← Search

Zhihao He

2 accepted papers

2026

VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding

ICML 2026poster

Current Video Large Language Models (Video LLMs) typically encode frames via a vision encoder and employ an autoregressive (AR) LLM for understanding and generation. However, this AR paradigm inevitably faces a dual efficiency bottleneck: strictly unidirectional attention compromises *understanding …

Cited by 3SourceScholar
2025

Rodimus*: Breaking the Accuracy-Efficiency Trade-Off with Efficient Attentions

ICLR 2025poster

Recent advancements in Transformer-based large language models (LLMs) have set new standards in natural language processing. However, the classical softmax attention incurs significant computational costs, leading to a $O(T)$ complexity for per-token generation, where $T$ represents the context leng…