MyoSem introduces an EMG-action semantic alignment framework that transforms low-level muscle signals into a shared semantic space, enabling bidirectional retrieval between EMG data and natural langua…

The paper proposes a novel cross-axis feature fusion architecture and an auxiliary joint-difference prediction task to significantly improve text-based 3D human motion editing by better understanding…

The paper proposes Agentic ASR, a closed-loop framework that treats ASR as a multi-turn refinement task, significantly improving semantic accuracy over traditional token-level metrics.

This paper systematically evaluates LLMs' ability to infer pragmatic meaning from non-verbal responses, finding that their accuracy significantly drops compared to verbal inputs.

The paper proposes InSemRAG, an enhanced RAG framework that improves retrieval accuracy and knowledge integrity by incorporating intent-aware retrieval and semantics-preserving chunking, achieving sta…

AnchorSteer introduces a framework that achieves high-fidelity, structure-preserving music editing by decoupling semantic concept injection from structural constraints.

The paper introduces ERGeoBench, a comprehensive diagnostic benchmark designed to evaluate the fine-grained capabilities of multimodal large language models (MLLMs) for embodied geo-localization acros…

The paper proposes a dual-interventional framework to characterize how linguistic structures and contextual cues influence LLMs' spatial reasoning for navigation, finding that topological information…

SkillPager is a novel two-stage framework that efficiently selects minimal, execution-sufficient context from large procedural skill documents by leveraging typed semantic nodes, significantly reducin…

The paper introduces CERA, a novel contrastive retrieval framework that improves RAG factuality and interpretability by using subjectivity-based hard negative selection and an auxiliary attention alig…

The paper proposes Resonant Context Anchoring (RCA), a lightweight, training-free method that enhances factual faithfulness in LLMs by dynamically amplifying the signal of external context evidence du…

The paper introduces AnyMo, a unified multimodal framework that enables high-quality, scalable conditional human motion generation by leveraging a massive, cross-modal dataset and a masked modeling tr…

Qwen-VLA introduces a unified embodied foundation model that extends vision-language understanding to continuous action generation, enabling robust, multi-task generalization across diverse robotic ta…

This paper introduces the concept of Safety Geometry Collapse, demonstrating that multimodal inputs degrade the safety separation of LLMs, and proposes ReGap, a training-free method that adaptively co…

The paper proposes using GPT-4o to generate controlled paraphrases of target text for sign language translation (SLT) augmentation, achieving significant BLEU-4 improvements on PHOENIX14T.

This paper demonstrates that typographic attacks pose a significant, measurable, and physically consequential threat to household robot manipulation systems by causing the robot to grasp and transport…

VLA-Pro is a plug-and-play framework that enhances cross-task generalization in Vision-Language-Action models by storing and dynamically retrieving task-specific procedural memories, achieving signifi…