Quanquan Gu @QuanquanGu
Professor @UCLA | Head of AIDD, ByteDance Research | Recent work: Self-play fine-tuning (SPIN) | Opinions are my own cs.ucla.edu/~qgu/ Los Angeles, CA Joined August 2017-
Tweets1K
-
Followers9K
-
Following2K
-
Likes9K
Agree. Here are the top three LLM benchmarks I would recommend: 1. Open LLM leaderboard 2. MT-Bench 3. AlpacaEval
Agree. Here are the top three LLM benchmarks I would recommend: 1. Open LLM leaderboard 2. MT-Bench 3. AlpacaEval
HELM Lite v1.2.0 is out! Datasets: NarrativeQA, NaturalQA, OpenbookQA, MMLU, MATH, GSM8K, LegalBench, MedQA, WMT14 Results (we still need to add Claude 3, which requires more prompt finagling): crfm.stanford.edu/helm/lite/v1.2…
While the dataset determines the upper limit for model performance, sample efficiency should be the primary performance metric. This aspect has been extensively studied in statistical learning theory, yet remains relatively understudied in large language models (LLMs). Effective…
While the dataset determines the upper limit for model performance, sample efficiency should be the primary performance metric. This aspect has been extensively studied in statistical learning theory, yet remains relatively understudied in large language models (LLMs). Effective…
Apple presents OpenELM An Efficient Language Model Family with Open-source Training and Inference Framework The reproducibility and transparency of large language models are crucial for advancing open research, ensuring the trustworthiness of results, and
New paper alert: React-OT: Optimal Transport for Generating Transition State in Chemical Reactions (arxiv.org/abs/2404.13430). React-OT formulates TS search as a transport problem, approaching chemical accuracy while taking only 0.5 seconds in inference on a single GPU. #compchem
In our latest research, we've leveraged Rosetta energy as a reward in residual-level DPO tailored for antibody design. Check out our paper at: arxiv.org/html/2403.1657…
In our latest research, we've leveraged Rosetta energy as a reward in residual-level DPO tailored for antibody design. Check out our paper at: arxiv.org/html/2403.1657… https://t.co/YLJvOVNxG5
[LG] ScaleFold: Reducing AlphaFold Initial Training Time to 10 Hours F Zhu, A Nowaczynski, R Li, J Xin… [NVIDIA] (2024) arxiv.org/abs/2404.11068 - AlphaFold has achieved breakthroughs in protein folding prediction, but its training is computationally prohibitive and does not…
Well, the truly open source AI represents a valuable service and contribution to both the community and society, driven not by profit motives but by a commitment to collective advancement.
Well, the truly open source AI represents a valuable service and contribution to both the community and society, driven not by profit motives but by a commitment to collective advancement.
Great experiments! It's quite predictable though to observe this phenomenon, akin to how experienced individuals often grasp (new) skills quicker than novices with less guidance.
Great experiments! It's quite predictable though to observe this phenomenon, akin to how experienced individuals often grasp (new) skills quicker than novices with less guidance.
We have just released 🍷 FineWeb: 15 trillion tokens of high quality web data. We filtered and deduplicated all CommonCrawl between 2013 and 2024. Models trained on FineWeb outperform RefinedWeb, C4, DolmaV1.6, The Pile and SlimPajama!
Can Language Models Solve Olympiad Programming? - Uses self-reflection and retrieval over episodic knowledge to boost the perf of GPT-4 on USACO from 8.7% pass@1 to 20.2% - Giving a small number of targeted hints solves most of the questions repo: github.com/princeton-nlp/… abs:…
1/ 🥁Scaling Laws for Data Filtering 🥁 TLDR: Data Curation *cannot* be compute agnostic! In our #CVPR2024 paper, we develop the first scaling laws for heterogeneous & limited web data. w/@goyalsachin007 @zacharylipton @AdtRaghunathan @zicokolter 📝:arxiv.org/abs/2404.07177
Very inspiring talk!
The new @MistralAI is now #1 on the openLLM leaderboard. Apache 2.0 license too! 🔥🔥🔥
Don't underestimate the potential of high schoolers. Some could become CEOs at companies like OpenAI in the near future, while many PC/AC/Reviewers may find themselves working under their leadership.😄
Don't underestimate the potential of high schoolers. Some could become CEOs at companies like OpenAI in the near future, while many PC/AC/Reviewers may find themselves working under their leadership.😄
People like doing things for nothing.
Nvidia presents RULER What's the Real Context Size of Your Long-Context Language Models? The needle-in-a-haystack (NIAH) test, which examines the ability to retrieve a piece of information (the "needle") from long distractor texts (the "haystack"), has been widely adopted to
Google presents Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention 1B model that was fine-tuned on up to 5K sequence length passkey instances solves the 1M length problem arxiv.org/abs/2404.07143
Clément Canonne @ccanonne_
31K Followers 928 Following Senior Lecturer @Sydney_Uni. Postdocs @IBMResearch, @Stanford; PhD @Columbia. Converts ☕ into puns: sometimes theorems. He/him. @[email protected]Gautam Kamath @thegautamkamath
44K Followers 505 Following Assistant Prof of CS @UWaterloo, Faculty @VectorInst, Canada @CIFAR_News AI Chair. Co-EiC @TmlrOrg. I lead @TheSalonML. Privacy, robustness, machine learning.Amin Karbasi @aminkarbasi
8K Followers 2K Following Associate Professor at Yale University, staff research scientist at Google.Dan Roy @roydanroy
45K Followers 2K Following ML / AI researcher, emphasis on theory. Research Director and Canada CIFAR AI Chair, @VectorInst Professor, @UofT (Statistics/CS)Csaba Szepesvari @CsabaSzepesvari
8K Followers 704 Following "If there is not folly in the world, then the world itself is folly. You must understand that mistakes are not always regrets." - Paul Tobin, Bandette🤠Peter Richtarik @peter_richtarik
6K Followers 593 Following Federated Learning Guru. Tweeting since 20.5.2020. Lived in 🇸🇰🇺🇸🇧🇪🇬🇧🇸🇦Dimitris Papailiopoul.. @DimitrisPapail
11K Followers 972 Following prof @ wisconsin; thinking about transformers; learning in context; babas of Inez LilyAlex Dimakis @AlexGDimakis
13K Followers 2K Following UT Austin Professor. Researcher in Machine Learning and Information Theory. National AI Institute on the Foundations of Machine Learning (IFML) Co-director.Jason Lee @jasondeanlee
10K Followers 3K Following Associate Professor at Princeton and Research Scientist at Google DeepMind. ML/AI Researcher working on foundations of LLMs and deep learningMaxim Raginsky @mraginsky
8K Followers 2K Following father, academic, raconteur, aging wannabe hipster blog: https://t.co/akk6LCvKw6Behnam Neyshabur @bneyshabur
18K Followers 690 Following Senior Staff Research Scientist @GoogleDeepMind, Interested in reasoning w. LLMs, traveling & backpackingFrancesco Orabona @bremen79
6K Followers 394 Following Associate professor at @KAUST_News. Formerly @BU_ece, @sbucompsc, @YahooResearch, @TTIC_Connect. ML theory&practice and history of scienceYuandong Tian @tydsh
16K Followers 801 Following Research Scientist and Senior Manager in Meta AI (FAIR). AI-guided Optimization and Representation Learning. Novelist in spare time. PhD in @CMU_Robotics.Michal Valko @misovalko
5K Followers 2K Following Llama @AIatMeta Paris & Inria & MVA - Ex: Gemini and BYOL @GoogleDeepMindProf. Anima Anandkuma.. @AnimaAnandkumar
25K Followers 2K Following Bren Professor @caltech, Fmr Sr Director of #AI research @nvidia, Fmr Principal Scientist @awscloud, AI+Science, PDE, Neural operators. Views my own.William Wang @WilliamWangNLP
14K Followers 716 Following UCSB NLP Lab + ML Center. https://t.co/6TOnqbk6YT https://t.co/KJYhnav3Et Mellichamp Chair Prof. at UCSB CS. PhD @ CMU SCS. Areas: #NLProc, Machine Learning, AI.Arya Mazumdar @MountainOfMoon
3K Followers 319 Following Professor @UCSanDiego Dy. Director+AD for Research NSF AI Inst https://t.co/wblPm6DhUX, UCSD Site Lead @encoreinstitut Information Theory, Coding Th., Machine LearningYisong Yue @yisongyue
19K Followers 3K Following Machine Learning @Caltech (@YueLabCaltech). AI for invention at @AsariAILabs. Autonomous Driving at https://t.co/riZHAmvcAr. Senior Program Chair @iclr_conf.Sam Power @sp_monte_carlo
17K Followers 7K Following Lecturer in Maths & Stats at Bristol. Interested in probabilistic + numerical computation, statistical modelling + inference. (he / him)N Sreeram @NSreeram5
53 Followers 500 FollowingAbhinav Gupta @backpropper
801 Followers 5K Following phd student @Mila_Quebec | ms @CILVRatNYU @NYU_Courant | previously @GoogleDeepMind @AIatMeta @GoogleAI @labsdotgoogle @MSFTResearch @AdobeResearchHaozhe Ji @HaozJi
41 Followers 93 Following Grad student @ Tsinghua university | NLPer | I play the celloKai-Fu Lee @kaiifulee
1K Followers 2K Following #AI Expert, CEO of @01ai_yi and Chairman of 创新工场 @sinovationvc , former President of Google China, Author of AI 2041 and NYT Bestseller AI SuperpowersRavi Yadav @raviy0807
45 Followers 454 Following AI Researcher at General Motors. Interest in AI Ethics, reinforcement learning, deep learning, Explainable vision & autonomous vehicleschristian cch @chris_cch_
194 Followers 3K Followingxiaoboliang @xiaobolian66449
2 Followers 96 FollowingKarthik Prasad @karthikprassad
88 Followers 978 FollowingFelo @wangzhi0467
9 Followers 98 Followingzy_zhao @zhao_zy44927
40 Followers 60 FollowingLingfeng Shen @Lingfeng_nlp
287 Followers 525 Following MS student @jhuclsp, Research on #NLP and #ML @MercedesAMGF1 Fan!Chenru Duan @chenru_duan
764 Followers 452 Following ex-MSFT Quantum | Ph.D. @KulikGroup @MITChemistry | #AI4Science workshop organizer. #compchem, #MachineLearning, and #chemdiscovery.Xindong Chen @Dabenmao3
85 Followers 1K Following Postdoc researcher at Tsinghua University. #CellDynamics #Biophysics #Protein-Protein Interactions #AppliedMathematics #Drug-AIGC!Startup Shinobi @startupshinobi
2K Followers 4K Following Wit and wisdom for founders and investors from a GP. Startups and VC are ripe for ridicule. Follow me for the knowledge but stay for the laughs.StarlightXYY @huyue82028905
18 Followers 45 FollowingTodd Kueny — e/acc @techgazetteco
3K Followers 6K Following Empowering worlds where AI enriches lives, solves complex problems, and inspires continuous learning.Simon Mathis @SimMat20
717 Followers 867 Following PhD @Cambridge_Uni | AI in protein design & engineering | biotech & environmental applications | enzymes | geometric DL | prev. @ETH_physicslyftium.eth @lyftium
760 Followers 5K Following Explorer l’inconnu et pousser les limites de l’impossible. e/acc. ResearcherXiaoguang Xue @cygx1xue
271 Followers 1K Following Structural immunology • Genmab • Opinions are my ownChing-Shin Huang @chingshinhuang
113 Followers 618 Following Structural biologist. Open science supporter. Opinions are my own. Also on @[email protected]Chen Robben @RobbenChen68
2 Followers 4 FollowingJiaxin Huang @jiaxinhuang0229
293 Followers 54 Following Incoming assistant professor @WUSTL CSE. PhD Candidate @IllinoisCS. Currently visiting @uwnlp. NLP, ML, Data Mining.Wujie Wang @WujieWang
275 Followers 312 Following design proteins @generate_biomed with energy-based models https://t.co/WWfIm0omNqmetaphysics enjoyer @1n4pl4c3
38 Followers 811 Following I like to post things only I find funny. #iliketoeatrawmilkbruhJustin Barton @all_your_bayes
92 Followers 309 Following Computational biology, machine learning ∩ immunology, distributed systems, modern datamancyLarry Bernstein @lbern57
16 Followers 95 FollowingEter Griffin @EterGriffinthor
242 Followers 3K Following Nōn nōbīs, Domine, nōn nōbīs, sed nōminī tuō dā glōriamMuneeb Sultan @mmsltn
1K Followers 2K Following GenAI for proteins @abscibio. Prev. founding team @insitro, @Stanford PhD, and @Yale alumni. 🇵🇰🇺🇸 sigmoid. social/@mmsltnJavin Oza @ozalabCP
731 Followers 1K Following Javin Oza; Oza Lab @ Cal Poly, SLO - biochemistry, synthetic biology, biological engineering. Opinions are my own. https://t.co/VDrZffJIRXAkash Bahai @akashbahai
524 Followers 3K Following Structural Bioinformatics | Machine Learning, PostDoc at NTU | Past: @IISERPune, @Helmholtz_HZIJason Yim @json_yim
1K Followers 225 Following PhD student @MIT_CSAIL. Generative models, protein design.Random Proof @randomproof8
23 Followers 2K Following Notes 📝 on Maths, Theory CS & Economics for now. Maths in Phys, Bio, EE; Neuro, Phil etc., other sciences in future.Dheeraj Mekala @MekalaDheeraj
617 Followers 295 Following Ph.D. student at @UCSanDiego. Research Scientist Intern at FAIR @MetaAI Previously @msftresearch, @AmazonScience, @iitkanpur Data! Data! Data!Lihe Li @lilh76
16 Followers 91 Following MSc student at LAMDA group of Nanjing University. Research interest: Reinforcement Learning (RL).عبدالعزيز س.. @azizsirajkaki
405 Followers 4K FollowingPensé FFun @inftyCategory
113 Followers 6K FollowingClément Canonne @ccanonne_
31K Followers 928 Following Senior Lecturer @Sydney_Uni. Postdocs @IBMResearch, @Stanford; PhD @Columbia. Converts ☕ into puns: sometimes theorems. He/him. @[email protected]Gautam Kamath @thegautamkamath
44K Followers 505 Following Assistant Prof of CS @UWaterloo, Faculty @VectorInst, Canada @CIFAR_News AI Chair. Co-EiC @TmlrOrg. I lead @TheSalonML. Privacy, robustness, machine learning.Amin Karbasi @aminkarbasi
8K Followers 2K Following Associate Professor at Yale University, staff research scientist at Google.Dan Roy @roydanroy
45K Followers 2K Following ML / AI researcher, emphasis on theory. Research Director and Canada CIFAR AI Chair, @VectorInst Professor, @UofT (Statistics/CS)Csaba Szepesvari @CsabaSzepesvari
8K Followers 704 Following "If there is not folly in the world, then the world itself is folly. You must understand that mistakes are not always regrets." - Paul Tobin, Bandette🤠Percy Liang @percyliang
49K Followers 408 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | PianistPeter Richtarik @peter_richtarik
6K Followers 593 Following Federated Learning Guru. Tweeting since 20.5.2020. Lived in 🇸🇰🇺🇸🇧🇪🇬🇧🇸🇦Dimitris Papailiopoul.. @DimitrisPapail
11K Followers 972 Following prof @ wisconsin; thinking about transformers; learning in context; babas of Inez LilyAlex Dimakis @AlexGDimakis
13K Followers 2K Following UT Austin Professor. Researcher in Machine Learning and Information Theory. National AI Institute on the Foundations of Machine Learning (IFML) Co-director.Jason Lee @jasondeanlee
10K Followers 3K Following Associate Professor at Princeton and Research Scientist at Google DeepMind. ML/AI Researcher working on foundations of LLMs and deep learningMaxim Raginsky @mraginsky
8K Followers 2K Following father, academic, raconteur, aging wannabe hipster blog: https://t.co/akk6LCvKw6Jelani Nelson @minilek
22K Followers 184 Following Professor @Berkeley_EECS. Research Scientist (part-time) @GoogleAI. Founder @addiscoder. 🇻🇮🇺🇸🇪🇹Behnam Neyshabur @bneyshabur
18K Followers 690 Following Senior Staff Research Scientist @GoogleDeepMind, Interested in reasoning w. LLMs, traveling & backpackingFrancesco Orabona @bremen79
6K Followers 394 Following Associate professor at @KAUST_News. Formerly @BU_ece, @sbucompsc, @YahooResearch, @TTIC_Connect. ML theory&practice and history of scienceYuandong Tian @tydsh
16K Followers 801 Following Research Scientist and Senior Manager in Meta AI (FAIR). AI-guided Optimization and Representation Learning. Novelist in spare time. PhD in @CMU_Robotics.NeurIPS Conference @NeurIPSConf
111K Followers 35 Following New Orleans, Dec 10-16, 23. https://t.co/ga8aOw615g Tweets to this account are not monitored. Please send feedback to [email protected].Michal Valko @misovalko
5K Followers 2K Following Llama @AIatMeta Paris & Inria & MVA - Ex: Gemini and BYOL @GoogleDeepMindProf. Anima Anandkuma.. @AnimaAnandkumar
25K Followers 2K Following Bren Professor @caltech, Fmr Sr Director of #AI research @nvidia, Fmr Principal Scientist @awscloud, AI+Science, PDE, Neural operators. Views my own.Ben Recht @beenwrekt
26K Followers 365 Following optimization. machine learning. uc berkeley. I blog at https://t.co/fkJujOPsJb The world won't end.Shiyue Zhang @byryuer
2K Followers 1K Following Research Engineer @TechAtBloomberg | ex PhD student at UNC-Chapel Hill (@unccs @uncnlp) | Bloomberg PhD Fellow | Past Intern at @MetaAI @MSFTResearch | #NLProcWei Xiong @weixiong_1
188 Followers 173 Following PhD Student @IllinoisCS, Practice Math for 2.5 YearsChen Robben @RobbenChen68
2 Followers 4 FollowingDheeraj Mekala @MekalaDheeraj
617 Followers 295 Following Ph.D. student at @UCSanDiego. Research Scientist Intern at FAIR @MetaAI Previously @msftresearch, @AmazonScience, @iitkanpur Data! Data! Data!Sheng Shen @shengs1123
1K Followers 539 Following Ph.D. student @berkeley_ai; Building 🦙@MetaAi; Former @MSFTResearch, @allen_ai, @GoogleDeepMindSwabha Swayamdipta @swabhz
6K Followers 461 Following Assistant Prof. @CSatUSC | Researcher in #NLProc | Previously with @uwnlp @allenai | she/herKristian Kersting @kerstingAIML
5K Followers 2K Following #AI prof @TUDarmstadt, co-director @Hessian_AI, @DFKI, @RealAAAI Councilor, @vision_claire, @ELLISforEurope, AI Columnist @WELTAMSONNTAGJackson Hinkle 🇺�.. @jacksonhinklle
2.7M Followers 365 Following Fighting for a FREE AMERICA 🇺🇸☦️ [email protected] - https://t.co/bvulmS3517 🚨 DEARBORN SHOW MAY 24: https://t.co/1WdSgELhGfFarnaz Jahanbakhsh (@.. @FarnazJ_
1K Followers 578 Following Postdoc at @StanfordHAI, Incoming assistant prof at @UMichCSE in 2024, PhD @MIT_CSAIL | HCI, Social ComputingRaymond Wang @RaywangSci
8 Followers 4 FollowingWeiyan Shi @shi_weiyan
3K Followers 683 Following Postdoc @StanfordNLP, incoming assistant professor @Northeastern, PhD @Columbia| Prev Intern @MetaAI |Co-created CICERO | persuasive chatbots + privacy #nlprocLianmin Zheng @lm_zheng
4K Followers 438 Following CS Ph.D. @ UC Berkeley. Creator of Alpa, Vicuna, and Chatbot Arena. @lmsysorgYan Wang @YanWang_CC
9 Followers 9 Following Phd candidate, Mathematical Sciences, Tongji University, ShanghaiAshwinee Panda @PandaAshwinee
944 Followers 602 Following PhD @princeton, @Cal alum, currently working on LLMsPuneesh Deora @puneeshdeora
33 Followers 234 Following Grad student at UBC. Working on ML Theory and Optimization.Bhavya Vasudeva @bhavya_vasudeva
39 Followers 231 Following PhD candidate @CSatUSC | @iitroorkee'20 | Interested in theory of deep learning, optimization and robustness/generalization | she/herAlexander Wettig @_awettig
385 Followers 235 Following PhD Student in ML/NLP @princeton @princeton_nlp @PrincetonPLILibs of TikTok @libsoftiktok
3.1M Followers 854 Following News you can’t see anywhere else. 📧 [email protected]. DM submissions. Bookings: [email protected]. ⬇️Subscribe to our newsletterYuxin Chen @chenyx04
194 Followers 187 Following Associate professor of statistics and data science at UPennTim Dettmers @Tim_Dettmers
29K Followers 819 Following PhD Student at @UW. I blog about deep learning and PhD life at https://t.co/Y78KDJJFE7.Alex Chu @alexechu_
1K Followers 725 Following Deep learning & protein design. @googledeepmind PhD @StanfordHou Chao @houchao1
42 Followers 322 Following Postdoc @Columbia | PhD 2023 & Bachelor 2020 @PKU1898 | Computational Biology & GeneticsBin Yu @bbiinnyyuu
357 Followers 7 Following Professor of Statistics, EECS and Comp. Bio. at UC BerkeleyCosta Huang @vwxyzjn
3K Followers 1K Following RLHF @huggingface 🤗; main dev of @cleanrl_lib; CS PhD @DrexelUniv; Ex @CuraiHQ @weights_biases @NVIDIAAI @riotgames.James @JamesLEE808
3 Followers 13 FollowingGowthami Somepalli @gowthami_s
6K Followers 979 Following Grad student @UMDCS. Past: @AIatMeta, @AmazonScience, @IITMadras. Currently working on #Diffusion and #Multimodal understanding. GPU poor. She/her.Qiaoyu Tan @qiaoyu_tan
101 Followers 270 Following Incoming Assistant Professor @NYUShanghai | CS PhD @TAMUAakanksha Chowdhery @achowdhery
7K Followers 3K Following LLMs @ Google DeepMind :: PaLM, Gemini // Previously @MSFTResearch, @Stanford, @Princeton // views my own and subject to changeBram Wallace @bram_wallace
180 Followers 69 FollowingYuanzhou Adrian Chen @ChenAladdin
10 Followers 124 Following CS PhD student at UCLA, working on AI4Science, machine learning theory | Previous math/statistics undergrad from PKU | Music, Piano, StoriesWeikai Li @billywkli
7 Followers 39 Following CS PhD Student at @UCLA | Previous CS undergrad from @Tsinghua_Uni | Graph neural network, high-level synthesisAte-a-Pi @8teAPi
39K Followers 2K Following self aware neuron; historian from 2130; epistemic polluter; 95 yr old man;Adina Yakup @AdeenaY8
2K Followers 454 Following @huggingface 🤗 | Contributing to Chinese ML community.Ying Sheng @ying11231
4K Followers 485 Following PhD student @Stanford. Large Language Models and Programs. | Do it anywayIt's not every day we get to celebrate an MBA Love Story! Congratulations to Tiffany Lin ('24) & Richie Chang, MBA ('21) on their engagement - which happened right here at UCLA Anderson! #bruinlove
Nothing like campus in full bloom 🌸 📸 Instagram: danielagh.2, alice_yutong, tell.my.tales, gabrielpdeleon
Last call! 📢 Today is the final day to enter our lottery for a free ICLR conference registration. Don't miss out: buff.ly/4dkTH46 #DeadlineDay #ICLR2024 #WiML
@ChujieZheng @QuanquanGu Hey @ChujieZheng check out our new Arena-Hard benchmark :) x.com/lmsysorg/statu…
Introducing Arena-Hard – a pipeline to build our next generation benchmarks with live Arena data. Highlights: - Significantly better separability than MT-bench (22.6% -> 87.4%) - Highest agreement to Chatbot Arena ranking (89.1%) - Fast & cheap to run ($25) - Frequent update…
This cost + latency for llama 3 is actually insane. Just look at the rest of the models in comparison
📊Delighted to welcome Command-R-Plus, Llama-3, and and Gemini-Pro-1.5 into the Berkeley Function Calling Leaderboard. Check out how they stack up across different categories, P95 latency, and costs at gorilla.cs.berkeley.edu/leaderboard.ht… Congratulations to @cohere, @AIatMeta, and…
Agree. Here are the top three LLM benchmarks I would recommend: 1. Open LLM leaderboard 2. MT-Bench 3. AlpacaEval
Can people please use more than one benchmark to prove their methods in their papers? Every new paper seems to test on nothing but alpaca eval and just makes me think the paper is unserious and unproven. Just spend the 20 dollars and do a few more evals. Mt bench, open llm…
As an ICML 2024 Area Chair, I've handled 19 papers. Recommended 7 to be accepted, 10 to be rejected, and 2 withdrew. The avg scores of the accepted papers = 4.25-6.33. The avg scores of the rejected papers = 2.60-6.00. I did not merely threshold the scores.
I’ll take llama-3 over phi-3 any day, phi series of models are an interesting experiment but not something I’m using daily
✨New Paper Alert✨ Excited to introduce ExPO, an extremely simple method to boost LLMs' alignment with human preference, via weak-to-strong model extrapolation 👇 #LLMs #MachineLearning #NLProc #ArtificialIntelligence #AI
OpenAI is the best hype-creation engine of our times They are constantly ginning up all kinds of theories about AGI! Claiming major improvements, threatening to steamroll start-ups and making up stories about AI sentience All while - llama-3 70b matches GPT-4 performance and…
Slides for my talk about “Beyond ERM: What Optimization can help Large Foundation Models”: people.tamu.edu/~tianbao-yang/…. Key takeaways: 1. Empirical X-risk Optimization should be adopted for CLIP training. 2. DRO framework can be used to optimize temperature. 3. Use TempNet for LLM
We are very excited that our first GH200 nodes have arrived in TACC for our GenAI center. Here is one. Fun facts: NVIDIA makes GH200 'superchips' (i.e. modules), a GH200 DGX box and a GH200 rack, which are all different. As Dan Stanzione, our TACC director, kindly explained…
The latest chapter in the saga of using stochastic localization/denoising diffusions to sample from highly multi-modal Gibbs measures. With the amazing Brice Huang and Huy Tuan Pham. (1/4) arxiv.org/abs/2404.15651
When you are hardcore, this is how you start the introduction of the paper. Quite refreshing :D
The latest chapter in the saga of using stochastic localization/denoising diffusions to sample from highly multi-modal Gibbs measures. With the amazing Brice Huang and Huy Tuan Pham. (1/4) arxiv.org/abs/2404.15651
day 4096 of not really understanding what explainable and interpretable means
I’m biased but I’m very excited for this extremely talented team of Joe and colleagues. 🙂
I'm excited to announce that I'm part of the team at Xaira Therapeutics! This project has been some time in the making. I'm convinced that generative modelling, and ML for biology more generally, will play a pivotal role in the next generation of therapeutics. 1/2
Our Warwick Foundation of AI seminar (FAIS) is starting! Looking forward to @CevherLIONS Prof. Volkan Cevher’s talk on adversarial training! See more details on our seminar website faiseminarswarwick.github.io
🎉🎉🎉We're thrilled to announce the kickoff of our Foundations of AI Seminar (FAIS) series, featuring an impressive lineup of speakers, starting tomorrow. Our first seminar is a special one, as we are honoured to welcome Prof. Volkan Cevher @CevherLIONS from @EPFL_en.
@maksym_andr @SebastienBubeck @zicokolter @KrzakalaF Congratulations Maksym 🎉🎉🎈🎈🥳🥳 Must be one of the best theses of our era to read and learn from.