AI.info
Fan Yang
Explore Fan Yang on AI.info.
- Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World Models
- BLaDA: Bridging Language to Functional Dexterous Actions within 3DGS Fields
- VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos
- SpatialReward: Bridging the Perception Gap in Online RL for Image Editing via Explicit Spatial Reasoning
- TRACER: Texture-Robust Affordance Chain-of-Thought for Deformable-Object Refinement
- From Internal Diagnosis to External Auditing: A VLM-Driven Paradigm for Data-Free Online Backdoor Defense
- Learning Fine-Grained Correspondence with Cross-Perspective Perception for Open-Vocabulary 6D Object Pose Estimation
- MRD: Multi-resolution Retrieval-Detection Fusion for High-Resolution Image Understanding
- Catastrophic Forgetting in Kolmogorov-Arnold Networks
- Breaking the Stealth-Potency Trade-off in Clean-Image Backdoors with Generative Trigger Optimization
- LiveStar: Live Streaming Assistant for Real-World Online Video Understanding
- KnowThyself: An Agentic Assistant for LLM Interpretability
- StreamingCoT: A Dataset for Temporal Dynamics and Multimodal Chain-of-Thought Reasoning in Streaming VideoQA
- Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents
- VoiceAgentEval: A Dual-Dimensional Benchmark for Expert-Level Intelligent Voice-Agent Evaluation of Xbench's Professional-Aligned Series
- GAPS: A Clinically Grounded, Automated Benchmark for Evaluating AI Clinicians