Xinyue Liu @irisiris_l
PhD student @sbucompsc. Prev @LTIatCMU cauchy221.github.io Stony Brook Joined July 2023-
Tweets32
-
Followers15
-
Following119
-
Likes8
Am I the only person who thinks this $1.5bn Anthropic books settlement counts as a win for Anthropic?
How do we navigate a growing collection of post-trained LLMs? In Delta Activations: A Representation for Finetuned LLMs, we propose a compact embedding that encodes the post-training signal. Try the interactive model navigator 👉 oscarxzq.github.io/delta_activati…
Language models often produce repetitive responses, and this issue is further amplified by post-training. In this work, we introduce DARLING, a method that explicitly optimizes for both response diversity and quality within online reinforcement learning!
Language models often produce repetitive responses, and this issue is further amplified by post-training. In this work, we introduce DARLING, a method that explicitly optimizes for both response diversity and quality within online reinforcement learning!
👀Have you asked LLM to provide a more detailed answer after inspecting its initial output? Users often provide such implicit feedback during interaction. ✨We study implicit user feedback found in LMSYS and WildChat. #EMNLP2025
It’s rare for competitors to collaborate. Yet that’s exactly what OpenAI and @AnthropicAI just did—by testing each other’s models with our respective internal safety and alignment evaluations. Today, we’re publishing the results. Frontier AI companies will inevitably compete on…
We also have a very similar and maybe simpler observations in our recent paper Large Language Models Encode Semantics in Low-Dimensional Linear Subspaces arxiv.org/abs/2507.09709 In fact we can build very effective guardrails using the subspace observation…
We also have a very similar and maybe simpler observations in our recent paper Large Language Models Encode Semantics in Low-Dimensional Linear Subspaces arxiv.org/abs/2507.09709 In fact we can build very effective guardrails using the subspace observation…
We have more evidence that some AI detectors ( in particular @pangramlabs ) work more than others and we should use them
We have more evidence that some AI detectors ( in particular @pangramlabs ) work more than others and we should use them
Introducing Generative Interfaces - a new paradigm beyond chatbots. We generate interfaces on the fly to better facilitate LLM interaction, so no more passive reading of long text blocks. Adaptive and Interactive: creates the form that best adapts to your goals and needs!
NEW: A major AI copyright legal showdown just took a huge twist today. Facing a class action on behalf of book authors that could've seen it pay over a TRILLION in damages for alleged piracy, Anthropic has agreed to settle instead: wired.com/story/anthropi…
New Anthropic research: filtering out dangerous information at pretraining. We’re experimenting with ways to remove information about chemical, biological, radiological and nuclear (CBRN) weapons from our models’ training data without affecting performance on harmless tasks.
Not all benchmarks are equally useful for comparing LMs—some are noisy, others show little signal. This work led by @heinemandavidj, analyzes 30 datasets across 900k OLMo training checkpoints and quantifies their signal-to-noise ratio.
Not all benchmarks are equally useful for comparing LMs—some are noisy, others show little signal. This work led by @heinemandavidj, analyzes 30 datasets across 900k OLMo training checkpoints and quantifies their signal-to-noise ratio. https://t.co/R1u7hEL6yv
Excited to be at #CHI2025. I will be presenting our work ( Best Paper Honorable Mention) tomorrow April 29th ( 11:10-11:22) moderated by @huashen218 Location : G416+ 417 I am also recruiting PhD students and visiting researchers at @sbucompsc . DMs are open. Please say hi !!
Introducing OLMoTrace! Now you can trace back OLMo generations to the training data. This is a feature that open data, open training recipe can unlock. We’ve pushed explainability to the next level, combining open data and fast search through trillions of tokens. So proud of…
Introducing OLMoTrace! Now you can trace back OLMo generations to the training data. This is a feature that open data, open training recipe can unlock. We’ve pushed explainability to the next level, combining open data and fast search through trillions of tokens. So proud of…
We created SuperBPE🚀, a *superword* tokenizer that includes tokens spanning multiple words. When pretraining at 8B scale, SuperBPE models consistently outperform the BPE baseline on 30 downstream tasks (+8% MMLU), while also being 27% more efficient at inference time.🧵
🎄🎅starting tomorrow at 10 am pacific, we are doing 12 days of openai. each weekday, we will have a livestream with a launch or demo, some big ones and some stocking stuffers. we’ve got some great stuff to share, hope you enjoy! merry christmas.
This is not good, "Surprisingly, we observe a significant decline in LLMs’ reasoning abilities under format restrictions." Link: arxiv.org/abs/2408.02442
Any paper with @YejinChoinka on it is a must read.
We’ve developed Rule-Based Rewards (RBRs) to align AI behavior safely without needing extensive human data collection, making our systems safer and more reliable for everyday use. openai.com/index/improvin…
Brihi Joshi @BrihiJ
2K Followers 4K Following PhD-ing @nlp_usc🏝 + @AmazonScience @Apple Fellow, ex-@IIITDelhi. Sky pics, #NLProc, @5sos and cat content, mostly thinking about “useful” AI
Anirudh Atmakuru @aatmakuru6
44 Followers 166 Following NLP PhD student @Cornell_CS with @tanyaagoyal | MS CS @UMassAmherst | https://t.co/07XQtkxTJi
Tuhin Chakrabarty @TuhinChakr
3K Followers 608 Following Assistant Prof @sbucompsc @stonybrooku Visiting Prof → @SFResearch Interests : Human Centered AI / Future of Work / AI & Creativity Formerly @ColumbiaCompSci
Clara Na @claranahhh
967 Followers 594 Following PhD student at @LTIatCMU / @SCSatCMU she/her, prev. @UVA and intern @ai2_allennlp @/clara on https://t.co/GHxXbrRHSB and @/clarana on https://t.co/47UIhMGaRd
Yoonsang Lee @yoonsang_
228 Followers 609 Following CS PhD @princeton_nlp @princetonPLI; prev @SeoulNatlUni
Roy Lee @SRoyLee
2K Followers 2K Following Assistant Professor @sutdsg, working on online trust & safety, computational social science, and social NLP. Currently leading the Social AI Studio.
Yu Ying Chiu (Kelly C... @kellychiuyy
137 Followers 148 Following UW NLP | MATS Scholar | Comp. Psyc/Social Sci. | ai values ↔ human values • value alignment for the good of humanity | Working on eval • data collection in wild
Jinghan Zhang @jinghan23
108 Followers 130 Following CSE PhD student @hkust in her second year advised by @junxian_he . Machine learning, NLP. bluesky here: https://t.co/ECxlKtKTxz
Yi-Hao Peng @yolohao
661 Followers 822 Following Just another 280-character amusing discrete prompts from @cmuhcii @SCSatCMU
Chinmaya Andukuri @chinmaya_mohan
53 Followers 265 Following applied research @CapitalOne, previously @StanfordAILab / @StanfordHAI
Lorenzo Xiao @lrzneedresearch
1K Followers 493 Following Anthropomorphism @LTIatCMU with @monadiab77 | NLP x HCI x CSS | prev @CarnegieMellonQ /@sutdsg
TuringPost @TheTuringPost
76K Followers 13K Following Newsletter exploring AI&ML - AI 101, Agentic Workflow, Business insights. From ML history to AI trends. Led by @kseniase_ Know what you are talking about👇🏼
Liqiya.L @Ciaraa_Liu
2 Followers 3 Following
Anirudh Atmakuru @aatmakuru6
44 Followers 166 Following NLP PhD student @Cornell_CS with @tanyaagoyal | MS CS @UMassAmherst | https://t.co/07XQtkxTJi
Brihi Joshi @BrihiJ
2K Followers 4K Following PhD-ing @nlp_usc🏝 + @AmazonScience @Apple Fellow, ex-@IIITDelhi. Sky pics, #NLProc, @5sos and cat content, mostly thinking about “useful” AI
Zeyuan Allen-Zhu, Sc.... @ZeyuanAllenZhu
20K Followers 452 Following physics of language models @ Meta (FAIR, not GenAI) 🎓：Tsinghua Physics — MIT CSAIL — Princeton/IAS 🏅：IOI x 2 — ACM-ICPC — USACO — Codejam — math MCM
Jason Weston @jaseweston
13K Followers 713 Following @Meta+NYU. NLP from scratch(Pretrain+FT LLM) 2008, MemNet (pre-Transformer) 2015, DrQA(pre-RAG) 2017, BlenderBot(dialog pre-ChatGPT) 2018+,Self-Rewarding+more!
Miles Wang @MilesKWang
3K Followers 1K Following Researcher @OpenAI. Beneficial and safe AGI. Prev @Harvard
Owain Evans @OwainEvans_UK
16K Followers 361 Following Runs an AI Safety research group in Berkeley (Truthful AI) + Affiliate at UC Berkeley. Past: Oxford Uni, TruthfulQA, Reversal Curse. Prefer email to DM.
Lei Li @lileics
6K Followers 439 Following Generative AI for language and science. MT, LLM, GenAI Safety, Drug Discovery
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
Naman Jain @StringChaos
2K Followers 1K Following PhD @UCBerkeley ; Research @cursor_ai | Projects - LiveCodeBench, DeepSWE, R2E-Gym, GSO, Syzygy, LMArena Coding | Past: @MetaAI @AWS @MSFTResearch @iitbombay
Percy Liang @percyliang
84K Followers 417 Following Associate Professor in computer science @Stanford @StanfordHAI @StanfordCRFM @StanfordAILab @stanfordnlp | cofounder @togethercompute | Pianist
Mina Lee @MinaLee__
4K Followers 474 Following Assistant Professor at @UChicagoCS ✍️ NLP & HCI AI-assisted writing, Human-AI interaction, Language models
Chenhao Tan @ChenhaoTan
4K Followers 949 Following Professor @UChicagoCS @UChicago. Directing @ChicagoHAI, also part of @UChicagoCI. Visiting @AbridgeHQ. DM/email for Postdoc/PhD opportunities.
MIT Media Lab @medialab
457K Followers 1K Following News from the MIT Media Lab. Explore all of the official MIT social media accounts at https://t.co/VBCkJP7BuC.
MIT NLP @nlp_mit
4K Followers 51 Following NLP Group at @MIT_CSAIL! PIs: @yoonrkim @jacobandreas @lateinteraction @pliang279 @david_sontag, Jim Glass, @roger_p_levy
Paul Liang @pliang279
8K Followers 711 Following Assistant Professor MIT @medialab @MITEECS @nlp_mit || PhD from CMU @mldcmu @LTIatCMU || Foundations of multisensory AI to enhance the human experience.
Jiacheng Liu @liujc1998
2K Followers 228 Following 🎓 PhD'ing @uwcse @uwnlp. 🧪 Cooking @allen_ai. 🛩 Private pilot. Prev: 🧑💻 @oculus, 🎓 @IllinoisCS. 📖 🥾 🚴♂️ 🎵 ♠️
Jiawei (Joe) Zhou @jzhou_jz
288 Followers 85 Following Natural language processing researcher. Assistant Professor at Stony Brook University. Previous: Research Assistant Professor at TTIC, PhD from Harvard.
Tuhin Chakrabarty @TuhinChakr
3K Followers 608 Following Assistant Prof @sbucompsc @stonybrooku Visiting Prof → @SFResearch Interests : Human Centered AI / Future of Work / AI & Creativity Formerly @ColumbiaCompSci
Zhiqing Sun @EdwardSun0909
19K Followers 1K Following Agents @Meta MSL TBD Lab. previously posttraining research @OpenAI train LLMs to do things: deep research, chatgpt agent, etc. CS PhD @LTIatCMU
Keenan Crane @keenanisalive
37K Followers 485 Following Digital Geometer, Assoc. Prof. of Computer Science & Robotics @CarnegieMellon @SCSatCMU and member of the @GeomCollective. There are four lights.
Shrimai @shrimai_
2K Followers 526 Following Senior Research Scientist @nvidia | PhD from @SCSatCMU | Prev @SFResearch @facebookai & @MSFTResearch
Nelson Liu @nelsonfliu
4K Followers 846 Following @stanfordnlp PhD student. tweets auto-deleted periodically.
Lianhui Qin @Lianhuiq
6K Followers 465 Following Assistant Professor at UCSD CSE. NLP, ML, AI. I’m recruiting PhD students.
Weijia Shi @WeijiaShi2
9K Followers 1K Following PhD student @uwnlp @allen_ai | Prev @MetaAI @CS_UCLA | 🏠 https://t.co/Q6Mzg8ow2j
Clara Na @claranahhh
967 Followers 594 Following PhD student at @LTIatCMU / @SCSatCMU she/her, prev. @UVA and intern @ai2_allennlp @/clara on https://t.co/GHxXbrRHSB and @/clarana on https://t.co/47UIhMGaRd
Eunsol Choi @eunsolc
6K Followers 910 Following on natural language processing / machine learning. assistant prof at @NYUDataScience @NYU_Courant prev @UTCompSci @googleai, @uwcse, @Cornell.
Daniel Fried @dan_fried
4K Followers 864 Following Assistant prof. @LTIatCMU @SCSatCMU. Working on NLP: language interfaces, applied pragmatics, language-to-code, grounding.
Yoonsang Lee @yoonsang_
228 Followers 609 Following CS PhD @princeton_nlp @princetonPLI; prev @SeoulNatlUni
Roy Lee @SRoyLee
2K Followers 2K Following Assistant Professor @sutdsg, working on online trust & safety, computational social science, and social NLP. Currently leading the Social AI Studio.
Zhaofeng Wu @zhaofeng_wu
2K Followers 263 Following PhD student @MIT_CSAIL | Previously @allen_ai | MS'21 BS'19 BA'19 @uwnlp
Yu Ying Chiu (Kelly C... @kellychiuyy
137 Followers 148 Following UW NLP | MATS Scholar | Comp. Psyc/Social Sci. | ai values ↔ human values • value alignment for the good of humanity | Working on eval • data collection in wild
Shuyan Zhou @shuyanzhxyc
3K Followers 806 Following assistant professor @dukecompsci | past: research lead @AIatMeta / msl (?) llama computer use agent, phd @LTIatCMU
Emmy Liu @_emliu
1K Followers 510 Following PhD student @LTIatCMU, working with @gneubig on NLP || intern @AIatMeta || UofT ‘21 🇨🇦 ||🤖✨🔡
Hanna Hajishirzi @HannaHajishirzi
9K Followers 443 Following Sr. Director of AI at @allen_ai, Prof at @uw_cse, lead OLMo, Tulu
Danqi Chen @danqi_chen
17K Followers 785 Following Associate professor @princeton_nlp @princetonPLI @PrincetonCS. Previously: @facebookai, @stanfordnlp, @Tsinghua_Uni https://t.co/hLXgShMIPE
Sewon Min @sewon__min
13K Followers 816 Following Assistant professor @Berkeley_EECS @berkeley_ai || Research scientist at @allen_ai || PhD from @uwcse @uwnlp
Akari Asai @AkariAsai
18K Followers 868 Following Incoming Assistant Professor @SCSatCMU & research scientist @allen_ai. akariasai @ 🦋
Jinghan Zhang @jinghan23
108 Followers 130 Following CSE PhD student @hkust in her second year advised by @junxian_he . Machine learning, NLP. bluesky here: https://t.co/ECxlKtKTxz
Yi-Hao Peng @yolohao
661 Followers 822 Following Just another 280-character amusing discrete prompts from @cmuhcii @SCSatCMU
Javier Rando @javirandor
4K Followers 747 Following security and safety research @anthropicai • people call me Javi • vegan 🌱Trends for United States
You might like
