Yadan Luo

Norm$\times$Direction: Restoring the Missing Query Norm in Vision Linear Attention

Could Student Selection Be the Missing Piece for Efficient Distillation?

MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection

Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents

CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving

PolaFormer: Polarity-aware Linear Attention for Vision Transformers

Latent Refinement via Flow Matching for Training-free Linear Inverse Problem Solving

Tokens on Demand: Token Condensation as Training-free Test-time Adaptation