Zhepei Wei @weizhepei
Ph.D. Student @CS_UVA | Research Intern @Meta. Previously @AmazonScience. Research interest: ML/NLP/LLM. cs.virginia.edu/~tqf5qb/ Charlottesville, VA Joined January 2016-
Tweets88
-
Followers192
-
Following533
-
Likes2K
OpenAI realesed new paper. "Why language models hallucinate" Simple ans - LLMs hallucinate because training and evaluation reward guessing instead of admitting uncertainty. The paper puts this on a statistical footing with simple, test-like incentives that reward confident…
🔮 Introducing Prophet Arena — the AI benchmark for general predictive intelligence. That is, can AI truly predict the future by connecting today’s dots? 👉 What makes it special? - It can’t be hacked. Most benchmarks saturate over time, but here models face live, unseen…
Thrilled to share this exciting work, R-Zero, from my student @ChengsongH31219 where LLM learns to reason from Zero human-curated data! The framework includes co-evolution of a "Challenger" to propose difficult tasks and a "Solver" to solve them. Check out more details in the…
Thrilled to share this exciting work, R-Zero, from my student @ChengsongH31219 where LLM learns to reason from Zero human-curated data! The framework includes co-evolution of a "Challenger" to propose difficult tasks and a "Solver" to solve them. Check out more details in the…
🚀🚀Excited to share our paper R-Zero: Self-Evolving Reasoning LLM from Zero Data ! How to train LLM without data? R-Zero teaches Large Language Models to reason starting with nothing but a base model. No data required!!! Paper: arxiv.org/abs/2508.05004 Code:…
R-Zero Self-Evolving Reasoning LLM from Zero Data
We’re running another round of the Anthropic Fellows program. If you're an engineer or researcher with a strong coding or technical background, you can apply to receive funding, compute, and mentorship from Anthropic, beginning this October. There'll be around 32 places.
As AI agents start taking real actions online, how do we prevent unintended harm? We teamed up with @OhioState and @UCBerkeley to create WebGuard: the first dataset for evaluating web agent risks and building real-world safety guardrails for online environments. 🧵
There will be *no more than 5 days* between the release of GSPO and its implementation in TRL
New paper alert: Unifies insights from Limit-of-RLVR and ProRL — does current RLVR actually expand reasoning? Turns out: RLVR is mostly an efficient sampler with shrinking, very rarely an explorer with explanding. Explore is holy grail for LLM and may entail beyond 0/1 reward.
Proud to introduce Group Sequence Policy Optimization (GSPO), our stable, efficient, and performant RL algorithm that powers the large-scale RL training of the latest Qwen3 models (Instruct, Coder, Thinking) 🚀 📄 huggingface.co/papers/2507.18…
Highlight of my #ICML2025 poster session: “So… did you train your model on the test set?” 😅 Probably the ML community’s new “standard practice” question — sadly necessary, but here we are 🤦♂️
I wrote a post on how to connect with people (i.e., make friends) at CS conferences. These events can be intimidating so here's some suggestions on how to navigate them I'm late for #ICLR2025 #NAACL2025, but just in time for #AISTATS2025 and timely for #ICML2025 acceptances! 1/4
🚨 LLM-as-a-Judge in RLVR can be easily hacked, even GPT-4o. Simple sentences can trick top models into false positives, although the task is just to compare a given solution to a reference answer. 📊 What we found: 1️⃣ Figure 1: “:” and “Thought process:” fool nearly all models…
🚨 LLM-as-a-Judge in RLVR can be easily hacked, even GPT-4o. Simple sentences can trick top models into false positives, although the task is just to compare a given solution to a reference answer. 📊 What we found: 1️⃣ Figure 1: “:” and “Thought process:” fool nearly all models… https://t.co/bntIRoHRMU
Will be at #ICML2025 next week! We'll present the following works: 🛠️ LarPO: Tue 7/15 (Poster Session 1 East) 🚀 AdaDecode: Wed 7/16 (Poster Session 3 East) 🧮 Negative Reinforcement for Reasoning: Fri 7/18 (AI for Math Workshop) Happy to chat about latest research in LLMs🤩
What Makes a Base Language Model Suitable for RL? Rumors in the community say RL (i.e., RLVR) on LLMs is full of “mysteries”: (1) Is the magic only happening on Qwen + Math? (2) Does the "aha moment" only spark during math reasoning? (3) Is evaluation hiding some tricky traps?…
Here's my conversation with Terence Tao, one of the greatest mathematicians in history. We talk about the hardest problems in mathematics & physics, and how AI might help us humans to solve them. This conversation was a huge honor for me. I can't quite put it into words, but…
Nice work! In our recent paper WebAgent-R1 (arxiv.org/abs/2505.16421), we also observed a similar finding—test-time scaling via increased interactions! Feels like we’re not far from discovering new scaling laws for agents!🤩
Nice work! In our recent paper WebAgent-R1 (arxiv.org/abs/2505.16421), we also observed a similar finding—test-time scaling via increased interactions! Feels like we’re not far from discovering new scaling laws for agents!🤩 https://t.co/eCOHrC397C
🚀🚀Excited to share our new work on Speculative Decoding by @shrangoh! We tackle a key limitation in draft models which predict worse tokens at later positions, and present PosS that generates high-quality drafts!
🚀🚀Excited to share our new work on Speculative Decoding by @shrangoh! We tackle a key limitation in draft models which predict worse tokens at later positions, and present PosS that generates high-quality drafts!
Yuma @yumahey
752 Followers 922 Following Autonomous businesses | https://t.co/ZB2pK7boKG | built one of the world’s first AI agents '23 in prod w 100k users
Evelyn @w_evelyn99
260 Followers 3K Following
Adithya Bhaskar @AdithyaNLP
359 Followers 351 Following Third year CS PhD candidate at Princeton University (@princeton_nlp @PrincetonPLI), previously CS undergrad at IIT Bombay
JinnyYang @jinny61767
3 Followers 72 Following
Jahidul Islam @JahidulZaid
222 Followers 76 Following
Shicheng Liu @ShichengGLiu
195 Followers 180 Following CS Phd @StanfordNLP @StanfordOVAL RS Intern @meta
Jason Liu @JasonLiu106968
76 Followers 71 Following
AlexiaHarper @47v1F6z9tUU6Tn
5 Followers 77 Following
Andy Jin @JinHuangStudy
193 Followers 984 Following
Keplore AI Inc. @KeploreAI
131 Followers 290 Following Run complex AI with 0 setup-- Autonomous Intelligence Builder.
Wuao Liu @liu_wuao
327 Followers 1K Following CS PhD Student @UMassAmherst | Prev @UMRobotics @ZJU_China | Computer Vision, AI4Science
Miwa - azooKeyの開�... @miwa_ensan
3K Followers 2K Following 🎓M1（休学中）｜💻TuringでMLエンジニア｜🚀未踏IT2024スパクリ｜🫘ニューラル日本語入力システム @azooKey_dev 開発｜💡NLP・言語学・UI・フォント・文字・タイポグラフィ・画像処理など｜📩DM歓迎！
Zeyu Huang @ZeroyuHuang
139 Followers 131 Following PhD @EdinburghNLP Working on LLM | Student Researcher @GoogleDeepmind
Guillaume Le Strat @GuillaumeLST
398 Followers 3K Following @zml_ai Tech, startups, data & music Paris - South of France
Rhea Shields @RheaS22772
71 Followers 3K Following
Junhyuck Kim @jhyuckkim
23 Followers 140 Following
Wenqi Shi @WenqiShi0106
270 Followers 629 Following Assistant Professor @UTSWMedCenter | Ph.D. @GeorgiaTech | LLMs | Agent | RAG | EHRs | Clinical Decision Support | Pediatric Healthcare
Visual-Intelligence @VI_Journal_CSIG
143 Followers 2K Following Official journal of China Society of Image and Graphics (CSIG). The jouarnl is published by Springer, sponsored by CSIG. E-ISSN 2731-9008.
Yuntian Deng @yuntiandeng
8K Followers 3K Following Assistant Professor @UWaterloo | Visiting Professor @NVIDIA | Associate @Harvard | Faculty Affiliate @VectorInst | Former Postdoc @ai2_mosaic | PhD @Harvard
anhydron @anhydron
58 Followers 3K Following
Henry Peng Zou @zou_henry43378
32 Followers 77 Following CS PhD @UIC | Applied Scientist Intern @AWS AI @Amazon | GenAI Research Intern @Zoom | LLMs & Agents
Tyler Griggs @tyler_griggs_
690 Followers 375 Following CS PhD student @UCBerkeley Sky Lab, co-leading @NovaSkyAI and building SkyRL | Previously @GoogleCloud infra | @Harvard 2020
Longtao Zheng @ltzheng01
153 Followers 570 Following PhD student @NTUsg. Training open-ended agents in open-ended worlds
Zhichao Xu Brutus @zhichaoxu_ir
241 Followers 528 Following Interested in NLP & IR. Currently scientist @awscloud. Prev CS PhD @UtahNLP; intern @GoogleAI @Dataminr @Visa.
wang @weixunwang
111 Followers 924 Following
Junhong Shen @JunhongShen1
2K Followers 572 Following PhD Student @mldcmu | BS @UCLA | Student Researcher @GoogleDeepMind | Interned @AIatMeta @MSFTResearch @DeterminedAI
Mickel Liu @mickel_liu
404 Followers 434 Following PhD student @uwcse/@uwnlp · visiting researcher @AIatMeta FAIR · I do LLM+RL · Prev: @pkucfcs2017, @uoftengineering
Taiqiang Wu @wu_taiqiang
83 Followers 296 Following Now a PhD student at @HKUniversity Master & B. Eng in @Tsinghua_Uni
Gaotang Li @GaotangLi
82 Followers 177 Following Ph.D. @UofIllinois | Undergrad @UMich. Language Models.
Liang Qiu @liangqiu_1994
254 Followers 613 Following Senior Applied Scientist @amazon. PhD @VCLA_UCLA. Past: @Salesforce, @MSFTResearch. Opinions are my own.
Maurice Weber @mauriceweberq
142 Followers 620 Following MTS @MicrosoftAI | previously @togethercompute @ETH_en
Langlin Huang @shrangoh
19 Followers 73 Following NLPer, LLM Reasoning, Multilingual. 1st. Year Ph.D. at Washington University in St. Louis.
Fredrik K. Gustafsson @fregu856
862 Followers 4K Following Postdoc at IBME in Oxford. Machine learning for healthcare. I'm more active on https://t.co/vwXdiYvHig.
Qiao Jin, MD @DrQiaoJin
2K Followers 975 Following Medical AI @NIH. MD @Tsinghua_Uni. K99 Awardee. Editor @jmirpub @JBI_Journal @ReviewAcl. PubMedQA, MedCPT, MedRAG, GeneGPT, GeneAgent, TrialGPT. Views my own.
Zhengliang Shi @Zhengliang_Shi
30 Followers 263 Following retrieval-augmented generation, knowledge discovery, LLM-based Agent
Yoram Bachrach @yorambac
3K Followers 7K Following Research Scientist at Meta (prev Google DeepMind and Microsoft Research). Working on LLM Agents and Multi-Agent Systems.
Yuetai Li @yuetai12575
227 Followers 571 Following Second year PhD @UW | Post-Training, LLM reasoning and synthetic dataset. https://t.co/cYAkbnCsCp Open to chat and collaborate!
Yuchen Zhuang @yuchen_zhuang
891 Followers 359 Following Research Scientist @GoogleDeepMind | Gemini Thinking & Coding | LLM Agent | Prev: PhD @MLatGT | Opinions are my own.
Zhongwen Xu @zhongwen2009
1K Followers 1K Following Principal Researcher at Tencent, ex-DeepMinder (@GoogleDeepMind), ex-SAILer (@SeaAIL)
Adithya Bhaskar @AdithyaNLP
359 Followers 351 Following Third year CS PhD candidate at Princeton University (@princeton_nlp @PrincetonPLI), previously CS undergrad at IIT Bombay
Subbarao Kambhampati ... @rao2z
26K Followers 68 Following AI researcher & teacher @SCAI_ASU. Former President of @RealAAAI; Chair of @AAAS Sec T. Here to tweach #AI. YouTube Ch: https://t.co/4beUPOmf6y Bsky: rao2z
Rohan Paul @rohanpaul_ai
97K Followers 8K Following Compiling in real-time, the race towards AGI. The Largest Show on X for AI. 🗞️ Get my daily AI analysis newsletter to your email 👉 https://t.co/6LBxO8215l
Vik Paruchuri @VikParuchuri
15K Followers 184 Following Open source AI. Founder of @datalabto Past: founded @dataquestio
Fei-Fei Li @drfeifei
526K Followers 1K Following Prof (CS @Stanford), Co-Director @StanfordHAI, Cofounder/CEO @theworldlabs, #AI #SpatialIntelligence #GenAI #computervision #robotics #AI-healthcare
Open Philanthropy @open_phil
18K Followers 231 Following Open Philanthropy's mission is to help others as much as we can with the resources available to us.
Thang Luong @lmthang
27K Followers 95 Following Lead Superhuman Reasoning team @GoogleDeepMind. AI IMO Gold. Co-led #DeepThink, #AlphaGeometry, #Bard (now Gemini) Multimodality, #MeenaBot. LuongAttention.
Fei Liu @feiliu_nlp
2K Followers 886 Following Associate professor @EmoryUniversity. Working on large language models, LLM inference, reasoning, natural language generation, and various aspects of GenAI.
Susan Zhang @suchenzang
34K Followers 700 Following @ Google Deepmind. Past: @MetaAI, @OpenAI, @unitygames, @losalamosnatlab, @Princeton etc. Always hungry for intelligence.
Saining Xie @sainingxie
23K Followers 1K Following researcher in #deeplearning #computervision | assistant prof at @nyu_courant | rs @googledeepmind | past: rs @meta (FAIR) @ucsandiego | ynwa
Paul Liang @pliang279
8K Followers 710 Following Assistant Professor MIT @medialab @MITEECS @nlp_mit || PhD from CMU @mldcmu @LTIatCMU || Foundations of multisensory AI to enhance the human experience.
Jessy Lin @realJessyLin
3K Followers 889 Following PhD @Berkeley_AI, visiting researcher @AIatMeta. Interactive language agents 🤖 💬
Feng Yao @fengyao1909
1K Followers 662 Following Ph.D. student @UCSD_CSE | Intern @Amazon Rufus Foundation Model Ex. @MSFTResearch @TsinghuaNLP
Shicheng Liu @ShichengGLiu
195 Followers 180 Following CS Phd @StanfordNLP @StanfordOVAL RS Intern @meta
Henry Peng Zou @zou_henry43378
32 Followers 77 Following CS PhD @UIC | Applied Scientist Intern @AWS AI @Amazon | GenAI Research Intern @Zoom | LLMs & Agents
Eliahu Horwitz @EliahuHorwitz
605 Followers 293 Following PhD student at @CseHuji | Passionate about model weights as a new data modality, and yoga - not necessarily in that order 😉 | Ex Intern Google Research.
Jason Liu @JasonLiu106968
76 Followers 71 Following
Zifan (Sail) Wang @_zifan_wang
607 Followers 507 Following @AIatMeta MSL | ex-RS @scale_AI (SEAL) and @ai_risks | PhD Alumni of CMU @cylab | Opinions of my own
Ming Yin @MingYin_0312
2K Followers 922 Following ML, RL, AI. @Princeton Postdoc. PhDs in CS & STATs. Ex @awscloud AI. undergrad @USTC Math. Area Chair @NeurIPS @ICML.
Chengshuai Zhao @ChengshuaiZhao
73 Followers 72 Following CS Ph.D. @ ASU Data Mining, AI4Science, LLMs
Isha Puri @ishapuri101
804 Followers 419 Following AI / NLP PhD-ing @MIT_CSAIL @nlp_mit, currently product @AbridgeHQ prev @Harvard /HBS
Mira Murati @miramurati
371K Followers 574 Following Now building @thinkymachines. Previously CTO @OpenAI
qizhe cai @CaiQizhe
228 Followers 157 Following Incoming Assistant Professor at UVA. I am building network stack/protocols/hardware for Terabit Ethernet.
Chujie Zheng @ChujieZheng
6K Followers 305 Following Researcher @Alibaba_Qwen | GSPO, Qwen3, QwQ, ProcessBench | Opinions are my own
Quentin Gallouédec @QGallouedec
3K Followers 675 Following PhD - Research @huggingface 🤗 TRL lead maintainer 🇫🇷 in 🇨🇦
Shizhe Diao @shizhediao
4K Followers 2K Following Research Scientist @NVIDIA focusing on efficient post-training of LLMs. Finetuning your own LLMs with LMFlow: https://t.co/UTykmQBwFr Views are my own.
Yang Yue @YangYue_THU
617 Followers 205 Following 🎓phd in Tsinghua University. Focus on RL, Embodied AI, and MLLM. 📖Author of limit-of-RLVR，phyworld，DeeR-VLA. 💼Seek a visit currently.
Wuao Liu @liu_wuao
327 Followers 1K Following CS PhD Student @UMassAmherst | Prev @UMRobotics @ZJU_China | Computer Vision, AI4Science
Fu-En (Fred) Yang @FuEnYang1
618 Followers 1K Following Research Scientist @NVIDIAAI | Ph.D. @NTU_TW | Prev. Research Intern @NVIDIAAI | Vision & Language | Multimodal AI
Zeyu Huang @ZeroyuHuang
139 Followers 131 Following PhD @EdinburghNLP Working on LLM | Student Researcher @GoogleDeepmind
Aryo Pradipta Gema @aryopg
1K Followers 2K Following AI Safety Fellow @Anthropic | PhD student @BioMedAI_CDT @EdinburghNLP @EdiClinicalNLP LLM Hallucinations | Clinical NLP | Opinions are my own.
ZML @zml_ai
2K Followers 2 Following High performance inference. Any model. Any hardware. No compromise. Zig / OpenXLA / MLIR / Bazel.
Steeve Morin @steeve
6K Followers 1K Following Building @zml_ai (and we're hiring), ex @zenly, ex Exalead, ex @google. Skydiver and wingsuiter.
Delta Institute @DeltaInstitutes
1K Followers 60 Following Supporting exceptional researchers/engineers, from academia to industry and beyond.
Alexander Wei @alexwei_
24K Followers 194 Following Reasoning @OpenAI. Co-built CICERO @MetaAI | @Berkeley_AI PhD '23 | @Harvard '20
Ed H. Chi @edchi
13K Followers 4K Following Research VP @ GoogleDeepMind. ex-Lead for LaMDA/Bard. Now focused on personalized reasoning & Astra universal personalized assistants. ACM Fellow.
Junhyuck Kim @jhyuckkim
23 Followers 140 Following
Hyung Won Chung @hwchung27
38K Followers 303 Following AI Research Scientist @Meta Superintelligence Labs. Past: @OpenAI / @Google Brain / PhD @MIT
Wenqi Shi @WenqiShi0106
270 Followers 629 Following Assistant Professor @UTSWMedCenter | Ph.D. @GeorgiaTech | LLMs | Agent | RAG | EHRs | Clinical Decision Support | Pediatric Healthcare
Yuntian Deng @yuntiandeng
8K Followers 3K Following Assistant Professor @UWaterloo | Visiting Professor @NVIDIA | Associate @Harvard | Faculty Affiliate @VectorInst | Former Postdoc @ai2_mosaic | PhD @Harvard
Zhaoran Wang @zhaoran_wang
4K Followers 1K Following Associate Professor @NorthwesternU | PhD @Princeton | studying Reinforcement Learning
Yiding Jiang @yidingjiang
2K Followers 608 Following PhD student @mldcmu @SCSatCMU. Formerly intern @MetaAI, AI resident @GoogleAI. BS from @Berkeley_EECS. Trying to understand stuff.
Longhui Yu @scut_longhui
988 Followers 1K Following Post-training in KIMI @Kimi_Moonshot | MS Peking University @PKU1898 Author of MetaMath, Easy2hard generalization, NuminaMath, Kimi k1.5, Kimi K2
Chenlu Ye @ye_chenlu
257 Followers 268 Following Ph.D. student at UIUC, interested in RL reasoning, agent
Hanning Zhang @HanningZhangHK
158 Followers 698 Following MSCS student at UIUC. Previously undergraduate student at The Hong Kong University of Science and Technology (HKUST). Interested in NLP and LLMTrends for United States
You might like
