Sen Wang

InclusiveVidPose: Bridging the Pose Estimation Gap for Individuals with Limb Deficiencies in Video-Based Motion

Robust Test-time Video-Text Retrieval: Benchmarking and Adapting for Query Shifts

ERNav: A Unified, Realistic Benchmark for Embodied AI with Exploration, Representation, and Navigation

Refining Bias and Reward in LLM Recommender Agents through Meta-Controlled Tool Invocation

When One Moment Isn't Enough: Multi-Moment Retrieval with Cross-Moment Interactions

General Scene Adaptation for Vision-and-Language Navigation

RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers

Medium-Difficulty Samples Constitute Smoothed Decision Boundary for Knowledge Distillation on Pruned Datasets

RePaFormer: Ferocious and Scalable Acceleration of MetaFormers via Structural Reparamterization

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

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