I am recruiting PhD students to join my lab at Harvard in Fall 2025! (deadline Dec 15) If you are interested in solving problems at the intersection of reinforcement learning, imitation learning, and NLP, pls consider applying (! @hseas @KempnerInst

RT @du_yilun: Excited to share our work on history guidance! By composing multiple diffusion score functions on different noise-corrupte…

RT @gneubig: Summary in case you missed any LLM research from the past month: * RL on math datasets improves math ability v1 * RL on math…

RT @hankyang94: Here is the paper containing technical details of “Global Contact-Rich Planning with Sparsity-Rich Semidefinite Relaxatio…

@gneubig I thought this was fun:

RT @hankyang94: Diffusion has shown great promise for generating robot **actions**, can it act as a **world model** to generate the future…

RT @ShamKakade6: 1/n In new work, we draw connections between accelerated SGD and various recent optimizers including AdEMAMix, Schedule-Fr…

@rm_rafailov @lateinteraction Yea, its a bit odd to me as well.

@rm_rafailov @rajammanabrolu I agree with this observation. If you add a discount factor it seems like this would help.

@rajammanabrolu I agree with this thought.

RT @jiayi_pirate: We reproduced DeepSeek R1-Zero in the CountDown game, and it just works Through RL, the 3B base LM develops self-verifi…

RT @boazbaraktcs: 1/5 Excited about our paper demonstrating that increasing inference-time compute improves robustness. I think moving from…

RT @KempnerInst: A huge congratulations to @KanakaRajanPhD of the #KempnerInstitute & @harvardmed who was awarded the Presidential Early Ca…

RT @MiroDudik: 📢My team at Microsoft Research New York is hiring a senior researcher in AI, both broadly in AI/ML, and in some specific are…

@rajammanabrolu Nice job @rajammanabrolu !

RT @akhil_bagaria: 🚨 My RL team at Amazon is looking for PhD interns for this summer! We apply RL to the Amazon supply chain, and do open-e…

RT @HenaffMikael: Excited to share our latest work ONI, which enables learning intrinsic rewards online without pre-collected data. We do t…

RT @KempnerInst: NEW in the #KempnerInstitute blog: learn about ProCyon, a multimodal foundation model to model, generate & predict protei…

RT @COLM_conf: Announcement #1: our call for papers is up! 🎉 And excited to announce the COLM 2025 program chairs @…

RT @KempnerInst: We are pleased to announce our first ever Kempner Institute Symposium, Frontiers in NeuroAI, a two-day event in Allston, M…

RT @KempnerInst: (1/3) The #NeurIPS2024 System-2 Reasoning at Scale Workshop today also features #KempnerInstitute work! Stop by for: