Jingfeng Yang @JingfengY
Applied Scientist @AmazonScience #LLMs #NLProc Formerly @SALT_NLP @Georgia_Tech @PKU1898 @Google @MSFTResearch . Opinions are my own. jingfengyang.github.io Joined April 2019-
Tweets483
-
Followers2K
-
Following618
-
Likes2K
The self-extend paper is really becoming important - "LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning" 🔥 📌 Extend existing LLMs’ context window without any fine-tuning 📌 One feasible way to avoid the O.O.D. ( out-of-distribution) problems by caused unseen…
Do models need to reason in words to benefit from chain-of-thought tokens? In our experiments, the answer is no! Models can perform on par with CoT using repeated '...' filler tokens. This raises alignment concerns: Using filler, LMs can do hidden reasoning not visible in CoT🧵
I guess you might have tried the demo (huggingface.co/spaces/Qwen/Qw…). Now the weights of Qwen1.5-110B are out! Temporarily only the base and chat models, AWQ and GGUF quantized models are about to be released very soon! Blog: qwenlm.github.io/blog/qwen1.5-1… Hugging Face:…
Thanks for implementing our paper! But actually, you only need to modify 5 lines of code to configure STORM with Claude models. ZERO line of change is needed now because I just added an example script to our repo! github.com/stanford-oval/…
Thanks for implementing our paper! But actually, you only need to modify 5 lines of code to configure STORM with Claude models. ZERO line of change is needed now because I just added an example script to our repo! github.com/stanford-oval/…
Excited to share our work at @GoogleDeepMind! We propose Naturalized Execution Tuning (NExT), a self-training method that drastically improves the LLM's ability to reason about code execution, by learning to inspect execution traces and generate chain-of-thought rationales 🧵👇
Great results on extending Llama-3 to long context reasoning!
Great results on extending Llama-3 to long context reasoning!
Self-Extend is one of the coolest and under-rated techniques for extending context length in a stable manner. I've personally used it with llama.cpp (it feels much more stable that RoPE) and it blows my mind that more projects don't support it since it does not require…
Self-Extend is one of the coolest and under-rated techniques for extending context length in a stable manner. I've personally used it with llama.cpp (it feels much more stable that RoPE) and it blows my mind that more projects don't support it since it does not require…
New results about LLama-3's long contexts abilities. Equipping Llama-3-8b/70b with SelfExtend (arxiv.org/pdf/2401.01325…), we test their in-context-learning abilities on two long tasks: DialogRe and FewNerd from LongCIL benchmark (arxiv.org/pdf/2404.02060…) @WenhuChen @TianleLI123.…
We tested our SelfExtend (arxiv.org/pdf/2401.01325…) for LLama-3-8B/70B-Instruct on the new challenging long context benchmark Ada-Eval (arxiv.org/abs/2404.06480). The task is selecting the best answer from candidates. The results are pretty good! 🌟 Highlights: 1: Equipped with…
Impressive results using self-extend in embedding models! Refer to table 3.
Since launching STORM code & web preview, thousands have tried it & offered feedback. - Can I run STORM with open LMs? - Can I change its report style? - Can I contribute to new info source support? Yes! We refactored our codebase for smoother running, customization & dev! 🔗🧵
🚀Excited to share our new paper "LongEmbed: Extending Embedding Models for Long Context Retrieval". We introduce the LongEmbed benchmark, explore context extension of existing embedding models, and release E5-Base-4k & E5-RoPE-Base. Paper: arxiv.org/abs/2404.12096
How Faithful are RAG Models? This new paper aims to quantify the tug-of-war between RAG and LLMs' internal prior. It focuses on GPT-4 and other LLMs on question answering for the analysis. It finds that providing correct retrieved information fixes most of the model…
🔥Exciting news -- GPT-4-Turbo has just reclaimed the No. 1 spot on the Arena leaderboard again! Woah! We collect over 8K user votes from diverse domains and observe its strong coding & reasoning capability over others. Hats off to @OpenAI for this incredible launch! To offer…
Verified that our Rufus could code :) , as I stated in my original tweet thread x.com/jingfengy/stat… you would expect even better coding and general-purpose models and agents from us :)
Verified that our Rufus could code :) , as I stated in my original tweet thread x.com/jingfengy/stat… you would expect even better coding and general-purpose models and agents from us :)
Thrilled to announce we’ve received IRB approval to launch our web demo of STORM at storm.genie.stanford.edu! 🌪️ While we’ve analyzed its limitations in our paper, we’re eager to kick off a real-world exploration. Try it out, and give us your feedback directly through the demo!
Thrilled to announce we’ve received IRB approval to launch our web demo of STORM at storm.genie.stanford.edu! 🌪️ While we’ve analyzed its limitations in our paper, we’re eager to kick off a real-world exploration. Try it out, and give us your feedback directly through the demo!
Totally agree with this, as I raised the question in my earlier blog post jingfengyang.github.io/alignment : “How to improve language agents’ capabilities as a whole, considering there is no moat for current LLM-driven agent frameworks? The moat is still the fundamental LLM capability,…
Totally agree with this, as I raised the question in my earlier blog post jingfengyang.github.io/alignment : “How to improve language agents’ capabilities as a whole, considering there is no moat for current LLM-driven agent frameworks? The moat is still the fundamental LLM capability,…
Social Skill Training with Large Language Models People rely on social skills like conflict resolution to communicate effectively and to thrive in both work and personal life. However, practice environments for social skills are typically out of reach for most people.
SelfExtend, without further training, upgrades Mistral-inst-v0.1 to match the performance level of its successor, v0.2, in qa tasks. therefore, the value of SelfExtend is at least equivalent to the training cost of Mistral-inst-v0.2?
New Anthropic research paper: Many-shot jailbreaking. We study a long-context jailbreaking technique that is effective on most large language models, including those developed by Anthropic and many of our peers. Read our blog post and the paper here: anthropic.com/research/many-…
Akari Asai @AkariAsai
11K Followers 650 Following Ph.D. student @uwcse & @uwnlp. NLP. IBM Ph.D. fellow (2022-2023). Meta student researcher (2023-) . ☕️ 🐕 🏃♀️🧗♀️🍳Bill Yuchen Lin 🤖 @billyuchenlin
6K Followers 2K Following Research @allen_ai. I evaluate (multi-modal) LLMs, build agents, and study the science of LLMs. Previously: @GoogleAI & @MetaAI FAIR @nlp_uscJim Fan @DrJimFan
229K Followers 3K Following @NVIDIA Sr. Research Manager & Lead of Embodied AI (GEAR Lab). Creating foundation models for Humanoid Robots & Gaming. @Stanford Ph.D. @OpenAI's first intern.Yu Su @ysu_nlp
6K Followers 857 Following Dist. Assist. Prof.@OhioState, Director @osunlp, 20% Researcher@Microsoft. I like to think about intelligence, artificial or biologicalYao Fu @Francis_YAO_
14K Followers 2K Following PhD @EdinburghNLP on LLMs and Machine Reasoning. Ex. @Columbia @PKU1898 @MITIBMLab @allen_ai AGI has yet to come, so keep runningTao Yu @taoyds
3K Followers 815 Following @XLangNLP lab, asst. prof. @HKUniversity. prev. postdoc @uwnlp; phd @Yale; intern @MSFTResearch, @SFResearch. he/him 🌈Weijia Shi @WeijiaShi2
5K Followers 968 Following PhD student @uwcse @uwnlp | Visiting Researcher @MetaAI | Undergrad @CS_UCLA | https://t.co/eLBQmgkvymSam Bowman @sleepinyourhat
35K Followers 3K Following AI alignment + LLMs at NYU & Anthropic. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.Xi Ye @xiye_nlp
2K Followers 304 Following CS PhD student @UTAustin. I study NLP, particularly explanations. I sometimes make memes.Michi Yasunaga @michiyasunaga
3K Followers 867 Following CS PhD @Stanford working on language models and multimodal models. Previously @Meta @GoogleDeepMind @YaleDiyi Yang @Diyi_Yang
14K Followers 2K Following Assistant Professor @Stanford CS @StanfordNLP @StanfordAILab. Formerly @GeorgiaTech. Computational Social Science & NLPWenhu Chen @WenhuChen
11K Followers 520 Following AI researcher @UWaterloo @GoogleAI @VectorInst. Interested in natural language processing, diffusion models. I direct TIGER-Lab at UWaterloo.Vivek Gupta @keviv9
2K Followers 5K Following PostDoc @cogcomp UPenn | Ph.D. CS @UUtah | @iitkanpur. @Bloomberg & @MSFTResearch Fellow | ex-@MetaAI, @IBM, @Verisk, @samsungresearch, @Synopsys #nlp #mlJie Huang @jefffhj
4K Followers 568 Following Ph.D. Candidate at UIUC🌽; Formerly @GoogleDeepmind @NVIDIAAI @AmazonScience. #NLProc Large Language ModelsHanjie Chen @hanjie_chen
2K Followers 365 Following Incoming Assistant Professor @RiceCompSci, Postdoc @jhuclsp, working on Trustworthy AI/NLP/ML, PhD @CS_UVA, former intern @allen_ai, @MSFTResearch, @IBMDinghuai Zhang 张鼎.. @zdhnarsil
2K Followers 1K Following PhD student at @Mila_Quebec. Ex intern at FAIR Labs @MetaAI. Previous math undergraduate at @PKU1898.Canwen Xu @XuCanwen
2K Followers 393 Following Member of Technical Staff @ https://t.co/60CJY0lbJL; PhD @UCSanDiego 🏄; Formerly @Microsoft @GoogleAI @huggingface 🤗. RT & like ≠ endorsements. Views are my own. He/himQingxiu Dong @qx_dong
841 Followers 592 Following PhD student @PKU1898. Research Intern @MSFTResearch Asia.Chao Zhang @chaozhangcs
466 Followers 393 Following Assistant Professor @ Georgia Tech CSE LLM, Uncertainty, AI for scienceSong Mei @Song__Mei
1K Followers 571 Following Assistant Professor at UC Berkeley, Department of Statistics and EECS. Researcher working on foundations of AI and deep learning.Saurabh Srivastava @_saurabh
830 Followers 375 Following Research in reasoning for better program synthesis (PhD, Postdoc, YC)Allen pang @Allenpang123456
1 Followers 15 FollowingRohan Paul @rohanpaul_ai
13K Followers 1K Following ML Engineer (e/acc) 📌 https://t.co/x0IIWfnOt8 🚀 https://t.co/QEO4CKRl1b Open LLMs is Happiness 💡 Ex Deutsche & HSBC. DM for collaboration.Lenna Register @RegistLenn
58 Followers 5K Followinghuansong @huansong514
7 Followers 172 FollowingFatih saidi @fatih_said87797
2 Followers 42 FollowingYasmine @bdwy240434
1 Followers 119 FollowingJames Chan @JamesChan736527
120 Followers 47 Following Seize opportunities with speed! DM for exclusive promotions. Swift action breeds success. Limited time: get 2, Pay for 1.nisten @nisten
10K Followers 5K Following fullstack-dev democratizing intelligence @skunkworks_ai | 🦝.ai | prev https://t.co/68jAlAVBKR |Roel Van de Paar @RoelVandePaar
710 Followers 302 FollowingKyle 'esSOBi' Stone @essobi
6K Followers 3K Following Hyperlexical Polymath Savant – GenTech / AI Constulant / CTO @ https://t.co/s7KzUOWpY5 - EX-Heroku Trust and Security. Bringing AGI to the public. GPT-5𝕋𝕒𝕥𝕤𝕦�.. @tatsuru_kikuchi
365 Followers 3K Following Research Officer at Faculty of Economics, The University of Tokyo. Keywords: Entrepreneur/OpenAI/Quantum/Crypto/Analytics/Consulting. Views are my own. Guy Swann ⚡️| Act.. @TheGuySwann
81K Followers 3K Following Liberty is a technology problem • Host of @BitcoinAudible, @Ai_Unchained • Pro Memecraft • Audiobook NarratorYin-Hong Cao @caoyinhong
141 Followers 1K Following Postdoc in Jiayang Li Lab, Institute of Genetics and Developmental Biology, CAS. Focus on the Multi-omics of dandelions & rice🌱🌾Recruiting Top-Tier Talents👇Parallel College @HenryWang550879
109 Followers 1K Following a new method to learn AI and Prompt Engineeringemanon @JianSuji
67 Followers 1K FollowingMarkus Junginger @greenrobot_de
1K Followers 408 Following Distributed and on-device data/AI. Cofounder/CTO @objectbox_io.zirui @zirui3
36 Followers 948 FollowingSiyuan Yu @cadaleyu
35 Followers 763 Following MSc @UAlberta @AmiiThinks Economics and Computation, Algorithmic Game Theory, Decision Making under UncertaintyPerry @kosh516
275 Followers 3K FollowingYifei Hu @hu_yifei
311 Followers 375 Following Ph.D. Candidate @LifeAtPurdue | NLP | LLM | UX | Programmer On job market for any AI related industry/academia rolesWard Plunet @StartupYou
129K Followers 110K Following Phd in Neuroscience looking at the intersection between machine learning and neuroscience #machinelearning #AI #neuroscienceJiefeng Chen @jiefengchen1
336 Followers 529 Following Research Scientist at Google | Working on LLM Research.Alo @Hal90910
0 Followers 2K FollowingPensé FFun @inftyCategory
100 Followers 6K FollowingAlyssa, Yi CHENG @YiCheng77783310
86 Followers 207 Following Ph.D. student, working on NLP for social good and conversational AI.Shay Zavala @ShayZavala36610
75 Followers 5K FollowingArjun Srivastava @arjunsriv
63 Followers 1K Following AI, reinforcement learning, distributed systems something new @Woven_ToyotaJP prev - discovery @bookmyshow, cs @IITIOfficialAugerDecay @augerdecay
133 Followers 3K Following 生活在两个世界之间,在旧的世界,它已经过去,但我们还清楚地记得它;新的世界,它正在到来,但我们还不完全理解它Charly Wargnier @DataChaz
112K Followers 31K Following 🥑 DevRel @Streamlit @SnowflakeDB 🪶 𝕏 about #AI, #LLMs, #DataScience, #WebApps, #SEO 💕 My heart is open source 🌍 Nature Lover 👀 My views!Shunyu Yao @ShunyuYao12
7K Followers 857 Following Language agents (ReAct, Reflexion, Tree of Thoughts) for digital automation (WebShop, SWE-bench, SWE-agent)Chetan Dhembre @ichetandhembre
1K Followers 4K Following CTO, co-founder @getloconow, ex @unacademy, @crowdfireTyne宇 @Tyne03720826082
110 Followers 3K FollowingAkari Asai @AkariAsai
11K Followers 650 Following Ph.D. student @uwcse & @uwnlp. NLP. IBM Ph.D. fellow (2022-2023). Meta student researcher (2023-) . ☕️ 🐕 🏃♀️🧗♀️🍳AK @_akhaliq
310K Followers 3K Following AI research paper tweets, ML @Gradio (acq. by @HuggingFace 🤗) dm for promo follow on Hugging Face: https://t.co/q2Qoey80GxPercy Liang @percyliang
49K Followers 408 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | PianistBill Yuchen Lin 🤖 @billyuchenlin
6K Followers 2K Following Research @allen_ai. I evaluate (multi-modal) LLMs, build agents, and study the science of LLMs. Previously: @GoogleAI & @MetaAI FAIR @nlp_uscWilliam Wang @WilliamWangNLP
14K Followers 718 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.Jim Fan @DrJimFan
229K Followers 3K Following @NVIDIA Sr. Research Manager & Lead of Embodied AI (GEAR Lab). Creating foundation models for Humanoid Robots & Gaming. @Stanford Ph.D. @OpenAI's first intern.Yi Tay @YiTayML
29K Followers 97 Following chief scientist / cofounder @RekaAILabs 🫠 past: research scientist @google brain 🤯 currently learning to be a dad 🍼Yann LeCun @ylecun
711K Followers 718 Following Professor at NYU. Chief AI Scientist at Meta. Researcher in AI, Machine Learning, Robotics, etc. ACM Turing Award Laureate.Yu Su @ysu_nlp
6K Followers 857 Following Dist. Assist. Prof.@OhioState, Director @osunlp, 20% Researcher@Microsoft. I like to think about intelligence, artificial or biologicalYao Fu @Francis_YAO_
14K Followers 2K Following PhD @EdinburghNLP on LLMs and Machine Reasoning. Ex. @Columbia @PKU1898 @MITIBMLab @allen_ai AGI has yet to come, so keep running(((ل()(ل() 'yoav))).. @yoavgo
46K Followers 2K FollowingGraham Neubig @gneubig
31K Followers 588 Following Associate professor at CMU, studying natural language processing and machine learning.Tao Yu @taoyds
3K Followers 815 Following @XLangNLP lab, asst. prof. @HKUniversity. prev. postdoc @uwnlp; phd @Yale; intern @MSFTResearch, @SFResearch. he/him 🌈Kayo Yin @kayo_yin
8K Followers 560 Following PhD student @berkeley_ai @berkeleynlp working on interpretability and signed languages. Former @msftresearch @deepmind @carnegiemellon @polytechnique. 🇫🇷🇯🇵Weijia Shi @WeijiaShi2
5K Followers 968 Following PhD student @uwcse @uwnlp | Visiting Researcher @MetaAI | Undergrad @CS_UCLA | https://t.co/eLBQmgkvymSam Bowman @sleepinyourhat
35K Followers 3K Following AI alignment + LLMs at NYU & Anthropic. Views not employers'. No relation to @s8mb. I think you should join @givingwhatwecan.Xi Ye @xiye_nlp
2K Followers 304 Following CS PhD student @UTAustin. I study NLP, particularly explanations. I sometimes make memes.Michi Yasunaga @michiyasunaga
3K Followers 867 Following CS PhD @Stanford working on language models and multimodal models. Previously @Meta @GoogleDeepMind @YaleSong Mei @Song__Mei
1K Followers 571 Following Assistant Professor at UC Berkeley, Department of Statistics and EECS. Researcher working on foundations of AI and deep learning.Rohan Paul @rohanpaul_ai
13K Followers 1K Following ML Engineer (e/acc) 📌 https://t.co/x0IIWfnOt8 🚀 https://t.co/QEO4CKRl1b Open LLMs is Happiness 💡 Ex Deutsche & HSBC. DM for collaboration.Jiefeng Chen @jiefengchen1
337 Followers 529 Following Research Scientist at Google | Working on LLM Research.Alyssa, Yi CHENG @YiCheng77783310
86 Followers 207 Following Ph.D. student, working on NLP for social good and conversational AI.Sicong (Sheldon) Huan.. @sicong_huang
715 Followers 1K Following Human, only human, infinitely human. Pretrained by evolution, finetuned by experience, prompted by situations. PhD student @UofT. Sharing ideas in AI&PsychologyChuang Gan @gan_chuang
4K Followers 456 Following Faculty Member at UMass Amherst; Principal researcher at MIT-IBM Watson AI Lab; Homepage: https://t.co/oXP6pqXCpoVaibhav @vaibhav_p1234
429 Followers 898 Following Unraveling AI complexities, crafting user-friendly innovations. Bridging the gap between intricate tech and practical applications.seshu bonam @seshubon
1K Followers 1K Following r/🔁 Reinforcement loops make everything better. building 🤹 Collaborative Ai spaces @ 🤖 https://t.co/jbHHOlOLTYAmanda Askell @AmandaAskell
26K Followers 653 Following Philosopher & ethicist teaching models to be good @AnthropicAI. Personal account. All opinions come from my training data.Han Fang @Han_Fang_
709 Followers 102 Following Research Scientist Manager at @meta GenAI, leading the LLM development of Meta AIEsin Durmus @esindurmusnlp
3K Followers 383 Following Research Scientist @anthropicai. Previously Postdoc @stanfordnlp and PhD @cornellcis. Working on LLMs & evaluating their safety and impact on society. she/her.Zac Kenton @ZacKenton1
1K Followers 1K Following Research Scientist in AI safety at DeepMind. Views are my own and don't represent DeepMind.Wanjia Zhao @WanjiaZhao1203
201 Followers 299 Following Incoming CS PhD @Stanford; Math Undergrad @ZJU_CHINA; Research intern @MSFTResearch Asia | ML/AI4SciSong Jiang @songjiang24
439 Followers 698 Following CS PhD student at @UCLA. Machine Learning, LLM, Causality and Graph.Xiang Yue @xiangyue96
2K Followers 434 Following Postdoc @LTIatCMU. PhD from Ohio State @osunlp. Training & evaluating foundation models. Pushing the boundaries of AI🤖. Previously @MSFTResearch.Binyuan Hui @huybery
6K Followers 318 Following 🐚 Core maintainer at Qwen and OpenDevin. || Code Generation, Text-to-SQL, Large Language Models.Roger Grosse @RogerGrosse
10K Followers 751 FollowingAakanksha Chowdhery @achowdhery
7K Followers 3K Following LLMs @ Google DeepMind :: PaLM, Gemini // Previously @MSFTResearch, @Stanford, @Princeton // views my own and subject to changeZhehao Zhang @Zhehao_Zhang123
98 Followers 390 Following Graduate student at @Dartmouthcs ; Visiting Research Intern @SALT_NLP; Prev. Research Intern @MSFTResearch; Formerly undergrad from @sjtu1896; NLP&ML #NLProcDan Hendrycks @DanHendrycks
17K Followers 81 Following • Director of the Center for AI Safety (https://t.co/ahs3LYCpqv) • GELU/ImageNet-C/MMLU/safety groundwork • PhD in AI from UC Berkeley https://t.co/rgXHAnYAsQ https://t.co/YtGtDh1aAVCollin Burns @CollinBurns4
11K Followers 276 Following Superalignment @OpenAI. Formerly @berkeley_ai @Columbia. Former Rubik's Cube world record holder.Zhaocheng Zhu (on the.. @zhu_zhaocheng
2K Followers 287 Following Final-year PhD @Mila_Quebec. BSc @PKU1898. Intern @Google. Reasoning, large language models, knowledge graphs and ML systems. Photographer held back by CS/ML.Nathan Lambert @natolambert
25K Followers 689 Following Figuring out AI @allen_ai, "rl boi" DM me papers. Writes @interconnectsai, talks @retortai Has phd and some credentialsHaotian Liu @imhaotian
6K Followers 397 Following building intelligence @xAI, creator of #LLaVA, cs @UWMadison, prev @MSFTResearchQinyuan Cheng @cheng_qinyuan
265 Followers 380 Following Alignment researcher, PhD student at FNLP Lab @FudanUniv; MOSS team; Intern at Shanghai AI Lab; True Dota2 fansLichang Chen @LichangChen2
214 Followers 486 Following LLM PhD @umdcs | Student Researcher @GoogleAI & @GoogleDeepmind| Building the AGI | BS @ZJU_China | Opinions are my own.Banghua Zhu @BanghuaZ
2K Followers 804 Following PhD @Berkeley_EECS, statistics, info theory, LLM, RL, Human-AI Interactions.Tianbao Xie @TianbaoX
1K Followers 1K Following Ph.D. student of @XLangNLP lab and @HKUNLP group 2022. Advised by @taoyds and @ikekong . e/iaTristan Thrush @TristanThrush
3K Followers 761 Following PhD-ing @StanfordAILab @stanfordnlp. Advisor @PlaytestAI. Past: @ContextualAI, @huggingface, @Meta FAIR, @mitbrainandcog, @MIT_CSAIL, @NASAJPLAri Holtzman @universeinanegg
3K Followers 2K Following PI @UChicagoCS & @DSI_UChicago, leader of Conceptualization Lab https://t.co/BVCT3zdaNV, Post-doc @Meta. We don’t really know much about language models...yet.Yang Song @DrYangSong
10K Followers 887 Following Leading the Strategic Explorations team @OpenAI. Score-Based Models. Diffusion Models. Consistency Models.Colin Raffel @colinraffel
30K Followers 655 Following nonbayesian parameterics, sweet lessons, and random birds. Friend of @srush_nlpChenhao Tan @ChenhaoTan
4K Followers 902 Following Assistant professor @UChicagoCS @UChicago. Working on human-centered AI, NLP, CSS at @ChicagoHAI, also part of @ChicagoNLP. DM for Postdoc/PhD opportunities.James Villarrubia @james_mtc
24K Followers 8K Following Tech, AI, and education startup nerd. Former @WhiteHouse, @DeptofDefense, @TheJusticeDept wonk. Now an Innovation Fellow in AI @NASA. Tweets are my own.Taiwei Shi @taiwei_shi
511 Followers 262 Following Ph.D. student @nlp_usc. Formerly @GeorgiaTech @USC_ISI. NLP & Computational Social Science.Ella Minzhi Li @EllaMinzhiLi
145 Followers 105 Following CS PhD student at NUS @wing_nus 🇸🇬, incoming visiting PhD at Stanford @stanfordnlp🌲, NLP researcher📒Yutong Bai @YutongBAI1002
3K Followers 397 Following EECS Rising Star, 2023 Apple Scholar, Visiting PhD @berkeley_ai, Intern @GoogleAI Brain team @MetaAI (FAIR Labs), CS PhD @JHUCompSciKai-Fu Lee @kaifulee
1.5M Followers 658 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 SuperpowersCheng Lu @ChengLu05671218
1K Followers 85 Following Member of technical staff @OpenAI. PhD @Tsinghua_Uni. Interested in diffusion models.Heng-Tze Cheng @HengTze
2K Followers 119 Following Director of Gemini Bard Research @GoogleDeepMind | Lead of LaMDA LLM & Conversation AI | Worked on Duplex, TensorFlow, Wide & Deep Learning | We're hiring!OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments Ever since OpenInterpreter, we've all been wondering just how effective agents can be if you give them a computer. Now we have a proper benchmark. Let's take a look (🧵):
Enjoyed this paper that plots emergent abilities with pretraining loss on the x-axis, which is actually a suggestion that @OriolVinyalsML also made a few years back: arxiv.org/abs/2403.15796 The paper uses intermediate checkpoints to plot a variety of pretraining losses. For some…
Nice paper from Microsoft - "LongEmbed: Extending Embedding Models for Long Context Retrieval" 🔥 ✨ While the context limit of LLMs has been pushed beyond 1 million tokens, embedding models are still confined to a narrow context window not exceeding 8k tokens, refrained from…
More than 50% of the reported reasoning abilities of LLMs might not be true reasoning. How do we evaluate models trained on the entire internet? I.e., what novel questions can we ask of something that has seen all written knowledge? Below: new eval, results, code, and paper.…
The self-extend paper is really becoming important - "LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning" 🔥 📌 Extend existing LLMs’ context window without any fine-tuning 📌 One feasible way to avoid the O.O.D. ( out-of-distribution) problems by caused unseen…
A video on what how an agent can improve a ML model on MLAgentBench: youtube.com/watch?v=s9NANr…
LLM Agent Operating System The integration and deployment of large language model (LLM)-based intelligent agents have been fraught with challenges that compromise their efficiency and efficacy. Among these issues are sub-optimal scheduling and resource allocation of agent
Introducing #AIOS, the world's first LLM Agent Operating System. AIOS embeds LLM into the OS as the brain, enabling an operating system "with soul". Paper1: arxiv.org/abs/2403.16971 Paper2: arxiv.org/abs/2312.03815 GitHub: github.com/agiresearch/AI… Discord: discord.gg/aUg3b2Kd
LLM Agent Operating System The integration and deployment of large language model (LLM)-based intelligent agents have been fraught with challenges that compromise their efficiency and efficacy. Among these issues are sub-optimal scheduling and resource allocation of agent
> phi-3 claims: better than mixtral 8x7B on benchmarks > phi-3 reality: worse than mistral 7b on lmsys you cannot cheat the scaling gods. very exciting 49 place. 🥲
Some small updates from the Anthropic Interpretability team: transformer-circuits.pub/2024/april-upd…
Scaling laws for dictionary learning! transformer-circuits.pub/2024/april-upd…
Some small updates from the Anthropic Interpretability team: transformer-circuits.pub/2024/april-upd…
Very excited to see this come out:
Do models need to reason in words to benefit from chain-of-thought tokens? In our experiments, the answer is no! Models can perform on par with CoT using repeated '...' filler tokens. This raises alignment concerns: Using filler, LMs can do hidden reasoning not visible in CoT🧵
Do models need to reason in words to benefit from chain-of-thought tokens? In our experiments, the answer is no! Models can perform on par with CoT using repeated '...' filler tokens. This raises alignment concerns: Using filler, LMs can do hidden reasoning not visible in CoT🧵
@mattshumer_ Hey Matt, appreciate you bringing this to our attention. We haven't modified any of the Claude 3 models since we launched them. On claude.ai, there's currently two layers that may contribute to perceived model performance: our T&S measures (standard mechanisms…
I guess you might have tried the demo (huggingface.co/spaces/Qwen/Qw…). Now the weights of Qwen1.5-110B are out! Temporarily only the base and chat models, AWQ and GGUF quantized models are about to be released very soon! Blog: qwenlm.github.io/blog/qwen1.5-1… Hugging Face:…
Thanks for implementing our paper! But actually, you only need to modify 5 lines of code to configure STORM with Claude models. ZERO line of change is needed now because I just added an example script to our repo! github.com/stanford-oval/…
STORM by @angelina_magr @MehdiAllahyari Implementation of the paper STORM (Synthesis of Topic Outlines through Retrieval and Multi-perspective Question Asking) -- uses Claude + sub-agents to write long-form articles. github.com/angelina-yang/…
From Claude100K to Gemini10M, we are in the era of long context language models. Why and how a language model can utilize information at any input locations within long context? We discover retrieval heads, a special type of attention head responsible for long-context factuality
First @nvidia DGX H200 in the world, hand-delivered to OpenAI and dedicated by Jensen "to advance AI, computing, and humanity":