Yang Li
7 papers · Latest:
ReCoVR: Closing the Loop in Interactive Composed Video Retrieval
ReCoVR introduces a dual-pathway architecture for interactive composed video retrieval, using reflexive perception to refine search with user feedback and retrieval history.
PhysForge: Generating Physics-Grounded 3D Assets for Interactive Virtual World
PhysForge generates physics-grounded 3D assets for interactive virtual worlds and embodied AI using a two-stage framework and a large-scale physical asset dataset.
From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models
This paper systematically compares latent action supervision methods for VLA models, finding image-based actions aid reasoning and action-based actions improve motor skills.
Logical Consistency as a Bridge: Improving LLM Hallucination Detection via Label Constraint Modeling between Responses and Self-Judgments
LaaB improves LLM hallucination detection by logically bridging neural features and symbolic self-judgments through a novel meta-judgment process.
VTouch++: A Multimodal Dataset with Vision-Based Tactile Enhancement for Bimanual Manipulation
VTouch++ is a new multimodal dataset leveraging vision-based tactile sensing to improve bimanual manipulation in contact-rich tasks.
Unveiling contrasting impacts of heat mitigation and adaptation policies on U.S. internal migration
Heat adaptation policies reduce U.S. internal out-migration, while mitigation policies surprisingly increase it, with effects varying by policy type and demographics.
EvoLen: Evolution-Guided Tokenization for DNA Language Model
EvoLen introduces an evolution-guided tokenization method for DNA language models, improving the preservation of functional sequence patterns and DNALM performance.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.