VLASH is a general asynchronous inference framework for VLAs that delivers smooth, accurate, and low-latency control with no overhead or architectural changes. By rolling the robot state forward with the previous action chunk, it achieves up to 2.03× speedup and 17.4× lower reaction latency while fully preserving accuracy.

ForeAct is a plug-and-play visual foresight planner that enables state-of-the-art VLAs to anticipate high-fidelity future observations for improved decision-making, generating 640×480 predictions in just 0.33s on a single H100 GPU without any architectural changes.

We introduce Locality-aware Parallel Decoding to accelerate autoregressive image generation and achieve 13× faster than traditional AR models and at least 3.4× faster than previous parallelized AR models.

StreamingVLM enables real-time understanding of infinite videos with low, stable latency. By aligning training on overlapped video chunks with an efficient KV cache, it runs at 8 FPS on a single H100. It achieves a 66.18% win rate vs. GPT-4o mini on a new benchmark with videos averaging over 2 hours long.

We present LongLive, a frame-level autoregressive (AR) framework for real-time and interactive long video generation. Try LongLive: turning your interactive prompts into long videos-instantly, as you type!

We introduce a novel block-wise approximate KV Cache mechanism tailored for bidirectional diffusion models, enabling cache reuse with negligible performance drop.