InterMesh: Explicit Interaction-Aware End-to-End Multi-Person Human Mesh Recovery

Humans constantly interact with their surroundings. Existing end-to-end multi-person human mesh recovery methods, typically based on the DETR framework, capture inter-human relationships through self-attention across all human queries. However, these approaches model interactions only implicitly and lack explicit reasoning about how humans interact with objects and with each other. In this paper, we propose InterMesh, a simple yet effective framework that explicitly incorporates human-environment interaction information into human mesh recovery pipeline. By leveraging a human-object interaction detector, InterMesh enriches query representations with structured interaction semantics, enabling more accurate pose and shape estimation. We design lightweight modules, Contextual Interaction Encoder and Interaction-Guided Refiner, to integrate these features into existing HMR architectures with minimal overhead. We validate our approach through extensive experiments on 3DPW, MuPoTS, CMU Panoptic, Hi4D, and CHI3D datasets, demonstrating remarkable improvements over state-of-the-art methods. Notably, InterMesh reduces MPJPE by 9.9% on CMU Panoptic and 8.2% on Hi4D, highlighting its effectiveness in scenarios with complex human-object and inter-human interactions.

Lost in the Hype: Revealing and Dissecting the Performance Degradation of Medical Multimodal Large Language Models in Image Classification

The rise of multimodal large language models (MLLMs) has sparked an unprecedented wave of applications in the field of medical imaging analysis. However, as one of the earliest and most fundamental tasks integrated into this paradigm, medical image classification reveals a sobering reality: state-of-the-art medical MLLMs consistently underperform compared to traditional deep learning models, despite their overwhelming advantages in pre-training data and model parameters. This paradox prompts a critical rethinking: where exactly does the performance degradation originate? In this paper, we conduct extensive experiments on 14 open-source medical MLLMs across three representative image classification datasets. Moving beyond superficial performance benchmarking, we employ feature probing to track the information flow of visual features module-by-module and layer-by-layer throughout the entire MLLM pipeline, enabling explicit visualization of where and how classification signals are distorted, diluted, or overridden. As the first attempt to dissect classification performance degradation in medical MLLMs, our findings reveal four failure modes: 1) quality limitation in visual representation, 2) fidelity loss in connector projection, 3) comprehension deficit in LLM reasoning, and 4) misalignment of semantic mapping. Meanwhile, we introduce quantitative scores that characterize the healthiness of feature evolution, enabling principled comparisons across diverse MLLMs and datasets. Furthermore, we provide insightful discussions centered on the critical barriers that prevent current medical MLLMs from fulfilling their promised clinical potential. We hope that our work provokes rethinking within the community-highlighting that the road from high expectations to clinically deployable MLLMs remains long and winding.

SCMAPR: Self-Correcting Multi-Agent Prompt Refinement for Complex-Scenario Text-to-Video Generation

Text-to-Video (T2V) generation has benefited from recent advances in diffusion models, yet current systems still struggle under complex scenarios, which are generally exacerbated by the ambiguity and underspecification of text prompts. In this work, we formulate complex-scenario prompt refinement as a stage-wise multi-agent refinement process and propose SCMAPR, i.e., a scenario-aware and Self-Correcting Multi-Agent Prompt Refinement framework for T2V prompting. SCMAPR coordinates specialized agents to (i) route each prompt to a taxonomy-grounded scenario for strategy selection, (ii) synthesize scenario-aware rewriting policies and perform policy-conditioned refinement, and (iii) conduct structured semantic verification that triggers conditional revision when violations are detected. To clarify what constitutes complex scenarios in T2V prompting, provide representative examples, and enable rigorous evaluation under such challenging conditions, we further introduce {T2V-Complexity}, which is a complex-scenario T2V benchmark consisting exclusively of complex-scenario prompts. Extensive experiments on 3 existing benchmarks and our T2V-Complexity benchmark demonstrate that SCMAPR consistently improves text-video alignment and overall generation quality under complex scenarios, achieving up to 2.67\% and 3.28 gains in average score on VBench and EvalCrafter, and up to 0.028 improvement on T2V-CompBench over 3 State-Of-The-Art baselines.

BoxComm: Benchmarking Category-Aware Commentary Generation and Narration Rhythm in Boxing

Recent multimodal large language models (MLLMs) have shown strong capabilities in general video understanding, driving growing interest in automatic sports commentary generation. However, existing benchmarks for this task focus exclusively on team sports such as soccer and basketball, leaving combat sports entirely unexplored. Notably, combat sports present distinct challenges: critical actions unfold within milliseconds with visually subtle yet semantically decisive differences, and professional commentary contains a substantially higher proportion of tactical analysis compared to team sports. In this paper, we present BoxComm, a large-scale dataset comprising 445 World Boxing Championship match videos with over 52K commentary sentences from professional broadcasts. We propose a structured commentary taxonomy that categorizes each sentence into play-by-play, tactical, or contextual, providing the first category-level annotation for sports commentary benchmarks. Building on this taxonomy, we introduce two novel and complementary evaluations tailored to sports commentary generation: (1) category-conditioned generation, which evaluates whether models can produce accurate commentary of a specified type given video context; and (2) commentary rhythm assessment, which measures whether freely generated commentary exhibits appropriate temporal pacing and type distribution over continuous video segments, capturing a dimension of commentary competence that prior benchmarks have not addressed. Experiments on multiple state-of-the-art MLLMs reveal that current models struggle on both evaluations. We further propose EIC-Gen, an improved baseline incorporating detected punch events to supply structured action cues, yielding consistent gains and highlighting the importance of perceiving fleeting and subtle events for combat sports commentary.

Silent Sabotage During Fine-Tuning: Few-Shot Rationale Poisoning of Compact Medical LLMs

Supervised fine-tuning (SFT) is essential for the development of medical large language models (LLMs), yet prior poisoning studies have mainly focused on the detectable backdoor attacks. We propose a novel poisoning attack targeting the reasoning process of medical LLMs during SFT. Unlike backdoor attacks, our method injects poisoned rationales into few-shot training data, leading to stealthy degradation of model performance on targeted medical topics. Results showed that knowledge overwriting was ineffective, while rationale poisoning caused significant decline on the accuracy of the target subject, as long as no correct samples of the same subject appear in the dataset. A minimum number and ratio of poisoned samples was needed to carry out an effective and stealthy attack, which was more efficient and accurate than catastrophic forgetting. We demonstrate though this study the risk of SFT-stage poisoning, hoping to spur more studies of defense in the sensitive medical domain.

From Continuous sEMG Signals to Discrete Muscle State Tokens: A Robust and Interpretable Representation Framework

Surface electromyography (sEMG) signals exhibit substantial inter-subject variability and are highly susceptible to noise, posing challenges for robust and interpretable decoding. To address these limitations, we propose a discrete representation of sEMG signals based on a physiology-informed tokenization framework. The method employs a sliding window aligned with the minimal muscle contraction cycle to isolate individual muscle activation events. From each window, ten time-frequency features, including root mean square (RMS) and median frequency (MDF), are extracted, and K-means clustering is applied to group segments into representative muscle-state tokens. We also introduce a large-scale benchmark dataset, ActionEMG-43, comprising 43 diverse actions and sEMG recordings from 16 major muscle groups across the body. Based on this dataset, we conduct extensive evaluations to assess the inter-subject consistency, representation capacity, and interpretability of the proposed sEMG tokens. Our results show that the token representation exhibits high inter-subject consistency (Cohen's Kappa = 0.82+-0.09), indicating that the learned tokens capture consistent and subject-independent muscle activation patterns. In action recognition tasks, models using sEMG tokens achieve Top-1 accuracies of 75.5% with ViT and 67.9% with SVM, outperforming raw-signal baselines (72.8% and 64.4%, respectively), despite a 96% reduction in input dimensionality. In movement quality assessment, the tokens intuitively reveal patterns of muscle underactivation and compensatory activation, offering interpretable insights into neuromuscular control. Together, these findings highlight the effectiveness of tokenized sEMG representations as a compact, generalizable, and physiologically meaningful feature space for applications in rehabilitation, human-machine interaction, and motor function analysis.

Learning the Mechanism of Catastrophic Forgetting: A Perspective from Gradient Similarity

Catastrophic forgetting during knowledge injection severely undermines the continual learning capability of large language models (LLMs). Although existing methods attempt to mitigate this issue, they often lack a foundational theoretical explanation. We establish a gradient-based theoretical framework to explain catastrophic forgetting. We first prove that strongly negative gradient similarity is a fundamental cause of forgetting. We then use gradient similarity to identify two types of neurons: conflicting neurons that induce forgetting and account for 50%-75% of neurons, and collaborative neurons that mitigate forgetting and account for 25%-50%. Based on this analysis, we propose a knowledge injection method, Collaborative Neural Learning (CNL). By freezing conflicting neurons and updating only collaborative neurons, CNL theoretically eliminates catastrophic forgetting under an infinitesimal learning rate eta and an exactly known mastered set. Experiments on five LLMs, four datasets, and four optimizers show that CNL achieves zero forgetting in in-set settings and reduces forgetting by 59.1%-81.7% in out-of-set settings.

CoScale-RL: Efficient Post-Training by Co-Scaling Data and Computation

Training Large Reasoning Model (LRM) is usually unstable and unpredictable, especially on hard problems or weak foundation models. We found that the current post-training scaling strategy can still improve on these cases. We propose CoScale-RL, a novel scaling strategy with better data and computational efficiency. We first scale up solutions to make problems solvable. The core idea is to collect multiple solutions for each problem, rather than simply enlarging the dataset. Then, we scale up rollout computation to stabilize Reinforcement Learning. We further leverage a model merge technique called Re-distillation to sustain or even improve computational efficiency when scaling up. Our method significantly improves data and computational efficiency, with an average 3.76$\times$ accuracy improvement on four benchmarks. CoScale-RL is able to improve an LRM's ability boundary without an extensive SFT dataset. Our method provides a new scaling direction to further improve LRM's reasoning ability.

BoxMind: Closed-loop AI strategy optimization for elite boxing validated in the 2024 Olympics

Competitive sports require sophisticated tactical analysis, yet combat disciplines like boxing remain underdeveloped in AI-driven analytics due to the complexity of action dynamics and the lack of structured tactical representations. To address this, we present BoxMind, a closed-loop AI expert system validated in elite boxing competition. By defining atomic punch events with precise temporal boundaries and spatial and technical attributes, we parse match footage into 18 hierarchical technical-tactical indicators. We then propose a graph-based predictive model that fuses these explicit technical-tactical profiles with learnable, time-variant latent embeddings to capture the dynamics of boxer matchups. Modeling match outcome as a differentiable function of technical-tactical indicators, we turn winning probability gradients into executable tactical adjustments. Experiments show that the outcome prediction model achieves state-of-the-art performance, with 69.8% accuracy on BoxerGraph test set and 87.5% on Olympic matches. Using this predictive model as a foundation, the system generates strategic recommendations that demonstrate proficiency comparable to human experts. BoxMind is validated through a closed-loop deployment during the 2024 Paris Olympics, directly contributing to the Chinese National Team's historic achievement of three gold and two silver medals. BoxMind establishes a replicable paradigm for transforming unstructured video data into strategic intelligence, bridging the gap between computer vision and decision support in competitive sports.

Towards Metric-Aware Multi-Person Mesh Recovery by Jointly Optimizing Human Crowd in Camera Space

Multi-person human mesh recovery from a single image is a challenging task, hindered by the scarcity of in-the-wild training data. Prevailing in-the-wild human mesh pseudo-ground-truth (pGT) generation pipelines are single-person-centric, where each human is processed individually without joint optimization. This oversight leads to a lack of scene-level consistency, producing individuals with conflicting depths and scales within the same image. To address this, we introduce Depth-conditioned Translation Optimization (DTO), a novel optimization-based method that jointly refines the camera-space translations of all individuals in a crowd. By leveraging anthropometric priors on human height and depth cues from a monocular depth estimator, DTO solves for a scene-consistent placement of all subjects within a principled Maximum a posteriori (MAP) framework. Applying DTO to the 4D-Humans dataset, we construct DTO-Humans, a new large-scale pGT dataset of 0.56M high-quality, scene-consistent multi-person images, featuring dense crowds with an average of 4.8 persons per image. Furthermore, we propose Metric-Aware HMR, an end-to-end network that directly estimates human mesh and camera parameters in metric scale. This is enabled by a camera branch and a novel relative metric loss that enforces plausible relative scales. Extensive experiments demonstrate that our method achieves state-of-the-art performance on relative depth reasoning and human mesh recovery. Code and data will be released publicly.