Shang Yang (@Shang

Shang Yang

50 posts

Shang Yang

@Shang_mit

Ph.D. Student @MITEECS. Undergrad @Tsinghua_Uni.

Cambridge, MA, US

Joined October 2023

Pinned
Shang Yang
@Shang_mit
Feb 27
🥳 Thrilled to see our work on TLT featured on the MIT homepage (mit.edu) and the cover of MIT News today! 🏛️✨ 🚀 2x faster RL training without losing accuracy. News: news.mit.edu/2026/new-metho… Paper: arxiv.org/abs/2511.16665 Code: github.com/mit-han-lab/fa…
00:00
Shang Yang
@Shang_mit
Nov 26, 2025
🚀 Introducing TLT (Taming the Long-Tail), an efficient, lossless system that boosts reasoning RL training by mitigating the rollout bottleneck! 🏆 Accepted by #ASPLOS2026 ✨ What’s new? ⚡ Enjoy 2× faster end-to-end reasoning RL training 🔒 Lossless on-policy RL —
Shang Yang
@Shang_mit
Jun 5
Come check out our work at CVPR! Excited to chat!
Zhuoyang Zhang
@zhuoyang_zhang
Jun 4
We‘ll be presenting ForeAct (🌟Highlight) at CVPR 2026: 📍 Poster: Sunday, 3:30PM, ExHall A #95 📍 NVIDIA Tech Talk: Friday, 12:40PM, Booth #211 @NVIDIAAI Feel free to stop by and chat! Also find our coffee making demo empowered by ForeAct! (youtube.com/watch?v=kBKJxW…) I’ll be at
00:00
Shang Yang
@Shang_mit
Feb 24
Enhancing your own VLAs with our visual planner. Efficient and easy to integrate! 🥳 📄Paper: arxiv.org/abs/2602.12322… 🔗Code: github.com/mit-han-lab/fo… #CVPR2026
Zhuoyang Zhang
@zhuoyang_zhang
Feb 24
We release ForeAct (accepted to CVPR’26🎉), a world model planner powered by visual foresight for VLAs - efficiently, modularly, and at scale. ✨ Seamlessly integrates with VLAs by visual augmentation — no architectural changes required ⚡ Generates high-fidelity 640×480 subgoal
00:00
Shang Yang
@Shang_mit
Nov 26, 2025
🚀 Introducing TLT (Taming the Long-Tail), an efficient, lossless system that boosts reasoning RL training by mitigating the rollout bottleneck! 🏆 Accepted by #ASPLOS2026 ✨ What’s new? ⚡ Enjoy 2× faster end-to-end reasoning RL training 🔒 Lossless on-policy RL —
Shang Yang
@Shang_mit
Feb 21, 2025
🎉 Excited to share that LServe, our efficient long-sequence LLM serving framework, is accepted by #MLSys’25! 🔥 ⚡Up to 2.9× faster prefilling & 1.3-2.1× faster decoding over vLLM 🔋Hybrid attention kernels unifying static & dynamic sparsity 🔗 hanlab.mit.edu/projects/lserve (1/5)