RLVR/RLHF libraries:
• verl - ByteDance
• TRL - HuggingFace
• slime - Zhipu AI
• prime-rl - Prime Intellect
• ROLL - Alibaba
• Nemo-RL - NVIDIA
• AReaL - Ant Research
• SkyRL - UC Berkeley
• open-instruct - Allen AI
• torchtune - PyTorch
Any I am missing? Which do you…
Announcing the ICLR 2026 Call for Papers!
Abstract submission: Sept 19 (AoE)
Paper submission: Sept 24 (AoE)
Reviews released: Nov 11
Author/Reviewer discussion: Nov 11-Dec 3
Final decisions: Jan 22 2026
iclr.cc/Conferences/20…
Ever confused by "prompt tuning" vs "model reprogramming" vs "in-context learning"?
What if they're all the same thing—just different names across ML, CV, and NLP communities?
Our recent paper introduces Neural Network Reprogrammability as a unifying framework showing these…
🧵New survey: Bridging Distribution Shift and AI Safety
Distribution shift and AI safety have long been studied in parallel. But how can their insights formally inform each other?
We present the first comprehensive, mathematically grounded, and one-to-one aligned treatment.
1/6
AI benchmarking culture is completely out of control. Tables with dozens of methods, datasets, and bold numbers, trying to answer a question that perhaps no one should be asking anymore.
I want to share my latest (very short) blog post: "Active Learning vs. Data Filtering: Selection vs. Rejection."
What is the fundamental difference between active learning and data filtering?
Well, obviously, the difference is that:
1/11
Wow, Deeply Supervised Nets received the Test of Time award at @aistats_conf 2025! It was the very first paper I submitted during my PhD. Fun fact: the paper was originally rejected by NeurIPS with scores of 8/8/7 (yes, that pain stuck with me... maybe now I can finally let it…
Wow, Deeply Supervised Nets received the Test of Time award at @aistats_conf 2025! It was the very first paper I submitted during my PhD. Fun fact: the paper was originally rejected by NeurIPS with scores of 8/8/7 (yes, that pain stuck with me... maybe now I can finally let it…
ICML 2025's rebuttal process be like🤣:
👨💻 Authors: spend a whole week writing a careful rebuttal
✅ Reviewer: clicks "acknowledge" without reading
🚫 Author: not allowed to reply anymore
So what does acknowledge mean here?
"You speak. I pretend to listen. Conversation over."🙃
グリーン・デイ 来日ライブ横浜Kアリーナ Day 2
セトリ最後まさかの観客がビリーのギターをステージで譲り受けてGood Riddanceを共演
若い日本の子がGreen Dayの曲を完璧に弾き継いでこんな幸せなファイナルある?
#greenday#グリーンデイ#setlist
Green Day - Good Riddance (Time of Your Life)
Separate from the recently announced Special Postdoctoral Researcher recruitment at RIKEN, the Robot Learning Team at RIKEN AIP @RIKEN_AIP_EN is seeking to hire two researchers! If you are interested, please consider applying.
riken.jp/en/careers/res…
🎉 Thrilled that our paper "On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent" is a Spotlight at #ICLR2025!
Huge thanks to my collaborators & reviewers! Excited to discuss at the conference!
📄 Paper: openreview.net/forum?id=97rOQ…
Today, we are publishing the first-ever International AI Safety Report, backed by 30 countries and the OECD, UN, and EU.
It summarises the state of the science on AI capabilities and risks, and how to mitigate those risks. 🧵
Link to full Report: assets.publishing.service.gov.uk/media/679a0c48…
1/16
If you’re using the #ICML LaTeX template, there’s a typo in algorithmic.sty that prevents cross-referencing specific lines in the algorithm environment. The fix is simple: change \addtocounter{ALC@line}{1} to \refstepcounter{ALC@line} on Line 106. Credit: tex.stackexchange.com/questions/5234…
Most AI researchers I talk to have been a bit shocked by DeepSeek-R1 and its performance.
My preliminary understanding nuggets:
1. Simple post-training recipe called GRPO: Start with a good model and reward for correctness and style outcomes. No PRM, no MCTS no fancy reward…
760 Followers 1K Following[email protected], Postdoc@tsinghua, working with Prof. Jie Tang. PhD advised by Prof. Yue Zhang. Prev: Interned @AWScloud. LLM Evaluation, Posttraining
2K Followers 840 FollowingAssistant Professor at @BristolUni, PhD from @UCL, prev. intern in @TikTok & @Microsoft. ✨ Reinforcement Learning, Causality, World Models.
623 Followers 54 FollowingA research group in @StanfordAILab researching AI Capabilities, Trust and Safety, Equity and Reliability
Website: https://t.co/CgOHvNHL4x
1K Followers 2K FollowingNSF AI Institute with researchers from @UTAustin, @UW, @WichitaState, @MSFTResearch, @UCBerkeley, @UCLA, @sfiscience, @Stanford, @Caltech, @ASU
1K Followers 3K FollowingVITA Group @UTAustin w/ Prof Atlas Wang | https://t.co/Wi3tJXf1mg Run by VITA students (PI is busy changing diapers😄). Tweets only reflect personal views
3K Followers 964 FollowingAssistant Prof @UCSD. I work on safety, interpretability, and personalization in ML. Previously @GoogleAI @Harvard @MIT @UCBerkeley🇨🇭🇹🇷
4K Followers 5K Following↑ profile picture is dreamed by Anime GAN /
cooking computational and ML sauce at Sakana AI /
before: google {brain,deepmind} ← stony brook u ← fudan u
760 Followers 1K Following[email protected], Postdoc@tsinghua, working with Prof. Jie Tang. PhD advised by Prof. Yue Zhang. Prev: Interned @AWScloud. LLM Evaluation, Posttraining
1K Followers 1K FollowingByteDance Seed @ByteDance_Seed | Senior Research Scientist working on LLMs | prev. @oxcsml @UniofOxford, @amazon, @apple, @bloomberg
All opinions are my own
357 Followers 496 FollowingPostdoc of Princeton AI Lab. PhD from the University of Science and Technology of China. Previous Visiting PhD at Harvard University.
4K Followers 862 FollowingProfessor of Computer Science and a music lover. Interested in formal methods, security, and Trustworthy ML. Oh yes, and classical music and jazz.
792 Followers 613 FollowingExploring & Building | Master @LTIatCMU | Prev @Microsoft @BytedanceTalk | LLMs, Agents, Reasoning | Random thoughts are my own
1K Followers 103 FollowingAI/RL researcher, Assistant Prof. at @Tsinghua_Uni, leading the RL lab at @AntResearch_, PhD at @berkeley_ai, frequent flyer and milk tea lover.
6K Followers 218 FollowingIncoming assistant professor at UCSD CSE in MLSys. Currently recruiting students! Also running the kernels team @togethercompute.
2K Followers 141 FollowingSilver Professor at NYU Courant and CDS, Research Scientist at FAIR
Research in Machine Learning, past in Quantum Computing & Finance. Posts my own.
2K Followers 840 FollowingAssistant Professor at @BristolUni, PhD from @UCL, prev. intern in @TikTok & @Microsoft. ✨ Reinforcement Learning, Causality, World Models.