Changsheng Xu

QueryStream: Advancing Streaming Video Understanding with Query-Aware Pruning and Proactive Response

From Forgetting to Robustness: Robust Class-Incremental Learning with CLIP

Rethinking LoRA Aggregation for Federated Fine-tuning of Foundation Models

OmniSAT: Compact Action Token, Faster Auto Regression

Never Seen Before: Benchmarking Genuine Zero-Shot Composed Image Retrieval with Consistent Video-Sourced Datasets

In Defense of Prompt-based Continual Learning: Task Interference Mitigation via Confidence-Stratified Classifier Calibration

Object-Consistent Distillation for Text-to-3D Generation

Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automation

SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding

Rethinking the Temperature for Federated Heterogeneous Distillation

Locality Preserving Markovian Transition for Instance Retrieval

LiveStar: Live Streaming Assistant for Real-World Online Video Understanding

LumiSculpt: A Consistency Lighting Control Network for Video Generation

Neighbor-aware Geodesic Transportation for Neighborhood Refinery

Revisiting Prompt-based Methods in Class Incremental Learning