Linh Le @linhlpv
PhD student at A2I2 Reinforcement Learning, Adaptation and Generalization linhlpv.github.io Joined December 2015-
Tweets212
-
Followers72
-
Following468
-
Likes2K
A new VLA for navigation that can take in goal images, positions, and language, and exhibits some pretty neat emergent language following!
A new VLA for navigation that can take in goal images, positions, and language, and exhibits some pretty neat emergent language following!
Is scale all you need? Or is there still a role for incorporating domain knowledge and inductive bias? While I was in Heidelberg, I took some time to write a short essay on this question called "The Bittersweet Lesson". theoryandpractice.org/2025/09/The%20… #HLF25
For those really into it, here are another 50 minutes of my views on planning and action selection in options-based AI agents (like in the Oak architecture). youtube.com/watch?v=eJSoV2…
DiffusionNFT: RL for diffusion models via the forward process • Contrastive fine-tuning: positives vs negatives → implicit policy improvement • Works with any solver, no CFG, no trajectory storage • 25× more efficient than FlowGRPO • Boosts SD3.5-M: GenEval 0.24 → 0.98 in…
Excited to announce that Streaming Flow Policy is accepted to CoRL’25 as an Oral presentation! 🎉 #CoRL2025 We just released a self-contained Jupyter notebook that trains and tests SFP in the Push-T environment: siddancha.github.io/streaming-flow… Looking forward to presenting this work…
Excited to announce that Streaming Flow Policy is accepted to CoRL’25 as an Oral presentation! 🎉 #CoRL2025 We just released a self-contained Jupyter notebook that trains and tests SFP in the Push-T environment: siddancha.github.io/streaming-flow… Looking forward to presenting this work…
I was surprised by how many didnt know that (1) per token MLE is whole seq MLE, and (2) PG at token level same as PG at seq level (optimizkng one big combinatorial action). story is different if you introduce fitted critic/Q-values or intermediate resets.
I was surprised by how many didnt know that (1) per token MLE is whole seq MLE, and (2) PG at token level same as PG at seq level (optimizkng one big combinatorial action). story is different if you introduce fitted critic/Q-values or intermediate resets.
Generative Modeling: What's After Flow Matching? Flow Matching lacks explicit modeling of scores on the data manifold. Introducing Energy Matching [NeurIPS 2025] unlocking exciting new inference-time capabilities! Paper: arxiv.org/pdf/2504.10612 Code: github.com/m1balcerak/Ene…
Check out our new work on scaling RL via iterative computation. We apply flow-matching to value function learning and it works really well 🔥
Check out our new work on scaling RL via iterative computation. We apply flow-matching to value function learning and it works really well 🔥
For agents to improve over time, they can’t afford to forget what they’ve already mastered. We found that supervised fine-tuning forgets more than RL when training on a new task! Want to find out why? 👇
The pi-05 model is now in openpi: github.com/Physical-Intel… Now with pytorch (πtorch?) support too!
With the right design decisions, value-based RL admits predictable scaling. value-scaling.github.io We wrote a blog post on our two papers challenging conventional wisdom that off-policy RL methods are fundamentally unpredictable.
World models hold a lot of promise for robotics, but they're data hungry and often struggle with long horizons. We learn models from a few (< 10) human demos that enable a robot to plan in completely novel scenes! Our key idea is to model *symbols* not pixels 👇
I was happy to give a more technical talk on how we might create an AI at RLC-2025 and AGI-2025 (video below). The Oak Architecture: A Vision of Super-Intelligence from Experience As AI has become a huge industry, to an extent it has lost its way. What is needed to get us back on…
Finding an ML summer school has never been easier Here is a GitHub repo with a comprehensive list, with 50+ ML summer (and winter) schools all over the world (link in comments) Some of them are even free, few even offer scholarship so you don't have to pay absolutely anything
🚀 I'm excited to share our new paper: SegDAC: Segmentation-Driven Actor-Critic for Visual Reinforcement Learning 🧠 SegDAC combines large vision models with online RL to reason about its environment at the object and sub-object level, avoiding noisy pixel-level reasoning. 🛠️…
Humanoids finally move like humans… and can do more than copy. [Details + demos in thread 👇] A new framework, BeyondMimic, shows how to learn naturalistic whole-body control from human motion. But then goes further by composing those skills into versatile, zero-shot…
At what point does perf optimization get ridiculous. During my PhD, everything was 500-5000 sps. Then I got 10k and was very proud. Then 100k in early versions of PufferLib. Then 1M in 2.0... and now we're at up to 6M productive SPS on some RL envs
Fine-tuning pre-trained robotic models with online RL requires a way to train RL with expressive policies Can we design an effective method for this? We propose EXPO, a sample-efficient online RL algorithm that enables stable fine-tuning of expressive policy classes (1/6)
✨Introducing SENSEI✨ We bring semantically meaningful exploration to model-based RL using VLMs. With intrinsic rewards for novel yet useful behaviors, SENSEI showcases strong exploration in MiniHack, Pokémon Red & Robodesk. Accepted at ICML 2025🎉 Joint work with @cgumbsch 🧵
missing ICML, and I used this week to write my first technical blog on some recent thoughts on two different roles of simulators in RL and the confusions/misconceptions around them. Comments welcome! nanjiang.cs.illinois.edu/2025/07/16/sim…
Robert Scoble @Scobleizer
543K Followers 24K Following The best from ML/AI community | Ex-Microsoft, Rackspace, Fast Company | Wrote eight books about the future | Silicon Valley robots, holodecks, BCIs, & startups.
Kayla @gyT87WktgG0606E
32 Followers 1K Following
Ziyan "Ray" Luo @RLC'... @RayZiyan41307
73 Followers 168 Following Abstraction & RL / Ph.D. @Mila_Quebec, @mcgillu with @XujieSi & Doina Precup / Music: @SunsetRay_Ra / https://t.co/im1jR2Vend
Josephine Howe @howe_josep16896
104 Followers 4K Following
Iefohwe @Iefohwe1009054
142 Followers 3K Following
jessica🩶 @ds_jessica_
14K Followers 12K Following analytics lead & angel investor & advisor. always learning = business & innovation. doing #datascience
Théo Vincent @Theo_Vincent_
326 Followers 449 Following PhD student at @DFKI & @ias_tudarmstadt, working on RL 🤖 Previously master student at MVA @ENS_ParisSaclay & ENPC 🎓
Clarisse Wibault @ClarisseWibault
24 Followers 54 Following PhD Student @UniofOxford @FLAIR_Ox | Supervised by @maosbot @j_foerst |
Johan Obando-Ceron �... @johanobandoc
2K Followers 4K Following Graduate student @Mila_Quebec @UMontrealDIRO | RL/Deep Learning/AI | De Cali/Colombia pal’ Mundo 🇨🇴 | #JuntosProsperamos⚡#TogetherWeThrive| 🌱🌎
John Zhou @johnlyzhou
113 Followers 267 Following PhD student @UCLA, previously @Columbia | Scalable reinforcement learning
Geonwoo Cho @GeonwooC51050
13 Followers 101 Following Reinforcement Learning | CS Undergrad Ex Match Group / HyperConnect Machine Learning Software Engineer
Zhaolin Gao @GaoZhaolin
140 Followers 116 Following CS PhD Student @Cornell & @cornell_tech | GenAI Intern @Meta https://t.co/9mVl01Ilui
Nacho Mellado @uavster
3K Followers 762 Following Building your companion robot in public: https://t.co/pDyfICPowG Formerly Google X, Apple, https://t.co/CaT9ffzG6r,@PickNikRobotics, demoscene.
Laurence Feil @LaurenceFe87679
116 Followers 4K Following
TRUMP SUPPORTER 🇺�... @_TRUMP2025_
54 Followers 521 Following MAKE/ AMERICAN /GREAT/TRUMP 2016/TRUMP 2020/TRUMP https://t.co/Nl8u4TPjtf
PoppyThoreau @65oOMKs588d3x4
122 Followers 2K Following
Kory Mathewson @korymath
11K Followers 4K Following @GoogleDeepMind working on Veo + Flow -- getting great generative AI into the hands of great creative people
Shivam Vats @ CoRL202... @ShivaamVats
741 Followers 517 Following Postdoc @BrownBigAI Previously: PhD @CMU_Robotics, Maths @IITKgp, Core developer @SymPy
David van Dijk @david_van_dijk
5K Followers 4K Following Assistant Professor @Yale @YaleMed @YaleCSDept | ML/AI comp bio
Joe Mayo @JoeMayo
16K Followers 5K Following Author and Independent Consultant Recent books: - Programming the Microsoft Bot Framework/MSPress - C# Cookbook/O'Reilly Agents, AI, Generative AI, MCP, RAG
Evelyn @omara_evelyn55
392 Followers 3K Following
Alessandro Montenegro @montenegronwski
59 Followers 117 Following 💡PhD Student @polimi | 🤖Reinforcement Learning @rl3polimi | 📍Made in Italy, Rome.
Zhaochen Su @SuZhaochen0110
344 Followers 711 Following LLM/LVLM Knowledge & Reasoning | Incoming Ph.D. Student @hkust @hkustnlp | Previous Shanghai AI Lab.
R. Alessio @ BU @rssalessio
108 Followers 243 Following Postdoc at Boston University with Aldo Pacchiano (PLAIA Lab). Interested in RL, Bandit problems and Adaptive Control.
Laixi Shi @ShiLaixi
419 Followers 242 Following RL with uncertainty foundation; Assistant Professor in JHU ECE&DSAI @JohnsHopkins; Postdoc in @Caltech; Ph.D. in CMU (@CMU_ECE); BEng in Tsinghua @Tsinghua_Uni
Arip @machinestein
1K Followers 779 Following
Abhishek Sharma @sharma_abhishek
427 Followers 1K Following PhD Candidate @ Harvard SEAS. Research in Reinforcement Learning and Probabilistic ML
Mirco Mutti @mirco_mutti
635 Followers 644 Following Postdoc @TechnionLive. PhD from @polimi. Reinforcement learning, but without rewards.
Yinglun Zhu @yinglun122
366 Followers 412 Following Assistant Prof @UCRiverside. PhD @WisconsinCS. Researching Efficient ML, RL, and LLMs.
Lucas Alegre @lnalegre
163 Followers 443 Following Professor at @INF_UFRGS. Interested in multi-task and multi-objective reinforcement learning.
Haimin Hu @HaiminHu
560 Followers 313 Following Incoming Assistant Professor @JHUCompSci | PhD @Princeton ECE | Postdoc & MSE @Penn @GRASPlab | BEng @ShanghaiTechUni. I like robots (when they are safe).
evo @evo_agent
16 Followers 45 Following
Academic Giant @APremierWriter
95 Followers 999 Following For due assignments, essays, classes or any other academic task, exams included, just HMU
Amir-massoud Farahman... @SoloGen
6K Followers 2K Following Goal: Understanding the computational and statistical principles required to design adaptive agents. Associate Prof @polymtl @Mila_Quebec 🇨🇦 #MahsaAmini
Hao Sun - RL @HolarisSun
898 Followers 962 Following RS @GoogleDeepMind. Prev. PhD @CambridgeUni, #MMLab, B.Phys. @PKU1898
Kyoung Whan Choe @kywch500
865 Followers 1K Following Robot Learning Engineer @ https://t.co/wcLx79rCuW
Zhiyong Wang @Zhiyong16403503
784 Followers 4K Following Postdoc at Edinburgh, Ph.D. at CUHK. Former Visiting Scholar at Cornell. Working on reinforcement learning and multi-armed bandits.
nissymori @nissymori1
191 Followers 434 Following PhD candidate@UTokyo_News_en(Sugiyama-Yokoya-Ishida lab) Reinforcement Learning (RL) JAX-based RL Game AI Slack Community Vista
Ignacio Carlucho @i_carlucho
179 Followers 670 Following Assistant Professor at @HeriotWattUni and @NRobotarium Working on Robotics and Reinforcement learning.
Hue @__lily_ng__
1 Followers 14 Following
Zixuan Huang @ZixuanHuang15
294 Followers 388 Following Intern at Amazon FAR. PhD @UMRobotics. Former MS @CMU_Robotics
Levi Lelis @levilelis
704 Followers 545 Following Artificial Intelligence Researcher - Associate Professor - University of Alberta - Canada CIFAR AI Chair (he/him, ele/dele).
Siddharth Ancha @siddancha
515 Followers 408 Following Research Scientist @UCBerkeley | Postdoc @MIT_CSAIL @MIT | PhD from @SCSatCMU @CarnegieMellon | I work on Robotics 🤖
Microsoft Research As... @msraurjp
3K Followers 569 Following Microsoft Research Asia -Tokyo, Japan： MSRにご興味のある方、インターン希望の方、Researcher希望の方、お気軽にご連絡ください。 【中の人：https://t.co/V8dTASC0js】
Khurram Javed @KhurramJaved_96
2K Followers 155 Following Developing efficient algorithms for real-time reinforcement learning. Research Scientist at Keen, a startup led by John Carmack. Prev ~ PhD with Richard Sutton
Nishanth Kumar @nishanthkumar23
2K Followers 886 Following AI/ML + Robots PhD Student @MIT_LISLab, intern @AIatMeta. Formerly @NVIDIAAI, @rai_inst, @brownbigai, @vicariousai and @uber.
Arash Tavakoli @arshtvk
844 Followers 508 Following Reinforcement Learning, Staff Research Scientist @RiotGames. Spent time @MPI_IS, @ImperialCollege, @UCL, @USC, @GeorgiaTech, @Microsoft (MSR), @UAlberta (RLAI).
Thao Nguyen @thao_nguyen26
1K Followers 309 Following PhD student @uwcse working on data research. Formerly visiting researcher @AIatMeta, @GoogleAI Resident, @Stanford'19, @twosigma.
Daphne Cornelisse @daphne_cor
1K Followers 560 Following Ph.D. student @nyuniversity • Building human-like agents 🦋 https://t.co/BhKiCutsdY
Alexandre Brown 🇨�... @AlexandreBrown0
173 Followers 1K Following PhD student at @UMontreal and research @Mila_Quebec working on RL applied to humanoid robots
Jiaxun Cui 🐿️ @cuijiaxun
700 Followers 779 Following Research Scientist @AIatMeta | Ph.D. @utlarg @UTAustin 🤘 | Multi-agent Reinforcement Learning | Undergrad SJTU @sjtu1896
Rui Shu @_smileyball
3K Followers 430 Following I draw smileyball https://t.co/VZJD2Av8PY Writing organic artisanal handcrafted code @OpenAI Previously doing the same @Stanford
Ziyan "Ray" Luo @RLC'... @RayZiyan41307
73 Followers 168 Following Abstraction & RL / Ph.D. @Mila_Quebec, @mcgillu with @XujieSi & Doina Precup / Music: @SunsetRay_Ra / https://t.co/im1jR2Vend
Qian Huang @qhwang3
14K Followers 330 Following prev @xai | CS PhD student @StanfordAILab (on leave)
Keerthana Gopalakrish... @keerthanpg
17K Followers 1K Following Mother of robots. Building Embodied AGI @DeepMind. Author of "AI for Robotics". Opinions my own.
Edward Grefenstette �... @egrefen
42K Followers 868 Following FR/US/GB AI/ML Person, Director of Research at @GoogleDeepMind, Honorary Professor at @UCL_DARK, @ELLISforEurope Fellow. All posts are personal.
Tabitha Edith Lee @TabulaRobot
940 Followers 592 Following Postdoc at @UMontreal & @Mila_Quebec in causal learning for robots and embodied AI. Prior stops at @CMU_Robotics, @nvidia, LM Space ATC, & Uber ATG.
Liliang Ren @liliang_ren
4K Followers 584 Following Senior Researcher at Microsoft GenAI | UIUC CS PhD graduate | Efficient LLM | NLP | Former Intern @MSFTResearch @Azure @AmazonScience
Christian Gumbsch @cgumbsch
190 Followers 170 Following Postdoc @UvA_Amsterdam | world models and sensorimotor abstractions |👾🤖🧠
Shuran Song @SongShuran
12K Followers 521 Following Assistant Professor @Stanford University working on #Robotics #AI #ComputerVision
Annie Chen @_anniechen_
1K Followers 410 Following PhD student @StanfordAILab. Prev: research @GoogleDeepMind, Stanford BS/MS
Nitish ⚡️ @nitishmutha
4K Followers 348 Following Co-founder and CTO @GenieAI - Building the world’s best AI Legal Drafter. @UCL alum.
Johan Obando-Ceron �... @johanobandoc
2K Followers 4K Following Graduate student @Mila_Quebec @UMontrealDIRO | RL/Deep Learning/AI | De Cali/Colombia pal’ Mundo 🇨🇴 | #JuntosProsperamos⚡#TogetherWeThrive| 🌱🌎
Kevin Ellis @ellisk_kellis
2K Followers 178 Following Cornell Computer Science, Assistant Professor. Program synthesis, AI
John Zhou @johnlyzhou
113 Followers 267 Following PhD student @UCLA, previously @Columbia | Scalable reinforcement learning
Geonwoo Cho @GeonwooC51050
13 Followers 101 Following Reinforcement Learning | CS Undergrad Ex Match Group / HyperConnect Machine Learning Software Engineer
Núria Armengol @NriaArmengol2
127 Followers 201 Following ETH/CLS PhD candidate focused on reinforcement learning and sports lover.
Eric Rosen @_ericrosen
1K Followers 635 Following Robotics Research Scientist @ Robotics and AI Institute (RAI) | Making robots smarter for everyone | CS PhD from @BrownUniversity 🤖
Robotic Systems Lab @leggedrobotics
16K Followers 174 Following The Robotic Systems Lab designs machines, creates actuation principles, and builds up control technologies for autonomous operation in challenging environments.
Sumeet Batra @SumeetBt
290 Followers 151 Following 5th year PhD Candidate at USC . Interested in robotics and generalist embodied agents. Inspired by neuroscience. Prev. 2X research intern at NVIDIA.
IEEE ICRA @ieee_ras_icra
12K Followers 82 Following #ICRA2025 IEEE International Conference on Robotics & Automation 19–23 May, Atlanta, USA
Georg Martius @GMartius
2K Followers 204 Following Researcher, interested in autonomous machine learning, reinforcement learning, robotics, 3d printing and more
Chris Paxton @chris_j_paxton
20K Followers 3K Following Mostly posting about robots. currently AI @agilityrobotics prev embodied AI @AIatMeta, @NVIDIAAI. All views my own. writing: https://t.co/iNLA4djfZo
Michael Black @Michael_J_Black
85K Followers 706 Following Director, Max Planck Institute for Intelligent Systems (@MPI_IS). Chief Scientist @meshcapade. Building 3D digital humans using vision, graphics, and learning.
ECML PKDD @ECMLPKDD
3K Followers 101 Following Official Twitter account of the European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. BlueSky: @ecmlpkdd.org
Ahmad Beirami @abeirami
10K Followers 4K Following sth new // ex Gemini RL+Inference @GoogleDeepMind // Chat AI @Meta // RL Agents @EA // ML+Information Theory @MIT+@Harvard+@GeorgiaTech // زن زندگی آزادی
Fan Nie @FanNie1208
779 Followers 362 Following AI @Stanford | Prev. @EPFL @SJTU1886 ｜Research in Reliable AI & Large Language Models
Hailey Nguyen @hailey_huong
241 Followers 218 Following Untangling the complexities of LLM alignment. Safety Researcher in FAIR @AIatMeta
Grace Liu @GraceLiu78
47 Followers 3 Following
Jiaxin Shi @thjashin
4K Followers 350 Following Research Scientist @GoogleDeepMind | prev @Stanford @MSRNE @VectorInst @RIKEN_AIP_EN @Tsinghua_Uni. Building probabilistic & algorithmic models for learning.
Luisa Zintgraf @luisa_zintgraf
5K Followers 501 Following Senior Research Scientist in the RL team @googledeepmind. PhD from @UniofOxford.
Chuang Gan @gan_chuang
9K Followers 490 Following Faculty Member at UMass Amherst; Principal researcher at MIT-IBM Watson AI Lab; Homepage: https://t.co/Pc8WeREfTzTrends for United States
You might like
