hao-ai-lab

A unified inference and post-training framework for accelerated video generation.

[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

[ICML 2024] CLLMs: Consistency Large Language Models

JetSpec++/JetSpec: Causal Parallel (Tree) Drafting with Self Refinement

[NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.

[ICML 2026] d3LLM: Ultra-Fast Diffusion LLM 🚀

ORA: Open Robot-Use Agents

[ICML 2026] Jacobi Forcing: Fast and Accurate Diffusion-style Decoding

Efficient Long-context Language Model Training by Core Attention Disaggregation

[NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank

[NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning

A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and caching, etc.

NVFP4 Flash-Attention 4 on BlackWell