Yang Chen @ychenNLP
Research Scientist @NVIDIA | PhD @GeorgiaTech| RL and LLM reasoning edchengg.github.io Joined September 2018-
Tweets75
-
Followers1K
-
Following554
-
Likes2K
Having thought about it some more, I think the 50 million H100 equivalent number in 5 years is about right. Eventually, billions.
Having thought about it some more, I think the 50 million H100 equivalent number in 5 years is about right. Eventually, billions.
Cable pr0n of @xai GB200 servers at Colossus 2
we have signed a deal for an additional 4.5 gigawatts of capacity with oracle as part of stargate. easy to throw around numbers, but this is a _gigantic_ infrastructure project. some progress photos from abilene:
Our released evaluation toolkit can reproduce our AceReason-Nemotron models numbers (see below): AceReason-Nemotron-1.0-7B: LiveCodeBench (Avg@8): * [05/23-05/24]: 72.0; [06/24-01/25]: 54.2 * release set v5: 51.2; release set v6: 44.4 AIME (Avg@64): * AIME'24: 68.6; AIME'25:…
Our released evaluation toolkit can reproduce our AceReason-Nemotron models numbers (see below): AceReason-Nemotron-1.0-7B: LiveCodeBench (Avg@8): * [05/23-05/24]: 72.0; [06/24-01/25]: 54.2 * release set v5: 51.2; release set v6: 44.4 AIME (Avg@64): * AIME'24: 68.6; AIME'25:…
The first thing we did was to make sure the eval setup is correct! We spend a lot of time to make sure our eval can - accurately reproduce the DeepSeek-R1 numbers on AIME, LiveCodeBench - it's IMPOSSIBLE to track the RL progress without a good eval set up (e.g., we see AIME up…
The first thing we did was to make sure the eval setup is correct! We spend a lot of time to make sure our eval can - accurately reproduce the DeepSeek-R1 numbers on AIME, LiveCodeBench - it's IMPOSSIBLE to track the RL progress without a good eval set up (e.g., we see AIME up…
📌Paper: arxiv.org/abs/2506.13284 📌Model: huggingface.co/nvidia/AceReas… 📌SFT Data: huggingface.co/datasets/nvidi… 📌Math RL Data: huggingface.co/datasets/nvidi… A series of our work on reasoning models: 📌5/22/2025: AceReason-Nemotron: Scaling RL for math and code (7B and 14B)…
With stronger SFT backbone, AceReason-Nemotron-1.1-7B significantly outperforms its predecessor and sets a record-high performance among Qwen2.5-7B-based reasoning models. 📄Report: arxiv.org/pdf/2506.13284 🤗Model: huggingface.co/nvidia/AceReas… 📚SFT Data: huggingface.co/datasets/nvidi…
With stronger SFT backbone, AceReason-Nemotron-1.1-7B significantly outperforms its predecessor and sets a record-high performance among Qwen2.5-7B-based reasoning models. 📄Report: arxiv.org/pdf/2506.13284 🤗Model: huggingface.co/nvidia/AceReas… 📚SFT Data: huggingface.co/datasets/nvidi…
Introducing AceReason-Nemotron 1.1 Our previous release, AceReason-Nemotron-1.0, introduced a stage-wise RL recipe that was applied sequentially to math-only and code-only prompts, demonstrating both high efficiency and strong effectiveness. Here, we systematically investigate…
@etash_guha @ryanmart3n I tried to reproduce DS-R1-distilled-7B and AceReason-7B's performance on your split (06/24-01/25), and they turn out to be 41.9 and 54.6 correspondingly, which is obviously higher than your reported number. Anything wrong here? @etash_guha @ryanmart3n
Does RL incentive reasoning capability over the starting SFT model? We show an interesting result with our recent published AceReason-Nemotron-7B model, which was trained with RL pass@K from 1 to 1024 consistently +10% on LiveCodeBench v6 perhaps scaling RL is the key
Does RL incentive reasoning capability over the starting SFT model? We show an interesting result with our recent published AceReason-Nemotron-7B model, which was trained with RL pass@K from 1 to 1024 consistently +10% on LiveCodeBench v6 perhaps scaling RL is the key
Nvidia just dropped AceReason-Nemotron on Hugging Face Advancing Math and Code Reasoning through Reinforcement Learning
with just math-RL, AceReason-Nemotron-14B surpass DeepCoder-14B on LiveCodeBench v5. we then did code-RL and found training becomes so much easier
with just math-RL, AceReason-Nemotron-14B surpass DeepCoder-14B on LiveCodeBench v5. we then did code-RL and found training becomes so much easier https://t.co/UnRMojtLoh
Introducing AceReason-Nemotron: Advancing math and code reasoning through reinforcement learning (RL) We propose conducting RL on math-only prompts first, then on code-only prompts. Our key findings include: - Math-only RL significantly boosts both math and code benchmarks! -…
Introducing AceMath-RL-Nemotron-7B, a math reasoning model trained entirely through reinforcement learning from DeepSeek-R1-Distilled-Qwen-7B. It achieves AIME24: 69.0%, AIME25: 53.6%, and GPQA: 52.1%. Interestingly, this math-focused RL training also improves the coding…
Introducing AceMath-RL-Nemotron-7B, a math reasoning model trained entirely through reinforcement learning from DeepSeek-R1-Distilled-Qwen-7B. It achieves AIME24: 69.0%, AIME25: 53.6%, and GPQA: 52.1%. Interestingly, this math-focused RL training also improves the coding…
Had a lot of fun to scale up RL to improve math reasoning! Excited to introduce AceMath-RL-Nemotron-7B with a scalable training recipe 📑Full blog: research.nvidia.com/labs/adlr/acem… 🔗Model: huggingface.co/nvidia/AceMath…
Had a lot of fun to scale up RL to improve math reasoning! Excited to introduce AceMath-RL-Nemotron-7B with a scalable training recipe 📑Full blog: research.nvidia.com/labs/adlr/acem… 🔗Model: huggingface.co/nvidia/AceMath…
Earther @EartherAI
308 Followers 3K Following CS + AI/ML Student | Researching learning systems & applied ML |Model- Code-Insight
Jasmine Lesner @JasmineLesner
2 Followers 117 Following
Syeda Nahida Akter @SNAT02792153
464 Followers 534 Following PhD student at @LTIatCMU @SCSatCMU and research intern @NVIDIA. Working on improving Reasoning of Generative Models! (@reasyaay.bsky.social)
Joe Sanchez @JoeSanchez1213
84 Followers 4K Following
Feng Yao @fengyao1909
1K Followers 635 Following Ph.D. student @UCSD_CSE | Intern @Amazon Rufus Foundation Model Ex. @MSFTResearch @TsinghuaNLP
FENG Yang @fy2598099
22 Followers 1K Following
Denghui Zhang @denghui_zhang
476 Followers 674 Following Assistant Professor at Stevens Institute of Technology.
Jiayi He @ivy3h
6 Followers 135 Following
Jayashree Narayan @jayashrenarayan
2K Followers 3K Following incoming grad @FU_Berlin | prev: physics @iisermohali
Brian D. Colwell @briandcolwell
72K Followers 2K Following The future is being written in atoms and algorithms. My role is to help ensure we're reading that story accurately & positioning ourselves wisely. Quantum Nerd.
Rishi Khare @rishiskhare
141 Followers 248 Following Efficient reasoning research @GeorgiaTech @Berkeley_AI co-author of GEPA
Sanjeev Kumar @sanjeevkumar761
362 Followers 3K Following AI Research Engineer Architect. Deep Reinforcement Learning focus. Creator of Agent Canvas. https://t.co/P6YZjMwguR #agentcanvas
Wenyue Hua @HuaWenyue31539
1K Followers 637 Following senior researcher @ Microsoft Research, AI Frontiers Postdoc @ucsbNLP Ph.D. @RutgersCS KAUST AI Rising Star LLM-based agent, LLM reasoning
Stella Sonza Esver @EsverStella
405 Followers 1K Following The Twitter engagements of Mars' Ingenue of Ingenuity: @StarryMessenge2: leisurely Bird-watching (b) Sister Verissima: aggressive Duck-hunting
Cheng Qian @qiancheng1231
661 Followers 714 Following UIUC PhD @uiuc_nlp advised by @hengjinlp | Prev THU Undergrad @TsinghuaNLP advised by @zibuyu9 | Current intern @salesforce | #LLM #Agent
Hoang Phi Nguyen @nghgphi
4 Followers 43 Following
SABEEH @MElkton54569
178 Followers 8K Following Passionate about AI 🤖, ML 🧠, AGI 🌐, ASI 🚀, and robotics 🤖. Never lose hope in God's mercy 💫. AI Engineer Microsoft He studies at MIT. Free Palestine 🇵🇸
Ch Lee @chlee_itri
2 Followers 88 Following
Chankyu Lee @chankyul77
11 Followers 52 Following
aman chourasia @aman245_tweets
20 Followers 107 Following
Andre Shportko @ShportkoAndrii
11 Followers 38 Following AI threat defense. Language death prevention. Research @CHAI_Berkeley
Valentina Tardelli @ValentinaT32922
92 Followers 6K Following
Wu Haoning @HaoningTimothy
2K Followers 616 Following PhD Nanyang Technological University🇸🇬, BS @PKU1898, cooking VLMs in @Kimi_Moonshot. Opinions are personal.
Danny Liu @DannyLi49530886
4 Followers 353 Following
Rahel Jhirad @RahelJhirad
2K Followers 7K Following Founder, Imaginator ai knowledge discovery 2D navigation TS ML DL recsys econ math incentives mech design finance networks bridges boundaries, Time, 3d type
NK Niazi @NkNiazi7
24 Followers 462 Following PhD student in Computer Science @uporto | Research Fellow @INESCTEC | Python/Data Science Instructor | FCT Scholar | AI Research @AIRCentre | Porto 🇵🇹
Andrew David Meier @andrewdmeier
113 Followers 2K Following
Null @Null0____0
2 Followers 586 Following
umlaut @barbara_rhubarb
16 Followers 596 Following
Adam @1990Xtwo
7 Followers 452 Following [email protected] professional inquiries or memes only please.
keesha @KeeshaBrown96
645 Followers 7K Following The wind is free to come and go, and we will meet when we are supposed to meet. If you decide to be brilliant, there is no mountain to block you, and no sea to
Chenxin An @AnChancy46881
631 Followers 506 Following PhD Candidate @ HKUNLP Awardee of Hong Kong PhD Fellowship Scheme
Omar U. Florez 🇵�... @OmarUFlorez
3K Followers 2K Following Leading the Pre-Training of LatamGPT (70B LLM, 300B tokens) | Sr ML Researcher @Twitter Cortex, @CapitalOne, @Intel Labs | Co-Founder of @LatinXinAI 🧠🤖
Shahid Ahmed @zenweet
7 Followers 734 Following
Taiqiang Wu @wu_taiqiang
80 Followers 294 Following Now a PhD student at @HKUniversity Master & B. Eng in @Tsinghua_Uni
Masoud Jafaripour @mjafaripoor110
339 Followers 2K Following Researcher (CS @UAlbertaCS), Community @Cohere_Labs, focus on #Multimodal Vision-Language GenAI (#LLMs, #VLMs), #Reasoning, previously @SharifUni, @UnivOfTehran
vimkain @vimkain
4 Followers 465 Following
Feng Yao @fengyao1909
1K Followers 635 Following Ph.D. student @UCSD_CSE | Intern @Amazon Rufus Foundation Model Ex. @MSFTResearch @TsinghuaNLP
Ziyang Luo @ChiYeung_Law
1K Followers 3K Following Research Scientist @salesforce | Agents Researcher | Ex @MSFTResearch @AlibabaGroup @NUSingapore @HKBU_NLP
Wenyue Hua @HuaWenyue31539
1K Followers 637 Following senior researcher @ Microsoft Research, AI Frontiers Postdoc @ucsbNLP Ph.D. @RutgersCS KAUST AI Rising Star LLM-based agent, LLM reasoning
Cheng Qian @qiancheng1231
661 Followers 714 Following UIUC PhD @uiuc_nlp advised by @hengjinlp | Prev THU Undergrad @TsinghuaNLP advised by @zibuyu9 | Current intern @salesforce | #LLM #Agent
Chankyu Lee @chankyul77
11 Followers 52 Following
Yifei Li @YifeiLiPKU
722 Followers 629 Following Ph.D. student @osunlp | Prev MSc @PKU1898 | BEng @NEUChina | Prev Intern @MSFTResearch (MSRA) | LLM & NLPer
Heming Xia @hemingkx
1K Followers 2K Following Ph.D. student @HongKongPolyU | Prev MEng & BSc @PKU1898 | Prev Intern @MSFTResearch (MSRA) | NLP | Language Modeling
Wu Haoning @HaoningTimothy
2K Followers 616 Following PhD Nanyang Technological University🇸🇬, BS @PKU1898, cooking VLMs in @Kimi_Moonshot. Opinions are personal.
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
Chenyang Zhao @Chenan3_Zhao
211 Followers 412 Following I am a CS PhD student at the University of California, Los Angeles. I am supervised by Prof. Quanuan Gu and work closely with Prof. Ying Sheng.
Aaron Li @boolusilan
9K Followers 4K Following Daily FSD Videos! 🚗 Watch highlights! 📽️ | 👨💻 12y Amazon, Software Eng & Mgr | 🔋 Long $TSLA investor | Tesla referral: weimin899383
Vilém Zouhar @zouharvi
3K Followers 2K Following PhD student @ ETH Zürich | all aspects of #NLProc but mostly HCI, evaluation and MT | go #vegan
Chenxin An @AnChancy46881
631 Followers 506 Following PhD Candidate @ HKUNLP Awardee of Hong Kong PhD Fellowship Scheme
William Yijiang Li @Williamiumli
120 Followers 382 Following Ph.D. student @UCSanDiego, M.S. in CS @JohnsHopkins
Qian Liu @sivil_taram
4K Followers 743 Following Researcher @ TikTok 🇸🇬 📄 Sailor / StarCoder / OpenCoder 💼 Past: Research Scientist @SeaAIL; PhD @MSFTResearch 🧠 Contribution: @XlangNLP @BigCodeProject
Kai Wang @kkwang999
40 Followers 242 Following
Taco Cohen @TacoCohen
27K Followers 3K Following Post-trainologer at FAIR. Into codegen, RL, equivariance, generative models. Spent time at Qualcomm, Scyfer (acquired), UvA, Deepmind, OpenAI.
Sanjeev Satheesh @issanjeev
536 Followers 398 Following
Xiaosen Zheng @xszheng2020
597 Followers 2K Following Researcher @ TikTok 📄 RegMix 💼 Past: PhD @sgSMU | Intern @SeaAIL 🧠 Interests: Data-Centric AI | Code AI
Wooseok Seo @just1nseo
48 Followers 266 Following PhD Student @yonsei_u | Research Intern @LG_AI_Research
Francesco Bertolotti @f14bertolotti
815 Followers 130 Following Postdoctoral researcher at the university of Milan
Jeonghwan Kim @MasterJeongK
821 Followers 938 Following PhD student @IllinoisCDS @UIUC_NLP | Previously @kaistpr, @HandongUniv | Research Intern @Meta, @Amazon
Xinyu Zhu @tianhongzxy
359 Followers 467 Following CS Ph.D. student @UVA. Intern @Apple Foundation Models. Working on LLM Reasoning and RL. Previous master @Tsinghua_uni, intern @MSFTResearch.
Grad @Grad62304977
4K Followers 2K Following
Yumo Xu @yumo_xu
758 Followers 2K Following AI Scientist at AWS AI Labs (@AmazonScience). PhD @EdinburghNLP. I research, build, and evaluate AI systems. Opinions are my own.
Prasanna Sattigeri @prasatti
513 Followers 2K Following Principal Research Scientist @IBMResearch and @MITIBMLab.
Qingcheng Zeng @SteveZeng7
1K Followers 2K Following PhD-ing with @rfpvjr and @kaize0409 / social computing, LLMs / Big fan of @Arsenal / Intern @Snowflake @TencentGlobal @jhuclsp @NlpWestlake / Christian
Chloe H. Su @Huangyu58589918
503 Followers 920 Following CS PhD @Harvard @KempnerInst Automated Reasoning @AmazonScience Prev @mldcmu @ntusg
Jingyuan Qi @jingyuan_qi
10 Followers 8 Following
Cecil Li | 策看世�... @sharkroman
4K Followers 423 Following Crypto HODL since 2011 Building AI @ TikTok I come here to escape a censored world. Please excuse my random lightbulb moments and stupid shower thoughts.
Enze "Alex" Liu (on t... @alexliu1
67 Followers 154 Following PhD student @ UC San Diego CSE. Doing research in security/privacy. Only use Twitter to advertise my own work and "stalk" other ppl. Advertisements are my own.
Yu Meng @yumeng0818
2K Followers 334 Following Asst. Professor @CS_UVA (LLM/ML/NLP) Past: PhD from @IllinoisCS, visiting researcher @princeton_nlp, Google PhD Fellow.
Zonghan Yang @yang_zonghan
2K Followers 2K Following PhD student at Tsinghua NLP & AIR, studying agents that automate tasks ranging from daily activities to creative endeavors. Two drifters with the world to see.
Johan Obando-Ceron �... @johanobandoc
2K Followers 4K Following Graduate student @Mila_Quebec @UMontrealDIRO | RL/Deep Learning/AI | De Cali/Colombia pal’ Mundo 🇨🇴 | #JuntosProsperamos⚡#TogetherWeThrive| 🌱🌎
Zhuolin Yang @lucas110550
24 Followers 30 Following Research Scientist @NVIDIA, Ph.D @UofIllinois. ICPCWF20' Bronze Words are my own.
Yi Wu @jxwuyi
1K Followers 103 Following AI/RL researcher, Assistant Prof. at @Tsinghua_Uni, leading the RL lab at @AntResearch_, PhD at @berkeley_ai, frequent flyer and milk tea lover.
Yuzhen Huang @yuzhenh17
286 Followers 254 Following PhD Student at @hkust @hkustnlp 📜 SimpleRL / Llm-compress-intel / C-Eval 🏫 Prev @sjtu1896 @TencentGlobal
Zhouliang Yu @ZhouliangY
98 Followers 178 Following Model-based AI, Autoformalization via Machine Learning, Reinforcement Learning
Ameya P. @AmyPrb
394 Followers 443 Following Exploring Science of Benchmarking & Scaling up Automated 🧬 Discovery. Postdoc @bethgelab @uni_tue; Previously: @OxfordTVG, @intelailabs RT != endorsement
Trends for United States
You might like
