Tian Ye

This paper analyzes the limitations of Counterfactual Knowledge Training (CFT) for LLM unlearning, identifying knowledge conflict and hallucination spillover as major pitfalls that hinder its effectiveness.

SANA-Streaming introduces a novel, efficient framework that enables real-time, high-resolution streaming video-to-video editing by combining a hybrid diffusion transformer with specialized training and hardware co-design.

The paper introduces Dr. DocBench, a difficulty-aware, comprehensive benchmark designed to rigorously test expert-level and challenging document parsing capabilities for VLMs, demonstrating that current state-of-the-art models fail on complex, domain-specific structures.

The paper proposes SimSD, a plug-and-play speculative decoding algorithm that adapts diffusion language models (dLLMs) to achieve fast, token-level acceleration by restoring causal masking capabilities.