Tingchen Fu @TingchenFu
Incoming PhD student @UniofOxford and @MetaAI, prev Renmin University of China (RUC) tingchenfu.github.io Beijing, China Joined September 2022-
Tweets184
-
Followers220
-
Following644
-
Likes1K
After thousands of papers on meta-learning, the approach that ended up being successful (ICL) was an accidental byproduct of language modeling. Serendipity at its best and a good reminder that research needs to be open-ended and pursue a diversity of goals to escape local minima.
Failing on 𝐥𝐚𝐫𝐠𝐞-𝐬𝐜𝐚𝐥𝐞 𝐑𝐋 with VeRL? ⚠️ Mixing inference backend (𝐯𝐋𝐋𝐌/𝐒𝐆𝐋𝐚𝐧𝐠) with training backends (𝐅𝐒𝐃𝐏/𝐌𝐞𝐠𝐚𝐭𝐫𝐨𝐧) 𝐬𝐞𝐜𝐫𝐞𝐭𝐥𝐲 𝐭𝐮𝐫𝐧𝐬 𝐲𝐨𝐮𝐫 𝐑𝐋 𝐢𝐧𝐭𝐨 𝐨𝐟𝐟-𝐩𝐨𝐥𝐢𝐜𝐲 — even if they share the same weights! 📉 Blog:…
New paper & surprising result. LLMs transmit traits to other models via hidden signals in data. Datasets consisting only of 3-digit numbers can transmit a love for owls, or evil tendencies. 🧵
🚨 Did you know that small-batch vanilla SGD without momentum (i.e. the first optimizer you learn about in intro ML) is virtually as fast as AdamW for LLM pretraining on a per-FLOP basis? 📜 1/n
my favorite joke of the year
the Grok 4 benchmark chart (leaked version) is just beautiful Did @xai really hit 45% on HLE (Humanities Last Exam) 🤯 Because the HLE test is so hard. It (HLE) holds 2,500 expert-written questions spanning more than 100 subjects, including math, physics, computer science and…
the Grok 4 benchmark chart (leaked version) is just beautiful Did @xai really hit 45% on HLE (Humanities Last Exam) 🤯 Because the HLE test is so hard. It (HLE) holds 2,500 expert-written questions spanning more than 100 subjects, including math, physics, computer science and… https://t.co/lSiHe8eGqm
💡Beyond math/code, instruction following with verifiable constraints is suitable to be learned with RLVR. But the set of constraints and verifier functions is limited and most models overfit on IFEval. We introduce IFBench to measure model generalization to unseen constraints.
All reviews: positive; Meta: accept; Rejected by #RecSys2025 I get that decisions are complex, eg, "maintaining a competitive ac rate expected for top-tier conf." Still, frustrating to see months of work from an amazing team dismissed in a single shot, with no further feedback.
Excited to share our paper: "Chain-of-Thought Is Not Explainability"! We unpack a critical misconception in AI: models explaining their Chain-of-Thought (CoT) steps aren't necessarily revealing their true reasoning. Spoiler: transparency of CoT can be an illusion. (1/9) 🧵
We've always been excited about self-play unlocking continuously improving agents. Our insight: RL selects generalizable CoT patterns from pretrained LLMs. Games provide perfect testing grounds with cheap, verifiable rewards. Self-play automatically discovers and reinforces…
😵💫 Struggling with 𝐟𝐢𝐧𝐞-𝐭𝐮𝐧𝐢𝐧𝐠 𝐌𝐨𝐄? Meet 𝐃𝐞𝐧𝐬𝐞𝐌𝐢𝐱𝐞𝐫 — an MoE post-training method that offers more 𝐩𝐫𝐞𝐜𝐢𝐬𝐞 𝐫𝐨𝐮𝐭𝐞𝐫 𝐠𝐫𝐚𝐝𝐢𝐞𝐧𝐭, making MoE 𝐞𝐚𝐬𝐢𝐞𝐫 𝐭𝐨 𝐭𝐫𝐚𝐢𝐧 and 𝐛𝐞𝐭𝐭𝐞𝐫 𝐩𝐞𝐫𝐟𝐨𝐫𝐦𝐢𝐧𝐠! Blog: fengyao.notion.site/moe-posttraini……
Excited to share our ACL 2025 oral presentation—see you in Vienna!!
Excited to share our ACL 2025 oral presentation—see you in Vienna!!
many such cases
🚨 CHINA’S BIGGEST PUBLIC AI DROP SINCE DEEPSEEK @Baidu_Inc open source Ernie, 10 multimodal MoE variants 🔥 Surpasses DeepSeek-V3-671B-A37B-Base on 22 out of 28 benchmarks 🔓 All weights and code released under the commercially friendly Apache 2.0 license (available on…
Theory of Mind (ToM) is crucial for next gen LLM Agents, yet current benchmarks suffer from multiple shortcomings. Enter 💽 Decrypto, an interactive benchmark for multi-agent reasoning and ToM in LLMs! Work done with @TimonWilli & @j_foerst at @AIatMeta & @FLAIR_Ox 🧵👇
I'm excited to be joining the board of the Laude Institute! We need more support and incentives for university researchers who have great ideas and early results to accelerate their work, and build new real-world solutions that have a meaningful impact on people and society.
I'm excited to be joining the board of the Laude Institute! We need more support and incentives for university researchers who have great ideas and early results to accelerate their work, and build new real-world solutions that have a meaningful impact on people and society.
Can an LLM be programmed? In our new preprint, we show that LLMs can learn to evaluate programs for a range of inputs by being trained on the program source code alone – a phenomenon we call Programming by Backprop (PBB). 🧵⬇️
EvoLM: In Search of Lost Language Model Training Dynamics "We present EvoLM, a model suite that enables systematic and transparent analysis of LMs' training dynamics across pre-training, continued pre-training, supervised fine-tuning, and reinforcement learning. By training…
Discrete Diffusion in Large Language and Multimodal Models: A Survey just released on Hugging Face Get an overview of research in discrete diffusion LLMs and MLLMs, which achieve performance comparable to autoregressive models with up to 10x faster inference!
# 🚨 4B open-recipe model beats Claude-4-Opus 🔓 100% open data, recipe, model weights and code. Introducing Polaris✨--a post-training recipe for scaling RL on advanced reasoning models. 🥳 Check out how we boost open-recipe reasoning models to incredible performance levels…
Hanzhi Wang @Hanzhi_Wang_
17 Followers 161 Following interested in graph analysis algorithms; previously focus on random-walk probability (e.g., PageRank)
Alden Gerhold-Marvin @MarvinAlde94099
106 Followers 3K Following
DataDrivenTrades🇺�... @Druoqqu50116
48 Followers 2K Following 15-30% Monthly | 2 High-Conviction Stocks.Short-Term Gains: 15-20% in Days/Weeks.DM "JOIN" for WhatsApp Alerts. Live Trade Signals • Market Analysis
Mwieirwou @Mwieirwou43720
31 Followers 1K Following
Zhouxing Shi @zhouxingshi
381 Followers 389 Following Assistant Professor @UCRiverside CSE. Machine learning and trustworthy AI.
Johan Skiles @JohanSkile92339
29 Followers 2K Following
PIE Lab @pielabpku
33 Followers 85 Following An #NLProc research group in Wangxuan Institute of Computer Technology, Peking University @PKU1898, led by Prof. Yansong Feng @ys_feng.
Rohan Paul @rohanpaul_ai
83K Followers 8K Following Compiling in real-time, the race towards AGI. 🗞️ Don't miss my daily top 1% AI analysis newsletter directly to your inbox 👉 https://t.co/6LBxO8215l
Zhihui Xie @_zhihuixie
386 Followers 601 Following PhD student @hkunlp2020 | Intern @AIatMeta | Previously @sjtu1896
Raj Dabre @prajdabre
15K Followers 1K Following Senior Research Scientist - @google, Adjunct Faculty - @iitmadras, @iitbombay, Ex: @NICT_Publicity Use of my tweets without permission ➡️ legal action
Ewupe @Ewupe053
153 Followers 3K Following
Jaeyoung Lee @lee__jaeyoung
123 Followers 709 Following Doing research on MLLM/LLM | Automated/Mechanistic Interpretability | prev: @SeoulNatlUni
Reihaneh Zohrabi @ReihaneZb
82 Followers 569 Following Multimodal AI PhD @TUDarmstadt | ELLIS Program @ELLISforEurope | w/ @marcus_rohrbach
Hanna Yukhymenko @a_yukh
489 Followers 352 Following agent 007 lr @huggingface | statistics msc @eth | making EEU languages strong @the_sri_lab @insaitinstitute | prev @kpiuaofficial @fractalai @projectlve
Feng Yao @fengyao1909
1K Followers 634 Following Ph.D. student @UCSD_CSE | Intern @Amazon Rufus Foundation Model Ex. @MSFTResearch @TsinghuaNLP
jiangjin @JiangJin_PKU
12 Followers 244 Following
Silvia Manampimbir @SManampimb75390
3 Followers 141 Following
Auquswooj @Auquswooj001
104 Followers 3K Following
Zhihao Jia @JiaZhihao
3K Followers 686 Following Assistant professor of Computer Science at Carnegie Mellon University. Research on systems and machine learning.
NatalieMacAdam @UFHYYRS45717E
130 Followers 4K Following Certified nap connoisseur 💤 | Chaotic good ✨
Tianqing Fang @TFang229
343 Followers 242 Following Researcher @TencentGlobal AI Lab | PhD @HKUST (@HKUSTKnowComp) | Former intern @epfl_en, @CSatUSC, @NVIDIAAI
Xinye Li @vclee8
7 Followers 226 Following Junior at HIT, RA at HKUST(GZ) Interest: LLM | Knowledge | Agent | Efficient ML
Tim Franzmeyer @frtimlive
333 Followers 412 Following Machine Learning PhD student @UniofOxford interested in reinforcement learning, multi-agent systems, and LLMs. Previously @GoogleDeepMind, @MetaAI and @ETH.
Fatemeh Rajabi @rjbi_ftmh
69 Followers 226 Following M.Sc of AI @AUT | Data Scientist | ML, NLP, ASR, LLMs, GenAI, HealthAI
The Research Code @TheResearchCode
3K Followers 2K Following Advancing Knowledge Through Global Research Insights💡| Connect for Collaboration🤝🏻 | DMs Open ✉️ #TheResearchCode
James Oldfield @jamesaoldfield
130 Followers 363 Following PhD student interested in interpretability and AI safety @ QMUL. Visiting student @ Oxford. Prev visiting @ UW-Madison
Jianli @Bin_goJ
0 Followers 92 Following
Pengxiang Li @oliverlee1999
42 Followers 95 Following Research intern at https://t.co/9Zh2yZllZF. #ComputerVision, #MultimodalLearning, #NonEuclideanOptimization Ph.D. Student of BIGAI&BIT @BIT1940.
Lisa Alazraki @LisaAlazraki
1K Followers 829 Following PhD student @ImperialCollege. Research Scientist Intern @AIatMeta prev. @Cohere, @GoogleAI. Interested in generalisable learning and reasoning. She/her
Zhepei Wei @weizhepei
188 Followers 531 Following Ph.D. Student @CS_UVA | Research Intern @Meta. Previously @AmazonScience. Research interest: ML/NLP/LLM.
Tim @Glorious_Tim
126 Followers 3K Following
Xinyun Chen @xinyun_chen_
7K Followers 1K Following Research Scientist @Meta MSL. Prev. @GoogleDeepMind. PhD @Berkeley_EECS.
Justin Chih-Yao Chen @cyjustinchen
882 Followers 954 Following Ph.D. Student @unccs, @uncnlp, MURGe-Lab. Intern @SFResearch. Formerly student researcher @Google. LLM reasoning & efficiency.
Subramanyam Sahoo @iamwsubramanyam
186 Followers 4K Following Independent AI Safety researcher, M. Tech x Summa Cum Laude @NITHamirpurHP. BASIS Fellow @UCBerkeley, RA @HarvardAISafety. Get Published or Die Trying.
Ray Yang @RuixinYang6
47 Followers 526 Following MSCS @ICatGT | Prev. undergrad @UBC_CS | Trustworthy LLM | Reliable AI
Hwan Chang @hwanchang16
38 Followers 675 Following
hengyuan-hu @HengyuanH
230 Followers 65 Following
Menci 💖 @lcMenci
5K Followers 199 Following Software Engineer @Microsoft · Code Artist · Works on C++/C#/Web/Win32/Linux/DevOps
Shimon Whiteson @shimon8282
18K Followers 421 Following Professor of Computer Science at Oxford. Senior Staff Research Scientist at Waymo.
Yuandong Tian @tydsh
26K Followers 876 Following Research Scientist Director in Meta FAIR. Reasoning, Optimization and Understanding LLM. Novelist in spare time. PhD in @CMU_Robotics.
Guangxuan Xiao @Guangxuan_Xiao
3K Followers 697 Following Ph.D. student at @MITEECS Prev: CS & Finance @Tsinghua_Uni
Kevin Lin @KevinQHLin
1K Followers 581 Following Ph.D. student at Show Lab @NUSingapore. Vision-Language Model / Video Understanding / Agent.
Jianhao (Elliott) Yan @yan_elliott
68 Followers 219 Following PhD Student @ Westlake University, former researcher @ WechatAI.
Zhoujun (Jorge) Cheng @ChengZhoujun
989 Followers 594 Following CS Ph.D. @UCSanDiego | Prev. @XLangNLP @MSFTResearch @sjtu1896
Timon Willi @TimonWilli
332 Followers 68 Following RS @AIatMeta, DPhil w/ @j_foerst, @UniofOxford; Formerly: Research Intern @GoogleDeepMind / PhD @VectorInst / RS at @nnaisense / MSc w/ @SchmidhuberAI
Zhihui Xie @_zhihuixie
386 Followers 601 Following PhD student @hkunlp2020 | Intern @AIatMeta | Previously @sjtu1896
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)
Yukang Chen @yukangchen_
231 Followers 87 Following Research Scientist @NVIDIA , CS PhD from CUHK | Research in LLMs/VLMs, Long-context || Like Basketball 🏀, Cooking 🍳
Dimitris Papailiopoul... @DimitrisPapail
20K Followers 1K Following Researcher @MSFTResearch, AI Frontiers Lab; Prof @UWMadison (on leave); learning in context; thinking about reasoning; babas of Inez Lily.
Hanna Yukhymenko @a_yukh
489 Followers 352 Following agent 007 lr @huggingface | statistics msc @eth | making EEU languages strong @the_sri_lab @insaitinstitute | prev @kpiuaofficial @fractalai @projectlve
Neel Nanda @NeelNanda5
30K Followers 123 Following Mechanistic Interpretability lead DeepMind. Formerly @AnthropicAI, independent. In this to reduce AI X-risk. Neural networks can be understood, let's go do it!
Ola Kalisz @OlaKalisz8
164 Followers 290 Following PhD student @UniofOxford, @FLAIR_Ox Previously a Senior AI Research Scientist @exscientiaAI
Bo Liu (Benjamin Liu) @Benjamin_eecs
598 Followers 375 Following RL PhD @NUSingapore | Intern @AIatMeta FAIR | Undergrad @PKU1898 | Building autonomous decision making system | Prev @deepseek_ai | DeepSeek-V2/VL/Prover SPIRAL
Feng Yao @fengyao1909
1K Followers 634 Following Ph.D. student @UCSD_CSE | Intern @Amazon Rufus Foundation Model Ex. @MSFTResearch @TsinghuaNLP
bycloud @bycloudai
9K Followers 703 Following I make youtube vids on cool AI research /// AI papers newsletter https://t.co/Xn7GMDbQSd /// paper recap @TheAITimeline /// building @findmypapersAI
Jonny Cook @JonnyCoook
390 Followers 551 Following SR @GoogleDeepMind // DPhil Student in AI @FLAIR_Ox // Prev. RS Intern @cohere, @GoogleDeepMind Scholar
Tim Franzmeyer @frtimlive
333 Followers 412 Following Machine Learning PhD student @UniofOxford interested in reinforcement learning, multi-agent systems, and LLMs. Previously @GoogleDeepMind, @MetaAI and @ETH.
Stella Li @StellaLisy
3K Followers 443 Following PhD student @uwnlp | visiting researcher @AIatMeta | undergrad @jhuclsp #NLProc
Pengxiang Li @oliverlee1999
42 Followers 95 Following Research intern at https://t.co/9Zh2yZllZF. #ComputerVision, #MultimodalLearning, #NonEuclideanOptimization Ph.D. Student of BIGAI&BIT @BIT1940.
Dongfu Jiang @DongfuJiang
857 Followers 685 Following AI researcher. Current Intern @nvidia; PhD student @UWCheritonCS. Former @allen_ai; @SeaAIL; @ZJU_China;
Gavin Brown @gavinrbrown1
600 Followers 698 Following Assistant Professor at @WisconsinCS. Machine learning, privacy, and memorization. Postdoc @uwcse and PhD at Boston University.
Wei Liu @WeiLiu99
576 Followers 474 Following #NLProc | Ph.D. Student @hkust @hkustnlp | Prev. @AlibabaGroup @ShanghaiTechUni
Jiawei Gu @Kuvvius
70 Followers 158 Following
kabi @kakakbibibi
249 Followers 496 Following Ph.D. Student in GSAI, @RenminUniv | Prev. Intern in @Alibaba_Qwen | Recent Works: Qwen2.5, AUTOIF, ARPO, WebThinker, Search-o1
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.
Adel Bibi @Adel_Bibi
1K Followers 1K Following Senior researcher in machine learning @UniofOxford. R&D Distinguished Advisor @SoftserveInc. JRF @KelloggOx. Ex-@Intel. @KAUST_News and @K_University alumnus.
凡人小北 @frxiaobei
15K Followers 284 Following 行道途中。非求速成，惟求通达。 2023 年扎进AI ，打通Know-How，不少赚钱项目，踩过坑，也见过光。 围城里待得够久了，出来聊聊世界，聊聊技术、聊聊赚钱。
Xiangyu Qi @xiangyuqi_pton
2K Followers 1K Following Research @openai | PhD @Princeton | Prev @GoogleAI @GoogleDeepMind
Niloofar (✈️ ACL) @niloofar_mire
7K Followers 2K Following Niloofar Mireshghallah — incoming asst. prof @LTIatCMU @CMU_EPP, RS in @AIatMeta, postdoc @uwcse, Ph.D. @ucsd_cse, former @MSFTResearch -Privacy, ML, NLP
You Jiacheng @YouJiacheng
8K Followers 2K Following a big fan of TileLang 关注TileLang喵！关注TileLang谢谢喵！ https://t.co/utshC0jrCO 十年老粉
jian @jianxliao
7K Followers 2K Following hci ∩ ai | founder https://t.co/ppXjJENSsq | building the world's first serverless agent platform @agentbase_
WhiteBox Research @whiteboxorg
25 Followers 13 Following We're a nonprofit aiming to develop more AI interpretability and safety researchers in Asia.
Foerster Lab for AI R... @FLAIR_Ox
2K Followers 61 Following ML research group @uniofoxford. Focussed on multi-agent, open-ended, meta and reinforcement learning as well as agent based models. More at https://t.co/kMMdoaadJ3.
Zhouxing Shi @zhouxingshi
381 Followers 389 Following Assistant Professor @UCRiverside CSE. Machine learning and trustworthy AI.
Yang Deng @ydeng_dandy
285 Followers 183 Following Assistant Professor @sgSMU | Prev @NUSingapore @CUHKofficial | 🚀proactive and trustworthy conversational agents 🤖
Jakob Foerster @j_foerst
21K Followers 974 Following Assoc Prof in ML @UniofOxford @StAnnesCollege @FLAIR_Ox/ RS @MetaAI, 2x dad. Ex: (A)PM @Google, DivStrat @GS, ex intern: @GoogleDeepmind, @GoogleBrain, @OpenAI
Hao Zhang @haozhangml
6K Followers 474 Following Asst. Prof. @HDSIUCSD and @ucsd_cse running @haoailab. Cofounder and runs @lmsysorg. 20% with @Snowflake
Kaizhao Liang @KyleLiang5
623 Followers 88 Following Class of 2020 @IllinoisCDS 5 years at @SambaNovaAI Grad student @UTCompSci since 2023 Interested in new optimizers and neural architectures
Gillian Hadfield @ghadfield
5K Followers 761 Following AI policy and alignment; integrating law, economics & computer science to build normatively competent AI that knows how to play well with humans
Tim Althoff @timalthoff
5K Followers 2K Following Associate Professor @UWCSE developing computational methods that leverage large-scale behavioral data to improve human well-being. Recruiting PhD students :-)
Ansong Ni @AnsongNi
2K Followers 417 Following Research Scientist @MetaAI FAIR. PhD from @Yale, MS @SCSatCMU. Opinions are my own.
Trends for United States
You might like
