Xiang Long @SDxFaith
MLE @ModelBest, ex-Alibaba Group/MSRA/Tencent AI Lab Joined February 2020-
Tweets26
-
Followers26
-
Following542
-
Likes17
SGLang, verl, OpenBMB and Tsinghua University: Pioneering End-to-End Multi-Turn RLHF We are thrilled to announce the release of the first fully functional, convergence-verified, end-to-end open source multi-turn Reinforcement Learning with Human Feedback (RLHF) framework,…
Demystifying Long CoT Reasoning in LLMs arxiv.org/pdf/2502.03373 Reasoning models like R1 / O1 / O3 have gained massive attention, but their training dynamics remain a mystery. We're taking a first deep dive into understanding long CoT reasoning in LLMs! 11 Major…
"When you find a genius, give them all power." I've been obsessed with this idea for 12 months now. I learned it from Munger but then saw all successful people apply it. From Steve Jobs to Robert Oppenheimer. Thread:
This is periodic reminder / recommendation to read this paper inside out. It is still the most helpful paper ive ever read. You may have not have encountered it because its not super popular like "Attention is all you need", but you WILL thank me. Despite the paper's title,…
We're excited about the future of truly multimodal tokens, where input and output seamlessly integrate across different media types. 🚀 #MultimodalAI #AI #Innovation
We're excited about the future of truly multimodal tokens, where input and output seamlessly integrate across different media types. 🚀 #MultimodalAI #AI #Innovation
May be indicate some signal of benchmark-oriented tuning lol
May be indicate some signal of benchmark-oriented tuning lol
I know your timeline is flooded now with word salads of "insane, HER, 10 features you missed, we're so back". Sit down. Chill. <gasp> Take a deep breath like Mark does in the demo </gasp>. Let's think step by step: - Technique-wise, OpenAI has figured out a way to map audio to…
[1/n] Happy to share our new work "MuPT: A Generative Symbolic Music Pretrained Transformer", encompassing a series of music generation models ranging from 190 million to 4.2 billion parameters, all based on the ABC Notation. According to human preference evaluations, our models…
Our 12 scaling laws (for LLM knowledge capacity) are out: arxiv.org/abs/2404.05405. Took me 4mos to submit 50,000 jobs; took Meta 1mo for legal review; FAIR sponsored 4,200,000 GPU hrs. Hope this is a new direction to study scaling laws + help practitioners make informed decisions
Introducing a new, fully open robotics dataset! - 76k episodes - 564 unique scenes - 100 contributors - 13 labs/institutions - 3 continents droid-dataset.github.io A short 🧵 on the backstory
Today is the beginning of our moonshot to solve embodied AGI in the physical world. I’m so excited to announce Project GR00T, our new initiative to create a general-purpose foundation model for humanoid robot learning. The GR00T model will enable a robot to understand multimodal…
Custom LLM and AI Agents (RAG) On Structured + Unstructured Data - AI Brain For Your Organization Imagine a ChatGPT-like interface over all your structured (database) and unstructured data. Ideally, you want to ask a question to an AI bot, and it should be able to run multiple…
Failure Points In RAG Systems Anyone who has tried to deploy an RAG system knows that there are several failure modes to watch out for While RAG helps you reduce hallucinations and create custom ChatLLM, there can be several failure points, given the complexity of the system.…
What is the correct recipe for finetuning LLMs for math reasoning? In MAmmoTH, we systematically study the SFT data composition and format for improving math, either in-distribution or out-of-distribution. Key takes: > Substantial, unprecidented performance gain for open-source…
What is the correct recipe for finetuning LLMs for math reasoning? In MAmmoTH, we systematically study the SFT data composition and format for improving math, either in-distribution or out-of-distribution. Key takes: > Substantial, unprecidented performance gain for open-source…
Ever want to make your LLM inference go brrrrr but got stuck at implementing speculative decoding and finding the suitable draft model? No more pain! Thrilled to unveil Medusa, a simple framework that removes the annoying draft model while getting 2x speedup. 🧵👇
50 Perplexity Prompts to Take Your Research to the Next Level. Don't forget to bookmark this post, to try these with Bard, ChatGPT, and Claude. 👇🏾 1. Emerging Industry Trends Prompt: "What are the emerging trends in [user input: specific industry] for the current year?" 2.…
Awesome repo for players using midjourney github.com/willwulfken/Mi…
Columbus Baumbach @ColumbusBa6592
25 Followers 2K Following
yu ma @yuma1089176
0 Followers 2 Following
Annalise Kuphal @KuphalAnna5646
65 Followers 3K Following
Monica @Monica0558877
0 Followers 5 Following
Justen Kerluke @JustenKerl29353
52 Followers 2K Following
Alirthu @Alirthu292546
32 Followers 606 Following
Jonathan Zheng @JonathanQZheng
35 Followers 58 Following Student at the Georgia Institute of Technology. Studying Computer Science with a concentration in Intelligence and Theory. Twitter Developer Account.
Yangqiu Song @yqsong
2K Followers 1K Following Associate Professor at HKUST, working on knowledge graphs, NLP, knowledge discovery on texts and graphs
Cunxiang Wang @CunxiangWang
760 Followers 1K Following [email protected], Postdoc@tsinghua, working with Prof. Jie Tang. PhD advised by Prof. Yue Zhang. Prev: Interned @AWScloud. LLM Evaluation, Posttraining
jinyang (patrick) li @jinyang34647007
1K Followers 1K Following CS PhD student @HKUniversity. Previously M.S. in @Columbia. Intern at @MSFTResearch, prev. at @AlibabaGroup. LLM, SQL Intelligence, Code Gen for New User Exp
Trending News by Pock... @triptotomorrow
1K Followers 3K Following
Wenmeng Zhou @zhouwenmeng
2K Followers 831 Following Engineering tech lead for Qwen and Wan api, Qwen Chat, Founding member for ModelScope, AI enthusiastic，Racing lover, Opinions are my own.
Ningyu Zhang@ZJU @zxlzr
3K Followers 2K Following Associate Professor @ZJU_China. Research interests include NLP, LLM, KG, Agent, Knowledge Editing.
Xuekai Zhu @zhu_xuekai
203 Followers 544 Following Ph. D. Candidate @sjtu1896 ｜ ACL 2023 Area Chair Award ｜Language models
OpenBMB @OpenBMB
4K Followers 134 Following OpenBMB (Open Lab for Big Model Base) aims to build foundation models and systems towards AGI.
Gong Junmin @junmingong
211 Followers 2K Following engineer and researcher. @ACEStudio_en @ ACE-Step
Mike Gunter @MikeGunter_
770 Followers 1K Following CTO and founder, @MatXComputing, designing hardware to make LLMs an order of magnitude smarter.
Pamela @rosaspamela14
312 Followers 3K Following
Kim Young @KimYoun73780490
120 Followers 961 Following A happy life requires three attitudes: Be indifferent to the past; Cherish the present; Believe in the future.
Alex Zhang @a1zhang
13K Followers 587 Following phd student @MIT_CSAIL + @SakanaAILabs, ugrad @Princeton, 🫵🏻 go participate in the @GPU_MODE kernel competitions!
Logan Kilpatrick @OfficialLoganK
209K Followers 2K Following Lead product for @GoogleAIStudio + the Gemini API. My views!
The AI Timeline @TheAITimeline
24K Followers 1 Following covering the latest AI & LLM research /// see "highlights" for all previous weekly threads /// building the best AI paper search engine @findmypapersai
Zihan Wang - on RAGEN @wzihanw
23K Followers 609 Following PhD Student @NorthwesternU. Intern @yutori_ai. I study PhysiCS of LLM. Ex @deepseek_ai @uiuc_nlp @RUC. RAGEN | Chain-of-Experts | ESFT.
el.cine @EHuanglu
81K Followers 583 Following Film director | AI Consultant | Partner with https://t.co/Vn9g3Z63CI Paris | Sharing practical ways to use AI for you and your business. All views 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.
Anjney Midha @AnjneyMidha
27K Followers 3K Following there are bitter lessons everywhere. some are sweet. general partner @a16z
Quentin Gallouédec @QGallouedec
3K Followers 663 Following PhD - Research @huggingface 🤗 TRL lead maintainer 🇫🇷 in 🇨🇦
Sohee Yang @ ACL 2025 @soheeyang_
2K Followers 543 Following PhD student/research scientist intern at @ucl_nlp/@GoogleDeepMind (50/50 split). Previously MS at @kaist_ai and research engineer at Naver Clova. #NLProc & ML
CAMEL-AI.org @CamelAIOrg
7K Followers 94 Following https://t.co/FmX1B3nzjA is working on finding the scaling laws of agents. The first and the best multi-agent framework. Discord: https://t.co/DRweXf0nOl. Product @Eigent_AI
Yunxin Li @LyxTg
1K Followers 509 Following Ph.D. Candidate. Currently focusing on multimodal reasoning and planning with large models. Past research interns: ByteDance Seed, Tencent PCG/AILab.
CodeGuide @CodeGuidedev
20K Followers 1 Following Generate coding docs for AI tools or run autonomous coding agent that can code for hours | by @cjzafir
Zhuang Liu @liuzhuang1234
11K Followers 1K Following Assistant Professor @PrincetonCS. researcher in deep learning, vision, models. previously @MetaAI, @UCBerkeley, @Tsinghua_Uni
Omar Sanseviero @osanseviero
50K Followers 3K Following Developer Experience Lead at @GoogleDeepMind Building Gemini API, Gemma, AI Studio and more AI products. My views ex-Chief Llama Officer @huggingface 🇵🇪🇲🇽
Alex Reibman 🖇️ @AlexReibman
46K Followers 806 Following Hyper Engineering @agentopsai Vibes @cerebral_valley Checks https://t.co/7GjxnkUotw Hack reporter
Prajwal Tomar @PrajwalTomar_
44K Followers 187 Following I build MVPs for founders in 21 days at @ignytlabs and teach others how to do the same inside @aimvpbuilders
ManusAI @ManusAI_HQ
204K Followers 25 Following Manus is the general AI agent that bridges minds and actions: it doesn't just think, it delivers results. Download our app: https://t.co/XSfjRhjdgo
Yichao 'Peak' Ji @peakji
25K Followers 167 Following Co-founder & Chief Scientist of Manus @ManusAI_HQ
verl project @verl_project
1K Followers 5 Following Open RL library for LLMs. https://t.co/Xpaq0thhgi Join us on https://t.co/uWI5Zbd6IH
BURKOV @burkov
47K Followers 110 Following My new LM book: https://t.co/YXNQUy7O3t PhD in AI, author of 📖 The Hundred-Page Language Models Book and 📖 The Hundred-Page Machine Learning Book
Garry Tan @garrytan
602K Followers 5K Following President & CEO @ycombinator —Founder @Initialized—designer/engineer who helps founders—San Francisco Dem accelerating the boom loop—e/acc—technology brother
Wenlong Huang @wenlong_huang
4K Followers 1K Following PhD Student @StanfordSVL @StanfordAILab. Previously @Berkeley_AI @GoogleDeepMind @NVIDIARobotics. Robotics, Foundation Models.
Heming Xia @hemingkx
1K Followers 2K Following Ph.D. student @HongKongPolyU | Prev MEng & BSc @PKU1898 | Prev Intern @MSFTResearch (MSRA) | NLP | Language Modeling
zhyncs @zhyncs42
3K Followers 518 Following 🌁 OPINIONS ARE MY OWN, Homepage https://t.co/saCowtppUm, Just for fun @lmsysorg SGLang, Prev @basetenco @meituan @Baidu_Inc
Kimi.ai @Kimi_Moonshot
50K Followers 98 Following Built by Moonshot AI to empower everyone to be superhuman.
kalomaze @kalomaze
18K Followers 2K Following ML researcher (@primeintellect), speculator • extremely silly jester
Ziniu Li @ZiniuLi
501 Followers 511 Following Ph.D. student @ CUHK, Shenzhen. Intern @Bytedance (Seed-Horizon) Working on RL and LLMs. Prev: Intern @Tencent (AI Lab)
LMSYS Org @lmsysorg
8K Followers 167 Following Large Model Systems Organization: Join our Slack: https://t.co/mSPNyKTLTS We developed SGLang https://t.co/jEqIJcGwGA, Chatbot Arena (now @lmarena_ai), and Vicuna!
Physical Intelligence @physical_int
24K Followers 30 Following Physical Intelligence (Pi), bringing AI into the physical world.
Furong Huang @furongh
9K Followers 2K Following Associate professor of @umdcs @umiacs @ml_umd at UMD. Researcher in #AI/#ML, AI #Alignment, #RLHF, #Trustworthy ML, #EthicalAI, AI #Democratization, AI for ALL.
RWKV @RWKV_AI
3K Followers 3 Following AI model built by the community, for everyone in this world Part of the Linux Foundation, Apache 2 licensed An RNN scaled to 14B params with GPT-level of perf
Chengzu Li @li_chengzu
393 Followers 197 Following PhD student in NLP @CambridgeLTL @JesusCollegeCam
Tianbao Xie @TianbaoX
3K Followers 2K Following Ph.D. candidate @XLangNLP lab and @hkunlp2020 . Incoming @OpenAI . Advised by @taoyds and @ikekong . 🤝 @Alibaba_Qwen @SFResearch
Justine Moore @venturetwins
125K Followers 971 Following Partner @a16z AI 🤖 and twin to @omooretweets | Investor in @elevenlabsio, @krea_ai, @bfl_ml, @hedra_labs, @WaveFormsAI, @ViggleAI, & more
Songlin Yang @SonglinYang4
12K Followers 3K Following PhD-ing @MIT_CSAIL. Working on scalable and principled algorithms in #LLM and #MLSys. In open-sourcing I trust 🐳. she/her/hers
leloy! @leloykun
6K Followers 4K Following Math @ AdMU • NanoGPT speedrunner • Muon fan 🤍 • prev ML @ XPD • 2x IOI & 2x ICPC • https://t.co/nfO038itfn
Shibo Hao @Ber18791531
2K Followers 1K Following Ph.D. student @UCSanDiego Previous Research Scientist Intern @AIatMeta. B.S. in Computer Science @PKU1898 Coconut, Reasoning-via-planning, ToolkenGPT
Hume AI @hume_ai
22K Followers 23 Following The foundational speech-language model with emotional intelligence. Available via TTS or Speech to SpeechTrends for United States
You might like
