Wenjun Li @liwenjun2016
Ph.D. Student @sgSMU, LLM x RL. wenjunli-0.github.io Singapore Joined September 2016-
Tweets23
-
Followers53
-
Following50
-
Likes32
Lol, smart authors 😂
A clearer and more direct explanation to Dr. GRPO.
A clearer and more direct explanation to Dr. GRPO.
🚀 Our new findings continue to unravel the mysteries of R1-Zero-like training! 📢 We identify that BIAS in GRPO leads to longer responses—so we fixed it. ✅ GRPO Done Right → 7B SOTA on AIME!
🚀 Our new findings continue to unravel the mysteries of R1-Zero-like training! 📢 We identify that BIAS in GRPO leads to longer responses—so we fixed it. ✅ GRPO Done Right → 7B SOTA on AIME!
Wenjun Li retweeted
🪂Understanding R1-Zero-Like Training: A Critical Perspective * DeepSeek-V3-Base already exhibits "Aha moment" before RL-tuning?? * The ever-increasing output length in RL-tuning might be due to a BIAS in GRPO?? * Getting GRPO Done Right, we achieve a 7B AIME sota! 🧵 📜Full…
rule-based reward shaping is the reason behind
rule-based reward shaping is the reason behind
these are the singal words
we foubd base models can directly perform CoT and self-reflection. Check out the example below.
we foubd base models can directly perform CoT and self-reflection. Check out the example below.
Surprisingly, Aha moment appears at epoch 0, the base models.
Surprisingly, Aha moment appears at epoch 0, the base models.
Wenjun Li retweeted
New airdrop: Kubinex Finance (KUBIX) Reward: 2500 KUBIX ($125) Rate: ⭐️ ⭐️⭐️⭐️ Remarks: 150,000,000 KUBIX to be Airdropped Distribution: From 20th May Bot Airdrop Link: t.me/airdropinspect… #Airdrop #Airdrops #Airdropinspector #BinanceSmartChain #BSC #BNB #Bitcoin #Crypto
Deebee @Deebee0182395
2 Followers 203 Following
Zrirtirv @Zrirtirv92510
0 Followers 214 Following
Truiheg @Truiheg0274
0 Followers 133 Following
Liang Ding @liangdingNLP
781 Followers 2K Following NLP/ML Researcher (working on developing GenAI and its human-centric applications) & Ex-@JD_Corporate @TencentGlobal @Sydney_Uni. Opinions are my own.
Dung Doan @dungdx34
332 Followers 7K Following
Fahad Shah @sfahad
935 Followers 8K Following @Leadership @DataScience @HP @AzureML @Happily Married 😊
Avinandan Bose @avibose22
155 Followers 303 Following 3rd Year PhD @UWCSE | Visiting Researcher FAIR @AiatMeta I Prev. Research Engineer @sgSMU | CSE @IITKanpur '22
Klara Kaleb @klarakaleb
496 Followers 3K Following postdoc @OxCSML @NatureRecovery 🌱 AI for Social Good @barefootlaw_org 🌍 prev @ClopathLab @TheTeamAtX @ucl @klarakaleb.bsky.social
AfSept. @Shown1088
13 Followers 315 Following
L @CodeTitanium
101 Followers 5K Following
Sidney Tio @SeedneyTio
19 Followers 128 Following Research Intern @SakanaAILabs | PhD Student in Reinforcement Learning, Curriculum Learning @sgSMU 🇸🇬
Carolyn @draincarolyn38
167 Followers 3K Following
Ivan Radkevich @radke149
39 Followers 1K Following La vie n'a pas d'prix Mais la muerte coute cher @UMNComputerSci
Grad @Grad62304977
4K Followers 2K Following
Bushrebate @bushrebate38761
0 Followers 10 Following
leloy! @leloykun
7K Followers 4K Following Math @ AdMU • NanoGPT speedrunner • Muon fan 🤍 • prev ML @ XPD • 2x IOI & 2x ICPC • https://t.co/nfO038itfn
oeohomos @joeohomos
48 Followers 2K Following
Alpay Ariyak @AlpayAriyak
3K Followers 3K Following Post-Training Lead @ Together AI | OpenChat Project Lead (#1 7B LLM on Arena for 2+ months, 2M+ downloads) | DeepCoder, DeepSWE
Zark Muckerburg @zplus1_
22 Followers 1K Following ai/ml open for research internship roles in computer vision (diffusion / rect flow specifically)
Mr. Jack Tung @MrJackTung
294 Followers 6K Following
Stephen Oates @stephenjaoates
810 Followers 7K Following
Ofir Press @OfirPress
15K Followers 6K Following I build tough benchmarks for LMs and then I get the LMs to solve them. SWE-bench & SWE-agent. Postdoc @Princeton. PhD @nlpnoah @UW.
Xiaosen Zheng @xszheng2020
597 Followers 2K Following Researcher @ TikTok 📄 RegMix 💼 Past: PhD @sgSMU | Intern @SeaAIL 🧠 Interests: Data-Centric AI | Code AI
Runxin Xu @pigjunebaba
7K Followers 3K Following AI researcher @deepseek_ai | @PKU1898 | @SJTU1896 Opinions are my own.
Adam Falls @AdamFalls172137
53 Followers 4K Following
Penghui Qi @QPHutu
121 Followers 105 Following Senior Research Engineer @SeaAIL PhD student @NUSingapore Working on RL, LLM Reasoning, and MLSys.
AISecHub @AISecHub
4K Followers 4K Following 🚀 AISecHub | AI & Cybersecurity | Discussing AI-driven threats, securing AI systems, and sharing insights on emerging challenges 💡
Eva Louise Marie Gabr... @e681554349
11 Followers 7K Following
Louella Gala ❤️ M... @GalaLouell59785
10 Followers 106 Following
Burny - Effective Cur... @burny_tech
19K Followers 8K Following On the quest to understand the fundamental mathematics of intelligence and of the universe with curiosity. https://t.co/mMchI2d4pg Upskilling @StanfordOnline
Tianyu Pang @TianyuPang1
1K Followers 311 Following 🇸🇬Research Scientist at Sea AI Lab @SeaGroup; 👨🏻🎓PhD/BS from @Tsinghua_Uni and ex-@MSFTResearch; 🛡️Trustworthy AI and Generative Models.
Jun (Richard) Wang @AI_richard
35 Followers 1K Following
Morgan McGuire @morgymcg
3K Followers 4K Following Applied AI @weights_biases | ex-Facebook Safety | https://t.co/a7i7G5dkLG | 🇮🇪 | Came for the bants, stayed for the rants
Shital Shah @sytelus
13K Followers 11K Following Mostly research and code. If universe is an optimizer, what is its loss function? All opinions are my own.
Nathan Benaich @nathanbenaich
61K Followers 34K Following solo member of investment staff @airstreet @airstreetpress @stateofaireport @raais
Changyu Chen @Cameron_Chann
252 Followers 244 Following PhD student @sgSMU. RL x LLMs. Previously @NTUsg, @ZJU_China Post-training for Sailor2
Varun Bhatt @vbhatt_cs
71 Followers 60 Following PhD Student at the University of Southern California
MoMo @XiaoPangHuBB
5 Followers 5K Following
Arunesh Sinha @aruneshsinha
147 Followers 114 Following Assistant Professor at Rutgers Business School, Interested in anything interesting!
Pradeep Varakantham @PradeepVarakan1
148 Followers 180 Following Professor of Computer Science, Lee Kuan Yew Fellow, School of Computing and Information Systems, Singapore Management University
Jason Wei @_jasonwei
98K Followers 634 Following ai researcher @meta superintelligence labs, past: openai, google 🧠
Yi Tay @YiTayML
46K Followers 81 Following research scientist @googledeepmind ✨♊, model co-lead/captain of gemini deepthink imo gold medal 🥇, opinions are my own.
Stefano Ermon @StefanoErmon
20K Followers 373 Following AI Prof @Stanford | CEO & Cofounder @InceptionAILabs | Co-inventor of DDIM, FlashAttention, DPO, GAIL, and score-based/diffusion models
Lilian Weng @lilianweng
163K Followers 166 Following Co-founder of Thinking Machines Lab @thinkymachines; Ex-VP, AI Safety & robotics, applied research @OpenAI; Author of Lil'Log
fly51fly @fly51fly
8K Followers 2K Following BUPT prof | Sharing latest AI papers & insights | Join me in embracing the AI revolution! #MachineLearning #AI #Innovation
Anna Goldie @annadgoldie
7K Followers 137 Following Senior Staff Research Scientist at @GoogleDeepMind. Prev: @AnthropicAI, @StanfordNLP, @MIT. AlphaChip co-lead.
Sidney Tio @SeedneyTio
19 Followers 128 Following Research Intern @SakanaAILabs | PhD Student in Reinforcement Learning, Curriculum Learning @sgSMU 🇸🇬
Quentin Gallouédec @QGallouedec
3K Followers 664 Following PhD - Research @huggingface 🤗 TRL lead maintainer 🇫🇷 in 🇨🇦
Penghui Qi @QPHutu
121 Followers 105 Following Senior Research Engineer @SeaAIL PhD student @NUSingapore Working on RL, LLM Reasoning, and MLSys.
Nathan Lambert @natolambert
56K Followers 853 Following Figuring out AI @allen_ai, open models, RLHF, fine-tuning, etc Contact via email. Writes @interconnectsai Wrote The RLHF Book Mountain runner
Alexander Doria @Dorialexander
19K Followers 4K Following Reasoning models to come. Co-founder @pleiasfr
Chujie Zheng @ChujieZheng
6K Followers 301 Following Researcher @Alibaba_Qwen | GSPO, Qwen3, QwQ, ProcessBench | Opinions are my own
Wenhu Chen @WenhuChen
22K Followers 664 Following AI researcher. Interested in Reasoning, Multimodal. I direct TIGER-Lab. Author of PoT, MMMU, MMLU-Pro, MAmmoTH, LongRAG, MAP-Neo, YuE, VL-Rethinker
Runxin Xu @pigjunebaba
7K Followers 3K Following AI researcher @deepseek_ai | @PKU1898 | @SJTU1896 Opinions are my own.
Xiaosen Zheng @xszheng2020
597 Followers 2K Following Researcher @ TikTok 📄 RegMix 💼 Past: PhD @sgSMU | Intern @SeaAIL 🧠 Interests: Data-Centric AI | Code AI
John Schulman @johnschulman2
65K Followers 1K Following Recently started @thinkymachines. Interested in reinforcement learning, alignment, birds, jazz music
Peiyi Wang @sybilhyz
11K Followers 302 Following PhD @PKU1898; Researcher @deepseek_ai; Recent: DeepSeek-R1/CoderV2/Math/V1/V2/V3, Mathshepherd, FairEval, Speculative Decoding.
Min Lin @mavenlin
179 Followers 203 Following
Chao Du @duchao0726
107 Followers 129 Following Research Scientist @SeaGroup; Prev Ph.D. @Tsinghua_Uni;
Qian Liu @sivil_taram
4K Followers 743 Following Researcher @ TikTok 🇸🇬 📄 Sailor / StarCoder / OpenCoder 💼 Past: Research Scientist @SeaAIL; PhD @MSFTResearch 🧠 Contribution: @XlangNLP @BigCodeProject
Jun (Richard) Wang @AI_richard
35 Followers 1K Following
Morgan McGuire @morgymcg
3K Followers 4K Following Applied AI @weights_biases | ex-Facebook Safety | https://t.co/a7i7G5dkLG | 🇮🇪 | Came for the bants, stayed for the rants
Shital Shah @sytelus
13K Followers 11K Following Mostly research and code. If universe is an optimizer, what is its loss function? All opinions are my own.
Nathan Benaich @nathanbenaich
61K Followers 34K Following solo member of investment staff @airstreet @airstreetpress @stateofaireport @raais
Tianyu Pang @TianyuPang1
1K Followers 311 Following 🇸🇬Research Scientist at Sea AI Lab @SeaGroup; 👨🏻🎓PhD/BS from @Tsinghua_Uni and ex-@MSFTResearch; 🛡️Trustworthy AI and Generative Models.
Changyu Chen @Cameron_Chann
252 Followers 244 Following PhD student @sgSMU. RL x LLMs. Previously @NTUsg, @ZJU_China Post-training for Sailor2
Jenny Zhang @jennyzhangzt
4K Followers 917 Following RS Intern @AIatMeta • PhDing @UBC @VectorInst • Undergrad @imperialcollege • Reinforcement Learning, Self-Improving AI, Open-endedness
Matt Fontaine @tehqin17
462 Followers 242 Following roboticist PhD trained @ USC, Algorithms Live! host, ICPC judge, USACO coach https://t.co/WaIWptKeot
Jack Parker-Holder @jparkerholder
9K Followers 779 Following Co-lead of Genie 3 @GoogleDeepMind & Honorary Associate Professor @UCL_DARK. Dad (👶🐶), CFC fan, BJJ. Views are my own :)
Stefanos Nikolaidis @snikolaidis19
1K Followers 181 Following Associate Professor @USC. PhD from @CMU_Robotics, MS from @MIT, MEng from #UTokyo, BS from @NTUA. Previously worked at @SquareEnix in Tokyo.
Varun Bhatt @vbhatt_cs
71 Followers 60 Following PhD Student at the University of Southern California
Jeff Clune @jeffclune
29K Followers 431 Following Professor, CS, U. British Columbia. CIFAR AI Chair, Vector Institute. Sr. Advisor, DeepMind | ML, AI, deep RL, deep learning, AI-Generating Algorithms (AI-GAs)
Tim Rocktäschel @_rockt
39K Followers 2K Following Director and Open-Endedness Team Lead @GoogleDeepMind, Professor of AI @AI_UCL, PI @UCL_DARK, Fellow @ELLISforEurope.
Michael Dennis @MichaelD1729
4K Followers 813 Following Open-Endedness RS @GoogleDeepMind. Building for an unspecifiable world | Unsupervised Environment Design, Game&Decision Theory, RL, AIS. prev @CHAI_Berkeley
Milind Tambe (moving ... @MilindTambe_AI
8K Followers 270 Following @Harvard Professor & Director Ctr for Computation & Society @HCRCS @GoogleDeepMind Principal Scientist & Director #AIforGood #AIforhealth #AIforConservation
Arunesh Sinha @aruneshsinha
147 Followers 114 Following Assistant Professor at Rutgers Business School, Interested in anything interesting!
Pradeep Varakantham @PradeepVarakan1
148 Followers 180 Following Professor of Computer Science, Lee Kuan Yew Fellow, School of Computing and Information Systems, Singapore Management University
Minqi Jiang @MinqiJiang
6K Followers 880 Following
Bob Wen @BobWen16
2 Followers 18 Following
Delvin Ce Zhang @delvincezhang
25 Followers 60 Following Assistant Professor @SheffieldNLP @sheffielduni, working on Multimodal LLM, RAG, Misinformation Detection, Recommender Systems, and AI for Science.
Hugh Lee @HughLee65444358
4 Followers 26 Following
Chelsea Finn @chelseabfinn
82K Followers 399 Following Asst Prof of CS & EE @Stanford Co-founder of Physical Intelligence @physical_int PhD from @Berkeley_EECS, EECS BS from @MITTrends for United States
30,9 B posts
62,8 B posts
51,4 B posts
6.608 posts
6.734 posts
34,6 B posts
67,6 B posts
8.868 posts
7.370 posts
39,1 B posts
36 B posts
39,5 B posts
7.522 posts
31,6 B posts
29,3 B posts
2.968 posts
46,5 B posts
9.708 posts
1.920 posts
7.224 posts
You might like
Kuan-Hao Huang
@kuanhaoh_
1K Followers
Yuzhe Yang
@yang_yuzhe
3K Followers
Guan-Horng Liu
@guanhorng_liu
1K Followers
Kai Wang
@kaiwang_gua
963 Followers
Steven Pei 白先慎
@StevenPei5
510 Followers
Liman Zhang
@zhang_liman
490 Followers
ICAPS Conference
@ICAPSConference
539 Followers
Rohan Chandra
@rohanchandra30
1K Followers
Yuchen Li
@_Yuchen_Li_
719 Followers
Pingsheng Liu
@PLIU74726252
577 Followers
Hu Xu
@Hu_Hsu
723 Followers
Xu Zhang 张旭
@xuzhang95
318 Followers
Yumo Xu
@yumo_xu
758 Followers
Sandhya Saisubramania...
@sandhya_ai
410 Followers
Nicola Branchini
@Branchini_Nic
777 Followers