-
Tweets66
-
Followers260
-
Following161
-
Likes40
Agentic folks, come and check out this exciting playground
Agentic folks, come and check out this exciting playground
Join our Discord(discord.gg/Y9WVnhChUX), Have Fun and Happy Coding with Fellow Agent Enthusiasts!
Join our Discord(discord.gg/Y9WVnhChUX), Have Fun and Happy Coding with Fellow Agent Enthusiasts!
🎉Introducing our latest paper: "A Survey of Neural Code Intelligence: Paradigms, Advances and Beyond" 📑Paper: arxiv.org/abs/2403.14734 🌟Repo: github.com/QiushiSun/NCIS… 🤗Huggingface: huggingface.co/papers/2403.14… 🧵[1/4]
Towards Generalist Computer Agents with Self-Improvement Introduces OS-Copilot, a framework to build generalist computer agents that interface with key elements of an operating system like Linux or MacOS. It also proposes a self-improving embodied agent for automating general…
Fun fact: The initial name we had for SeeClick was SeeAct. However, just right before submitting our paper to arXiv, we discovered an amazing project with the exact same name by @ysu_nlp & @boyuan__zheng (will update our related work section to include SeeAct in the new version)
Fun fact: The initial name we had for SeeClick was SeeAct. However, just right before submitting our paper to arXiv, we discovered an amazing project with the exact same name by @ysu_nlp & @boyuan__zheng (will update our related work section to include SeeAct in the new version)
Introducing ''AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents'' 📈Fine-grained Metrics: 🔍 Spotting incremental progress 📊Systematic Board: 🤔 What makes a LLM ace the agent game? Leaderboard: hkust-nlp.github.io/agentboard/ Repo: github.com/hkust-nlp/Agen… 🧵[1/4]
1/ After weeks of learning, I am proud to share - "The Annotated GPT-2" ladies and gentleman! In this post, I re-implement OpenAI's GPT-2 in PyTorch using @huggingface source code and try to explain all the magic that goes on inside the model. amaarora.github.io/2020/02/18/ann…
Tawanda Netz @NetzTawa
50 Followers 5K Following
Fan Zhou✈️ICLR@20.. @FaZhou_998
195 Followers 414 Following AI Research at Shanghai AI Lab | GAIR RA @XLangNLP @HKUniversity | Ex Intern @MSFTResearch Undergrad & M.S. @sjtu1896
li ii iq j @iq_li80427
56 Followers 370 Following
Ramonita Chary @CharyRamon64555
50 Followers 5K Following
Siheng Zhao @ ICLR �.. @SihengZhao
127 Followers 265 Following incoming CS PhD student @USC; prev. @XLangNLP
Rumaysah Pablo @pa_rumays
81 Followers 5K Following
Jacquie Huwe @HuweJacqui80942
0 Followers 158 Following
Rheba Ineson @rhe_ines
71 Followers 5K Following
Xinyun Chen @xinyun_chen_
4K Followers 851 Following Research Scientist at @GoogleDeepMind. PhD from @Berkeley_EECS.
Tetatha @Tetatha265746
5 Followers 639 Following Nice to meet you. My hobbies are reading, food and sports. I like cats😘 I like to meet new friends while traveling🎉🎉🎉
Massimo Caccia @MassCaccia
2K Followers 570 Following Research Scientist @ServiceNowRSRCH. Gradient-descent enthusiast building LLM agents. PhD @Mila_Quebec. Formerly @Deepmind, @AWScloud, @SpotifyResearch.
Angie Dupuis @DupuisAngi21202
18 Followers 913 Following
Xing Han Lu @xhluca
1K Followers 212 Following Tinkering with Conversational Web Agents @Mila_Quebec
Traci @traci4johnson
489 Followers 3K Following
OpenGVLab @opengvlab
734 Followers 70 Following Shanghai AI Lab, General Vision Team. We created InternImage, BEVFormer, VideoMAE, LLaMA-Adapter, Ask-Anything, and many more! [email protected]
An Vu 🚹 @mangoesai
52 Followers 273 Following Also building the homie Jarvis Previously @NASA @StabilityAI + Founded @Logseq
MikaStars★ @MikaStars39_
184 Followers 635 Following Second year B.A. / B.S. in @ZJU_China Prev: Bsc in @Polytechnique Devoted in LLM Architecture & Interpretability
haydée @etesperer
18 Followers 114 Following
Kellie Rish @RishKellie29898
102 Followers 5K Following
Yiran HU @Huyr21
47 Followers 157 Following Master student in Tsinghua University @THUIR_lab Research Assistant in HKU @HKUniversity Research interest: Computational Law, Information Retrieval
Liang Ding @liangdingNLP
483 Followers 1K Following NLP/ML Researcher (working on developing LLM and exploring its applications) & Ex-@JD_Corporate @TencentGlobal @Sydney_Uni. Opinions are my own.
Kunal Singh @ikunalsingh7
71 Followers 701 Following Lead AI Researcher https://t.co/z4idFlmggM (T2I), Lead AI Researcher @fractalai Prev: GSoC @CERN, Alumni @IITKgp, Intern @AmiiThinks Diffusion, VLMs, reasoning@LLM
Jennifer Campbell @jml_campbell
2K Followers 2K Following Partner at Founders Fund, Previously @tagomisystems, @usv
Chuanyang Jin @chuanyang_jin
149 Followers 177 Following undergrad @nyuniversity | visiting researcher @MIT
OS-Copilot @oscopilot
27 Followers 3 Following The library for generalist computer agents research and applications. Github: https://t.co/hQeNYDyHqB Discord: https://t.co/YZD6vjdHIt
Demi Wang @kiyuuasa
18 Followers 297 Following Music & Tech | Prev @Cal @BytedanceTalk | #NLProc | LLM Agents | e/acc
Qingxiu Dong @qx_dong
845 Followers 593 Following PhD student @PKU1898. Research Intern @MSFTResearch Asia.
Zhuosheng Zhang @zhangzhuosheng
1K Followers 542 Following Tenure-Track Assistant Professor at @sjtu1896. NLP/AI/ML. Prev intern @AmazonScience @MSFTResearch @NICT_Publicity @sinovationvc @IBM #NLProc
Blaze (Balázs Galamb.. @gblazex
1K Followers 1K Following A Smooth Guy; Developer of SmoothScroll for macOS, Windows & Google Chrome.
Christian Ströbele @c_stroebele
985 Followers 962 Following Religionen, Philosophie, Theologie, Interreligiöses. Leiter Fachbereich Interreligiöser Dialog @akademieRS @[email protected] @cstroebele.bsky.social
Jonny_vc @vc_jonny
43 Followers 109 Following
CogineAI @CogineAI
34 Followers 226 Following
luna ☼☽ @IunacieI
20 Followers 716 Following
Romano @____romano____
183 Followers 670 Following Praise the Lord and pass the ammunition. God wants you to go to war.
lueurverte @luerverte
494 Followers 5K Following
刘江/LIU Jiang @turingbook
54K Followers 3K Following Exploring AGI. Co-Founder of Turing Company. ex Meituan, BAAI, CSDN. 图灵联合创始人。曾任：智源研究院副院长，CSDN&《程序员》杂志总编，美团技术学院院长。
Chujie Zheng @ ICLR 2.. @ChujieZheng
587 Followers 506 Following LLM alignment #LLMs | Visiting scholar @CS_UCLA | PhD candidate @TsinghuaCoAI | On the job market (2025), seeking for industrial research postions or postdocs
Stefano Albrecht (UoE.. @UoE_Agents
1K Followers 162 Following Autonomous Agents Research Group @InfAtEd Research in AI and machine learning for autonomous systems. Homepage: https://t.co/wNWZTjrqgl
Xinyun Chen @xinyun_chen_
4K Followers 851 Following Research Scientist at @GoogleDeepMind. PhD from @Berkeley_EECS.
Massimo Caccia @MassCaccia
2K Followers 570 Following Research Scientist @ServiceNowRSRCH. Gradient-descent enthusiast building LLM agents. PhD @Mila_Quebec. Formerly @Deepmind, @AWScloud, @SpotifyResearch.
Frank Xu @frankxu2004
693 Followers 570 Following language and computer stuff, phd student @ltiatcmu
Thomas Scialom @ThomasScialom
6K Followers 233 Following AGI Researcher @MetaAI -- Lead Llama 2 and Postraining Llama 3. Also CodeLlama, Galactica, Toolformer, Bloom, Nougat, GAIA, ..
Jason Weston @jaseweston
9K Followers 568 Following Research @MetaAI+NYU. Pretrain+SFT: NLP from Scratch (2011). Multilayer attention+position encode+LLM: MemNet (2015). Recent (2024): Self-Rewarding LLMs & more!
Jindong Wang @jd92wang
3K Followers 409 Following Senior Researcher at @MSFTResearch. Robust machine learning, transfer learning, OOD generalization. Recently: large language models. https://t.co/fUsOEtxAW7
Desmond Elliott @delliott
3K Followers 440 Following Assistant Professor at the University of Copenhagen working on multimodal machine learning.
Xing Han Lu @xhluca
1K Followers 212 Following Tinkering with Conversational Web Agents @Mila_Quebec
Heng Ji @hengjinlp
4K Followers 238 Following
Div Garg @DivGarg9
17K Followers 99 Following Working on breaking things @MultiON_AI | RL + AI researcher | Adjunct Lecturer @Stanford CS | worked @nvidia Research, @apple SPG, @GoogleAI, @UberATG
OpenGVLab @opengvlab
734 Followers 70 Following Shanghai AI Lab, General Vision Team. We created InternImage, BEVFormer, VideoMAE, LLaMA-Adapter, Ask-Anything, and many more! [email protected]
Eugene Vinitsky @EugeneVinitsky
13K Followers 2K Following Lets make multi-agent learning easy. Anti-cynic. RS at Apple, Asst. Prof at @nyutandon. He/him. Anonymous feedback: https://t.co/Mmmg7uPm1t
AgentOps 🖇️ @AgentOpsAI
3K Followers 5 Following Agents suck. We're fixing that. (DMs open). https://t.co/GcfVtDtYlZ
Song Mei @Song__Mei
1K Followers 602 Following Assistant Professor at UC Berkeley, Department of Statistics and EECS. Researcher working on foundations of AI and deep learning.
Ivan Titov @iatitov
6K Followers 701 Following Professor of Natural Language Processing at Uni Edinburgh / Uni Amsterdam
Hanna Hajishirzi @HannaHajishirzi
6K Followers 328 Following Associate professor at @uw_cse; senior director at @allen_ai co-leading @allenNLP; AI/NLP researcher at @uw_nlp
Ningyu Zhang@ICLR2024 @zxlzr
1K Followers 924 Following Associate Professor @ZJU_China. Research interests include NLP, KG.
Luke Zettlemoyer @LukeZettlemoyer
8K Followers 2K Following
Jure Leskovec @jure
43K Followers 378 Following Professor of #computerscience @Stanford; Co-founder at https://t.co/hhm1j5wP0f #machinelearning #graphs.
JHU CLSP @jhuclsp
5K Followers 806 Following Center for Language and Speech Processing at @JohnsHopkins #NLProc #MachineLearning #AI https://t.co/6IXR5OSiDY @[email protected]
Mark Dredze @mdredze
4K Followers 788 Following John C Malone Professor at @JohnsHopkins @JHUCompSci @jhuclsp @jhumceh; Part time @techatbloomberg (tweets my own) Mastodon @[email protected]
Wenhao Zhu @Wenhao_NLP
254 Followers 442 Following PhD candidate @NJUNLP, visiting PhD student @EdinburghNLP, interested in multilingual LLM and machine translation.
Sham Kakade @ShamKakade6
12K Followers 387 Following Harvard Professor. Full stack ML and AI. Co-director of the Kempner Institute for the Study of Artificial and Natural Intelligence.
Da Yin @Wade_Yin9712
778 Followers 421 Following PhD @uclanlp | Intern at AI2 Mosaic @ai2_mosaic | Amazon PhD Fellow in 2023 @AmazonScience
Sanjeev Arora @prfsanjeevarora
21K Followers 32 Following Director, @PrincetonPLI and Professor @PrincetonCS. Seeks math/conceptual understanding of deep learning and large AI models.
Zachary Lipton @zacharylipton
59K Followers 2K Following Professor: CMU/@acmi_lab, CTO / CSO: @AbridgeHQ, Creator: @d2l_ai & https://t.co/QQt98VNLUp, Relapsing 🎷
Anna Korhonen @annalkorhonen
3K Followers 237 Following Professor of Natural Language Processing at University of Cambridge, Director @CambridgeLTL, Researcher #NLProc, #AI
Andreas Vlachos @vlachos_nlp
5K Followers 1K Following Professor in NLP/ML at @Cambridge_CL, Fellow of @FitzwilliamColl, @ELLISforEurope member
Jim Fan @DrJimFan
232K 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.
CambridgeNLP @cambridgenlp
9K Followers 196 Following The #NLP/#NLProc/#ML research group in the University of Cambridge, Computer Science department. Account managed by @Eric_chamoun, @richarddm1
Yuxiang (Jimmy) Wu @YuxiangJWu
1K Followers 1K Following Co-founder @WecoAI | UCL PhD | Natural Language Processing | Machine Learning | formerly intern @allen_ai @MetaAI
Zhiting Hu @ZhitingHu
3K Followers 353 Following Assist. Prof. at UC San Diego; Artificial Intelligence, Machine Learning, Natural Language Processing
OS-Copilot @oscopilot
27 Followers 3 Following The library for generalist computer agents research and applications. Github: https://t.co/hQeNYDyHqB Discord: https://t.co/YZD6vjdHIt
Yao 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
AutoGen @pyautogen
4K Followers 38 Following OSS library for agentic AI apps and research 🤖🤖 GitHub: https://t.co/LliIsorLuY Discord: https://t.co/2iE2O7QV6A Research: https://t.co/TeOUTAZrbd
Andrew Ng @AndrewYNg
1.0M Followers 916 Following Co-Founder of Coursera; Stanford CS adjunct faculty. Former head of Baidu AI Group/Google Brain. #ai #machinelearning, #deeplearning #MOOCs
yi 🦛 @agihippo
3K Followers 81 Following hobbies: swimming, chasing humans on a boat, AGI friends: @agikoala warning: spicy takes
Krista Opsahl-Ong @kristahopsalong
696 Followers 354 Following CS PhD candidate @Stanford @StanfordAILab || Prev @Google @Microsoft
Michael Ryan @michaelryan207
590 Followers 472 Following NLP Masters Student @stanfordnlp. || Working on DSPy 🧩 || Prev @GeorgiaTech @Microsoft
Percy Liang @percyliang
50K Followers 408 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | Pianist
Russ Salakhutdinov @rsalakhu
100K Followers 142 Following UPMC Professor of Computer Science at Carnegie Mellon University, ex-Director of AI research at @Apple, co-founder Perceptual Machines (acquired by Apple)
Sam 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.
Alex Cabrera @a_a_cabrera
1K Followers 491 Following PhD candidate @cmuhcii @scsatcmu. Humans + AI = ???I will be attending #ICLR2024 in Vienna from May 7-11. Excited to catch up with old friends and engage in discussions with new ones.
Delighted to release ✨Llama-3-8B-Web✨, the most capable agent built for web navigation by following instructions and replying💬. It surpasses GPT-4V* by 18% on WebLINX, a benchmark for web navigation with dialogue. Model: huggingface.co/McGill-NLP/Lla… Code: github.com/McGill-NLP/web…
Our vision large language model, InternVL-1.5, is now the best open-sourced #VLM model. 👉Give it a try! Online demo: internvl.opengvlab.com 🤗Download model: huggingface.co/OpenGVLab 🚀Code：github.com/OpenGVLab/Inte…
We are thrilled to announce the release of Reka Core. It is available at the Reka Playground chat.reka.ai. For more details, please refer to our tech report publications.reka.ai/reka-core-tech…
Meet Reka Core, our best and most capable multimodal language model yet. 🔮 It’s been a busy few months training this model and we are glad to finally ship it! 💪 Core has a lot of capabilities, and one of them is understanding video --- let’s see what Core thinks of the 3 body…
Lazy twitter: A common question in NLP class is "if xBERT worked well, why didn't people make it bigger?" but I realize I just don't know the answer. I assume people tried but that a lot of that is unpublished. Is the theory that denoising gets too easy for big models?
🤔Can we assess agents across various apps & OS w.o. crafting new envs? OSWorld🖥️: A unified, real computer env for multimodal agents to evaluate open-ended computer tasks with arbitrary apps and interfaces on Ubuntu, Windows, & macOS. + annotated 369 real-world computer tasks…
The newest version is going to be pushed soon!
Monograph on "Formal Aspects of Language Modeling" from @ryandcotterell et al. arxiv.org/abs/2311.04329 It would be so nice if everyone read this and we had shared foundations. Particularly for interpretability.
This thread remains important. Yes you can use DSPy as a prompting library or as a prompt optimizer, but it’s *not* either of those things. It proposes a new paradigm for programming modular AI systems, where prompting/finetuning are low-level implementations. See 🧵 below.
Now that DSPy is popular, some nuance. DSPy is *not* a prompting framework. It proposes a new paradigm: a framework for expressing & optimizing Language Programs. Think neural networks but with LM "layers", i.e. abstract modules that *learn* prompts/finetunes given a metric.
linear transformers framed as RNNs for narrative purposes is probably the weirdest thing in today's arch landscape. fwiw i think linear transformers actually don't work broadly. you can show a parity here and there on some tasks but you'll lose a lot at a broad level.
Tools can empower LMs to solve many tasks. But what are tools anyway? github.com/zorazrw/awesom… Our survey studies tools for LLM agents w/ –A formal def. of tools –Methods/scenarios to use&make tools –Issues in testbeds and eval metrics –Empirical analysis of cost-gain trade-off
First demo of a custom GPT that can control my computer. I can now use my computer remotely using only voice (or text) chat-based control. This GPT uses the new 'actions' API to control the mouse and keyboard, and 'look at'* the screen. (video in two parts)
We're excited to release VisualWebArena, with > 900 challenging, visually-grounded examples to evaluate multimodal web agents. jykoh.com/vwa Has self-contained web environments, and execution-based evaluation! And headroom: GPT-4V gets 16% success; people get 89%.
Computer interfaces are inherently visual. To build general autonomous agents, we will need strong vision language models. To assess the performance of multimodal agents, we introduce VisualWebArena (VWA): a benchmark for evaluating multimodal web agents on realistic visually…
Generalist web agents may get here sooner than we thought---introducing SeeAct, a multimodal web agent built on GPT-4V(ision). What's this all about? > Back in June 2023, when we released Mind2Web (osu-nlp-group.github.io/Mind2Web/) and envisioned generalist web agent, a language agent…
I'm unlikely to accomplish much else in 2020, so it's time for my roundup of what I *have* managed! It doesn't feel like much but whew ee it all counts double this year, so
NLP twitter: I thought the NeurIPS Impact statement was a nice addition this year. It was an excuse to spend precious deadline time chatting with grad students about higher-level questions. Is there any push to add this to NAACL/EMNLP? medium.com/@GovAI/a-guide…
It breaks my 💚 when researchers tell me that VAEs don't work. My first typical question is "did you try hierarchial VAE or vanilla VAE?", the answer is usually vanilla VAE. VAEs work much better with hierarchical structures. NVAEs and this work take this to the extreme!
Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images “Very Deep VAEs” achieve higher likelihoods, use fewer parameters, generate samples 1000x faster, and are more easily applied to hi-res images, compared to PixelCNN. openreview.net/forum?id=RLRXC…
I get the sense that plenty of people think that it's okay to be racist against Asians. Basically, the Model Minority Myth is still alive and well in 2020. en.wikipedia.org/wiki/Model_min…
How discovery (and the retrospective telling of discovery) works.
Trends for United States
You might like
