Feilong Tang

Hallucination Begins Where Saliency Drops

CARL: Preserving Causal Structure in Representation Learning

Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denosing Diffusion Process

StreamAgent: Towards Anticipatory Agents for Streaming Video Understanding

On the Measurement and Efficient Mitigation of Length Generalization Gaps in Large Language Models

Decoding Causal Structure: End-to-End Mediation Pathways Inference

Towards Dynamic 3D Reconstruction of Hand-Instrument Interaction in Ophthalmic Surgery

Intervening Anchor Token: Decoding Strategy in Alleviating Hallucinations for MLLMs

UniViT: Unifying Image and Video Understanding in One Vision Encoder

Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning