Xudong Jiang

Monocular Normal Estimation via Shading Sequence Estimation

Video-KTR: Reinforcing Video Reasoning via Key Token Attribution

Angle K-Means

Fire on Motion: Optimizing Video Pass-bands for Efficient Spiking Action Recognition

Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks

Learning to Respond: A Large-Scale Benchmark and Progressive Learning Framework for Trigger-Centric Online Video Understanding

Minutes to Converage: Dataset Distillation for Rapid SNN Training on Event Streams

Memory Makes The Poison: Over Memorization Drives Visual Poisoning in LVLMs

O²-CritiCuRL: Offline-Online Step-aware Curriculum Reinforcement Learning for Visual Reasoning

Advancing Expert Specialization for Better MoE

Multi-Scale Finetuning for Encoder-based Time Series Foundation Models

DSRF: A Dynamic and Scalable Reasoning Framework for Solving RPMs

Spiking GS: Towards High-Accuracy and Low-Cost Surface Reconstruction via Spiking Neuron-based Gaussian Splatting