevant historical videos. Technically, we employ a Temporal Enlargement driven by a frame scoring module that extracts highlight cues from video frames through two complementary pathways: sparse sampling and dense perception. Their outputs are adaptively fused to enable robust long-sequence content understanding. For Spatial Enlargement, we construct a Topology-Aware Memory Bank that hierarchically clusters historically relevant content based on topological relationships. Instead of directly expanding memory capacity, we update the encoder features of the corresponding clusters when incorporating new videos, enabling unbounded historical association without unbounded storage growth. Extensive experiments on three widely used MVPP benchmarks demonstrate that our method consistently outperforms 11 strong baselines across mainstream metrics, achieving robust improvements in both prediction accuracy and ranking consistency.

Sicheng Feng, Song Wang, Shuyi Ouyang et al.

Multimodal large language models (MLLMs) have recently achieved significant progress in visual tasks, including semantic scene understanding and text-image alignment, with reasoning variants enhancing performance on complex tasks involving mathematics and logic. However, their capacity for reasoning tasks involving fine-grained visual understanding remains insufficiently evaluated. To address this gap, we introduce ReasonMap, a benchmark designed to assess the fine-grained visual understanding and spatial reasoning abilities of MLLMs. ReasonMap encompasses high-resolution transit maps from 30 cities across 13 countries and includes 1,008 question-answer pairs spanning two question types and three templates. Furthermore, we design a two-level evaluation pipeline that properly assesses answer correctness and quality. Comprehensive evaluations of 15 popular MLLMs, including both base and reasoning variants, reveal a counterintuitive pattern: among open-source models, base models outperform reasoning ones, while the opposite trend is observed in closed-source models. Additionally, performance generally degrades when visual inputs are masked, indicating that while MLLMs can leverage prior knowledge to answer some questions, fine-grained visual reasoning tasks still require genuine visual perception for strong performance. Our benchmark study offers new insights into visual reasoning and contributes to investigating the gap between open-source and closed-source models.

Yunyao Zhang, Zuocheng Ying, Xinglang Zhang et al.

LLM-based social network simulation introduces a new computational approach for modeling event evolution in complex online environments. However, existing methods typically simulate social processes under a fixed event trajectory, treating the event as static once initialized and overlooking intervention dynamics, and thus fail to capture the intrinsic evolution of real social network events, where source-side interventions and collective interactions continuously reshape event trajectories, sometimes leading to secondary popularity explosions and collective attitude shifts. To address this limitation, we introduce an intervention-aware simulation framework, IntervenSim, that models event evolution and intervention in a closed loop. We model event developments and source-side interventions using source agents, and collective crowd reactions using crowd agents, capturing their continuous co-evolution through an intervention-aware mechanism that couples source-side intervention, group interaction, and feedback-driven adjustment of subsequent interventions. Experiments on diverse real-world events show that IntervenSim improves MAPE by 41.6% and DTW by 66.9% over prior frameworks, while reducing computational cost with fewer yet more capable agents. These improvements indicate that IntervenSim not only simulates regular event trajectories more faithfully, but also better captures opinion dynamics under intervention in complex cases.

Liliang Ye, Yunyao Zhang, Yafeng Wu et al.

Social media platforms serve as central hubs for content dissemination, opinion expression, and public engagement across diverse modalities. Accurately predicting the popularity of social media videos enables valuable applications in content recommendation, trend detection, and audience engagement. In this paper, we present Multimodal Video Predictor (MVP), our winning solution to the Video Track of the SMP Challenge 2025. MVP constructs expressive post representations by integrating deep video features extracted from pretrained models with user metadata and contextual information. The framework applies systematic preprocessing techniques, including log-transformations and outlier removal, to improve model robustness. A gradient-boosted regression model is trained to capture complex patterns across modalities. Our approach ranked first in the official evaluation of the Video Track, demonstrating its effectiveness and reliability for multimodal video popularity prediction on social platforms. The source code is available at https://anonymous.4open.science/r/SMPDVideo.

Liliang Ye, Yunyao Zhang, Yafeng Wu et al.

Social media popularity prediction plays a crucial role in content optimization, marketing strategies, and user engagement enhancement across digital platforms. However, predicting post popularity remains challenging due to the complex interplay between visual, textual, temporal, and user behavioral factors. This paper presents HyperFusion, a hierarchical multimodal ensemble learning framework for social media popularity prediction. Our approach employs a three-tier fusion architecture that progressively integrates features across abstraction levels: visual representations from CLIP encoders, textual embeddings from transformer models, and temporal-spatial metadata with user characteristics. The framework implements a hierarchical ensemble strategy combining CatBoost, TabNet, and custom multi-layer perceptrons. To address limited labeled data, we propose a two-stage training methodology with pseudo-labeling and iterative refinement. We introduce novel cross-modal similarity measures and hierarchical clustering features that capture inter-modal dependencies. Experimental results demonstrate that HyperFusion achieves competitive performance on the SMP challenge dataset. Our team achieved third place in the SMP Challenge 2025 (Image Track). The source code is available at https://anonymous.4open.science/r/SMPDImage.

Guiyi Zeng, Junqing Yu, Yi-Ping Phoebe Chen et al.

Recent advances in self-evolution video understanding frameworks have demonstrated the potential of autonomous learning without human annotations. However, existing methods often suffer from weakly controlled optimization and uncontrolled difficulty progression, as they lack structured guidance throughout the iterative learning process. To address these limitations, we propose CurEvo, a curriculum-guided self-evolution framework that introduces curriculum learning into self-evolution to achieve more structured and progressive model improvement. CurEvo dynamically regulates task difficulty, refines evaluation criteria, and balances data diversity according to model competence, forming a curriculum-guided feedback loop that aligns learning complexity with model capability. Built upon this principle, we develop a multi-dimensional adaptive QA framework that jointly evolves question generation and answer evaluation across perception, recognition, and understanding dimensions, ensuring coherent and measurable curriculum progression. Through this integration, CurEvo transforms weakly controlled self-evolution into a more structured learning process for autonomous video understanding. Across seven backbones, CurEvo consistently improves both benchmark accuracy and evaluator-based semantic score on four VideoQA benchmarks, validating the effectiveness of curriculum-guided self-evolution for video understanding.

Mingjin Lv, Zelin Liu, Feifei Shao et al.

While large models demonstrate the strong representational power of vanilla attention, this core mechanism cannot be directly applied to Dense Object Tracking: its quadratic all-to-all interactions are computationally prohibitive for dense motion estimation on high-resolution features. This mismatch prevents Dense Object Tracking from fully leveraging attention-based modeling in crowded and occlusion-heavy scenes. To address this challenge, we introduce GateMOT, an online tracking framework centered on Q-Gated Attention (Q-Attention), an efficient and spatially aware attention variant. Our key idea is to repurpose the Query from a similarity-conditioning term into a learnable gating unit. This Gating-Query (Gating-Q) produces a probabilistic gate that modulates Key features in an element-wise manner, enabling explicit relevance selection instead of costly global aggregation. Built on this mechanism, parallel Q-Attention heads transform one shared feature map into task-specific yet consistent representations for detection, motion, and re-identification, yielding a tightly coupled multi-task decoder with linear-complexity gating operations. GateMOT achieves state-of-the-art HOTA of 48.4, MOTA of 67.8, and IDF1 of 64.5 on BEE24, and demonstrates strong performance on additional Dense Object Tracking benchmarks. These results show that Q-Attention is a simple, effective, and transferable building block for attention-based tracking in dense tracking scenarios.

Liliang Ye, Guiyi Zeng, Yunyao Zhang et al.

Predicting social media popularity requires understanding both the intrinsic appeal of content and the external context that determines how it is exposed to users. Existing methods focus on content signals but do not separate them from exposure-related patterns, which causes the learned representations to absorb platform-specific visibility effects and weakens both interpretability and cross-platform transfer. This paper introduces OmniTrend, a unified framework that models popularity as the joint outcome of content attractiveness and contextual exposure. The content module learns cross-modal representations from visual, audio, and textual cues to quantify intrinsic appeal, while the context module estimates exposure from exogenous signals such as posting time, author activity, topical trends, and retrieval-based neighborhood statistics. OmniTrend learns separate predictors for content attractiveness and contextual exposure and integrates them in the final popularity estimate, which makes the role of each factor explicit and supports robust transfer across image and video platforms.

Wenkai Liu, Tao Guan, Bin Zhu et al.

In the domain of 3D scene representation, 3D Gaussian Splatting (3DGS) has emerged as a pivotal technology. However, its application to large-scale, high-resolution scenes (exceeding 4k$\times$4k pixels) is hindered by the excessive computational requirements for managing a large number of Gaussians. Addressing this, we introduce 'EfficientGS', an advanced approach that optimizes 3DGS for high-resolution, large-scale scenes. We analyze the densification process in 3DGS and identify areas of Gaussian over-proliferation. We propose a selective strategy, limiting Gaussian increase to key primitives, thereby enhancing the representational efficiency. Additionally, we develop a pruning mechanism to remove redundant Gaussians, those that are merely auxiliary to adjacent ones. For further enhancement, we integrate a sparse order increment for Spherical Harmonics (SH), designed to alleviate storage constraints and reduce training overhead. Our empirical evaluations, conducted on a range of datasets including extensive 4K+ aerial images, demonstrate that 'EfficientGS' not only expedites training and rendering times but also achieves this with a model size approximately tenfold smaller than conventional 3DGS while maintaining high rendering fidelity.

Yafeng Wu, Yunyao Zhang, Liliang Ye et al.

Online comments play a crucial role in shaping public sentiment and opinion dynamics on social media. However, evaluating their popularity remains challenging, not only because it depends on linguistic quality, originality, and emotional resonance, but also because stylistic preferences vary widely across platforms and user groups, causing the same comment to resonate differently in different communities. In this work, we present HotComment, a multimodal benchmark integrating video and text modalities that comprehensively quantifies popularity from three enhanced aspects: (1) Content Quality, which evaluates semantic similarity with ground-truth human comments and extends quality assessment through four interpretable dimensions; (2) Popularity Prediction, based on trends from models trained on real-world interaction data; and (3) User Behavior Simulation, which models the distribution of platform users and approximates \textbf{engagement scores} through an agent-based framework. Furthermore, we propose StyleCmt, inspired by social ripple effects, where multiple stylistic dimensions align to amplify socially resonant expressions and suppress incongruent ones.

Hang Zhou, Jiale Cai, Yuteng Ye et al.

A recent endeavor in one class of video anomaly detection is to leverage diffusion models and posit the task as a generation problem, where the diffusion model is trained to recover normal patterns exclusively, thus reporting abnormal patterns as outliers. Yet, existing attempts neglect the various formations of anomaly and predict normal samples at the feature level regardless that abnormal objects in surveillance videos are often relatively small. To address this, a novel patch-based diffusion model is proposed, specifically engineered to capture fine-grained local information. We further observe that anomalies in videos manifest themselves as deviations in both appearance and motion. Therefore, we argue that a comprehensive solution must consider both of these aspects simultaneously to achieve accurate frame prediction. To address this, we introduce innovative motion and appearance conditions that are seamlessly integrated into our patch diffusion model. These conditions are designed to guide the model in generating coherent and contextually appropriate predictions for both semantic content and motion relations. Experimental results in four challenging video anomaly detection datasets empirically substantiate the efficacy of our proposed approach, demonstrating that it consistently outperforms most existing methods in detecting abnormal behaviors.

Youjia Zhang, Anpei Chen, Yumin Wan et al.

In this paper, we introduce Ref-GS, a novel approach for directional light factorization in 2D Gaussian splatting, which enables photorealistic view-dependent appearance rendering and precise geometry recovery. Ref-GS builds upon the deferred rendering of Gaussian splatting and applies directional encoding to the deferred-rendered surface, effectively reducing the ambiguity between orientation and viewing angle. Next, we introduce a spherical Mip-grid to capture varying levels of surface roughness, enabling roughness-aware Gaussian shading. Additionally, we propose a simple yet efficient geometry-lighting factorization that connects geometry and lighting via the vector outer product, significantly reducing renderer overhead when integrating volumetric attributes. Our method achieves superior photorealistic rendering for a range of open-world scenes while also accurately recovering geometry.

Yangliu Hu, Zikai Song, Na Feng et al.

Video-based Large Language Models (Video-LLMs) have witnessed substantial advancements in recent years, propelled by the advancement in multi-modal LLMs. Although these models have demonstrated proficiency in providing the overall description of videos, they struggle with fine-grained understanding, particularly in aspects such as visual dynamics and video details inquiries. To tackle these shortcomings, we find that fine-tuning Video-LLMs on self-supervised fragment tasks, greatly improve their fine-grained video understanding abilities. Hence we propose two key contributions:(1) Self-Supervised Fragment Fine-Tuning (SF$^2$T), a novel effortless fine-tuning method, employs the rich inherent characteristics of videos for training, while unlocking more fine-grained understanding ability of Video-LLMs. Moreover, it relieves researchers from labor-intensive annotations and smartly circumvents the limitations of natural language, which often fails to capture the complex spatiotemporal variations in videos; (2) A novel benchmark dataset, namely FineVidBench, for rigorously assessing Video-LLMs' performance at both the scene and fragment levels, offering a comprehensive evaluation of their capabilities. We assessed multiple models and validated the effectiveness of SF$^2$T on them. Experimental results reveal that our approach improves their ability to capture and interpret spatiotemporal details.

Beibei Jing, Youjia Zhang, Zikai Song et al.

Generating realistic human motion sequences from text descriptions is a challenging task that requires capturing the rich expressiveness of both natural language and human motion.Recent advances in diffusion models have enabled significant progress in human motion synthesis.However, existing methods struggle to handle text inputs that describe complex or long motions.In this paper, we propose the Adaptable Motion Diffusion (AMD) model, which leverages a Large Language Model (LLM) to parse the input text into a sequence of concise and interpretable anatomical scripts that correspond to the target motion.This process exploits the LLM's ability to provide anatomical guidance for complex motion synthesis.We then devise a two-branch fusion scheme that balances the influence of the input text and the anatomical scripts on the inverse diffusion process, which adaptively ensures the semantic fidelity and diversity of the synthesized motion.Our method can effectively handle texts with complex or long motion descriptions, where existing methods often fail. Experiments on datasets with relatively more complex motions, such as CLCD1 and CLCD2, demonstrate that our AMD significantly outperforms existing state-of-the-art models.

Qilong Xing, Zikai Song, Youjia Zhang et al.

Despite significant advancements in adapting Large Language Models (LLMs) for radiology report generation (RRG), clinical adoption remains challenging due to difficulties in accurately mapping pathological and anatomical features to their corresponding text descriptions. Additionally, semantic agnostic feature extraction further hampers the generation of accurate diagnostic reports. To address these challenges, we introduce Medical Concept Aligned Radiology Report Generation (MCA-RG), a knowledge-driven framework that explicitly aligns visual features with distinct medical concepts to enhance the report generation process. MCA-RG utilizes two curated concept banks: a pathology bank containing lesion-related knowledge, and an anatomy bank with anatomical descriptions. The visual features are aligned with these medical concepts and undergo tailored enhancement. We further propose an anatomy-based contrastive learning procedure to improve the generalization of anatomical features, coupled with a matching loss for pathological features to prioritize clinically relevant regions. Additionally, a feature gating mechanism is employed to filter out low-quality concept features. Finally, the visual features are corresponding to individual medical concepts, and are leveraged to guide the report generation process. Experiments on two public benchmarks (MIMIC-CXR and CheXpert Plus) demonstrate that MCA-RG achieves superior performance, highlighting its effectiveness in radiology report generation.

Run Luo, Zikai Song, Longze Chen et al.

Multi-Object Tracking (MOT) aims to associate multiple objects across video frames and is a challenging vision task due to inherent complexities in the tracking environment. Most existing approaches train and track within a single domain, resulting in a lack of cross-domain generalizability to data from other domains. While several works have introduced natural language representation to bridge the domain gap in visual tracking, these textual descriptions often provide too high-level a view and fail to distinguish various instances within the same class. In this paper, we address this limitation by developing IP-MOT, an end-to-end transformer model for MOT that operates without concrete textual descriptions. Our approach is underpinned by two key innovations: Firstly, leveraging a pre-trained vision-language model, we obtain instance-level pseudo textual descriptions via prompt-tuning, which are invariant across different tracking scenes; Secondly, we introduce a query-balanced strategy, augmented by knowledge distillation, to further boost the generalization capabilities of our model. Extensive experiments conducted on three widely used MOT benchmarks, including MOT17, MOT20, and DanceTrack, demonstrate that our approach not only achieves competitive performance on same-domain data compared to state-of-the-art models but also significantly improves the performance of query-based trackers by large margins for cross-domain inputs.

Yunyao Zhang, Xinglang Zhang, Junxi Sheng et al.

Logical reasoning is a fundamental capability of large language models (LLMs). However, existing studies largely overlook the interplay between logical complexity and semantic complexity, resulting in methods that struggle to address challenging scenarios involving abstract propositions, ambiguous contexts, and conflicting stances, which are central to human reasoning. For this gap, we propose LogicAgent, a semiotic-square-guided framework designed to jointly address logical complexity and semantic complexity. LogicAgent explicitly performs multi-perspective deduction in first-order logic (FOL), while mitigating vacuous reasoning through existential import checks that incorporate a three-valued decision scheme (True, False, Uncertain) to handle boundary cases more faithfully. Furthermore, to overcome the semantic simplicity and low logical complexity of existing datasets, we introduce RepublicQA, a benchmark that reaches college-level difficulty (FKGL = 11.94) and exhibits substantially greater lexical and structural diversity than prior benchmarks. RepublicQA is grounded in philosophical concepts, featuring abstract propositions and systematically organized contrary and contradictory relations, making it the most semantically rich resource for evaluating logical reasoning. Experiments demonstrate that LogicAgent achieves state-of-the-art performance on RepublicQA, with a 6.25% average gain over strong baselines, and generalizes effectively to mainstream logical reasoning benchmarks including ProntoQA, ProofWriter, FOLIO, and ProverQA, achieving an additional 7.05% average gain. These results highlight the strong effectiveness of our semiotic-grounded multi-perspective reasoning in boosting LLMs' logical performance.

Qilong Xing, Zikai Song, Bingxin Gong et al.

Accurate prognosis of non-small cell lung cancer (NSCLC) patients undergoing immunotherapy is essential for personalized treatment planning, enabling informed patient decisions, and improving both treatment outcomes and quality of life. However, the lack of large, relevant datasets and effective multi-modal feature fusion strategies pose significant challenges in this domain. To address these challenges, we present a large-scale dataset and introduce a novel framework for multi-modal feature fusion aimed at enhancing the accuracy of survival prediction. The dataset comprises 3D CT images and corresponding clinical records from NSCLC patients treated with immune checkpoint inhibitors (ICI), along with progression-free survival (PFS) and overall survival (OS) data. We further propose a cross-modality masked learning approach for medical feature fusion, consisting of two distinct branches, each tailored to its respective modality: a Slice-Depth Transformer for extracting 3D features from CT images and a graph-based Transformer for learning node features and relationships among clinical variables in tabular data. The fusion process is guided by a masked modality learning strategy, wherein the model utilizes the intact modality to reconstruct missing components. This mechanism improves the integration of modality-specific features, fostering more effective inter-modality relationships and feature interactions. Our approach demonstrates superior performance in multi-modal integration for NSCLC survival prediction, surpassing existing methods and setting a new benchmark for prognostic models in this context.

Qilong Xing, Zikai Song, Yuteng Ye et al.

Segmentation of brain structures from MRI is crucial for evaluating brain morphology, yet existing CNN and transformer-based methods struggle to delineate complex structures accurately. While current diffusion models have shown promise in image segmentation, they are inadequate when applied directly to brain MRI due to neglecting anatomical information. To address this, we propose Collaborative Anatomy Diffusion (CA-Diff), a framework integrating spatial anatomical features to enhance segmentation accuracy of the diffusion model. Specifically, we introduce distance field as an auxiliary anatomical condition to provide global spatial context, alongside a collaborative diffusion process to model its joint distribution with anatomical structures, enabling effective utilization of anatomical features for segmentation. Furthermore, we introduce a consistency loss to refine relationships between the distance field and anatomical structures and design a time adapted channel attention module to enhance the U-Net feature fusion procedure. Extensive experiments show that CA-Diff outperforms state-of-the-art (SOTA) methods.

Wenbing Li, Zikai Song, Hang Zhou et al.

Recent efforts to combine low-rank adaptation (LoRA) with mixture-of-experts (MoE) for adapting large language models (LLMs) to multiple tasks still exhibit prevailing limitations: they either swap entire attention/feed-forward layers for switch experts or bolt on parallel expert branches, diluting parameter efficiency and task fidelity. We propose the LoRA-Mixer, a modular and lightweight MoE framework that integrates LoRA experts. Our core innovation lies in replacing the projection matrices of the attention module's input/output linear layers with dynamically routed, task-specific LoRA experts. This design ensures seamless compatibility with diverse foundation models, including transformers and state space models (SSMs), by leveraging their inherent linear projection structures. The framework supports two operational paradigms: (1) joint optimization of LoRA experts and routing mechanisms via a novel hard-soft routing strategy, or (2) direct deployment of pre-trained, frozen LoRA modules sourced from external repositories. To enable robust router training with limited data while ensuring stable routing decisions and maximizing expert reuse, we introduce an adaptive Specialization Balance Loss (SBL) that jointly optimizes expert balance and task-specific alignment. Extensive experiments on seven benchmark datasets, including MedQA, CoLA, SST-2, GSM8K, ARC-E, ARC-C, and HumanEval, demonstrate the effectiveness of LoRA-Mixer. On datasets such as GSM8K, HumanEval, and MedQA, LoRA-Mixer achieves significant improvements of 7.61%, 4.88%, and 3.08% over the base models, respectively. Compared with state-of-the-art methods, LoRA-Mixer achieves additional improvements of 1.09%, 1.45%, and 1.68%, respectively, using only 48% of the parameters, demonstrating its efficiency and strong performance.

Youjia Zhang, Zikai Song, Junqing Yu et al.

Generating multi-view images from a single input view using image-conditioned diffusion models is a recent advancement and has shown considerable potential. However, issues such as the lack of consistency in synthesized views and over-smoothing in extracted geometry persist. Previous methods integrate multi-view consistency modules or impose additional supervisory to enhance view consistency while compromising on the flexibility of camera positioning and limiting the versatility of view synthesis. In this study, we consider the radiance field optimized during geometry extraction as a more rigid consistency prior, compared to volume and ray aggregation used in previous works. We further identify and rectify a critical bias in the traditional radiance field optimization process through score distillation from a multi-view diffuser. We introduce an Unbiased Score Distillation (USD) that utilizes unconditioned noises from a 2D diffusion model, greatly refining the radiance field fidelity. We leverage the rendered views from the optimized radiance field as the basis and develop a two-step specialization process of a 2D diffusion model, which is adept at conducting object-specific denoising and generating high-quality multi-view images. Finally, we recover faithful geometry and texture directly from the refined multi-view images. Empirical evaluations demonstrate that our optimized geometry and view distillation technique generates comparable results to the state-of-the-art models trained on extensive datasets, all while maintaining freedom in camera positioning. Please see our project page at https://youjiazhang.github.io/USD/.