Heng Tao Shen

GeoPurify: A Data-Efficient Geometric Distillation Framework for Open-Vocabulary 3D Segmentation

Policy Contrastive Decoding for Robotic Foundation Models

Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation

Prototype-based Regularization Learning For Text-Video Retrieval

Efficient and Interpretable Multi-Agent LLM Routing via Ant Colony Optimization

RAG-FGO: Enhancing RAG with Fungal Growth Optimizer for LLM Agents

Truth in the Few: High-Value Data Selection for Efficient Multi-Modal Reasoning

Agent-GWO: Collaborative Agents for Dynamic Prompt Optimization in Large Language Models

MemoryField: Exploiting Gravitational Field for Long-term Memory Management

Geometric Enhancement in 3D Gaussian Splatting for Sparse-view Scene Reconstruction

More Than One Teacher: Adaptive Multi-Guidance Policy Optimization for Diverse Exploration

Analytical Construction on Geometric Architectures: Transitioning from Static to Temporal Link Prediction

SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism

TAU-106K: A New Dataset for Comprehensive Understanding of Traffic Accident

Table2LaTeX-RL: High-Fidelity LaTeX Code Generation from Table Images via Reinforced Multimodal Language Models

MMEvol: Empowering Multimodal Large Language Models with Evol-Instruct

SeMv-3D: Towards Semantic and Mutil-view Consistency simultaneously for General Text-to-3D Generation with Triplane Priors

ETC: Towards Training-Efficient Video Synthesis with Exploiting Temporal Capabilities of Spatial Attention