Philippe Laban @PhilippeLaban
Research Scientist @MSFTResearch. NLP/HCI Research. New York City Joined April 2022-
Tweets416
-
Followers2K
-
Following826
-
Likes4K
The 2nd workshop on CustomNLP (models customized to individuals, groups, specialized domains) is back at #ACL2026! Join us if you're around! Schedule 👇👇👇👇👇
🚨 Join us on July 3 for the 2nd CustomNLP Workshop at #ACL2026! We're excited to share a fantastic lineup of invited talks & papers on personalizing, adapting, and customizing LLMs. Hope to see you there! 🎉 📅 customnlp4u.github.io/schedule/ 👇 Meet our amazing invited speakers:
📚 AI-written stories get attention. AI-translated literature is reaching readers more quietly, shaping how they experience an author’s work. So what is lost in AI literary translation ⁉️🤔 🤖 AI translation into English is readable and often ‘fine’. ✍️ But human translation is valued more, especially on a closer look, for clarity and immersion. ‼️ Both vary in quality BUT AI varies more, even within a single book. (1/11)
AI NEWS UPDATE We've added 200k+ recent news articles and 5k op-eds from Oct 2025 - June 2026. Local news is up to ~10.81% AI-generated.
Are LLM-generated stories novel? They can have unique characters and cliché plots, or the other way around. A holistic score doesn’t help distinguish the two 😔. Meet GENIE 🧞 – a fine-grained novelty metric that tells you where and why a response is original!
Woke up this morning to read @vauhinivara’s brilliant existential essay at @nytimes on em dash that reinforces the beauty of language and resistance to a world where LLMs homogenize it :-)
Post-training makes LLMs safer and better at following instructions, but less diverse. 🤔 Can we get that diversity back without sacrificing alignment? Introducing ReDiPO: a preference optimization recipe for restoring distributional diversity while preserving safety and instruction-following.
People are increasingly worried that AI tools make us overreliant. But how do we actually measure this? We introduce Offloading Score, a measure of reliance based on the fraction of cognitive effort offloaded to AI while completing a task. In a controlled user study, Offloading Score detects increased reliance under time pressure, while several common alternatives do not. (1/9)
We built a joint experimental and computational platform for scalable multi-modal single-cell chemical screens — profiling RNA, protein (including phospho-signaling), and chromatin accessibility responses to thousands of small molecule perturbations in parallel. biorxiv.org/content/10.648…
New paper! Have you or a loved one been harmed by a bad multiple-choice benchmark? 😔 You may be entitled to a more reliable evaluation 🩺 At #ACL2026, we'll present BenchMarker: a toolkit to diagnose common flaws in MCQA benchmarks, inspired by best practices in education 🧑🏫🧵
Ran some 🧪 with @irisiris_l to 🔬 why the Granta story was certainly 🤖 slop A lot of bad writing happens coz AI hasn’t learned aesthetics. It has memorized the whole internet and called it a day. So sure, maybe you don't trust AI detectors. But you can trust your own 👁️.
Looking for 1 emergency reviewer for a @COLM_conf paper on Image Editing of Diffusion Model due Wednesday (05/20). Please DM me if interested. Thanks! Retweets appreciated
We like to delegate tasks to LLMs, where the models perform long-horizon and iterative operations on documents and return the results. But how far can you trust the models to stay faithful to the original content of the document? A new study by Microsoft Research answers this question with an interesting technique. They use "round-trip relay" tasks to evaluate the capability of LLMs to perform accurate edit tasks on documents. Basically, it is like back-translation. The model has to perform an operation on the document and then reverse it to produce the original content. To simulate multi-iteration tasks, they chain these operations together across 20 steps. They created a benchmark, DELEGATE-52, which measures delegation performance across different domains. The results: - Even the best LLMs corrupt up to 25% of the document contents. - Corruption doesn't happen by "death by a thousand cuts." Usually, one mishap derails the model, and it can happen on any of the iterations - Generic tools for code execution and file read/write access don't make things better What's the main takeaway: - Only delegate to the extent that you stay in control - Create domain-specific tools Many thanks to @PhilippeLaban for sharing comments and actionable insights for developers.
Frontier AI models don't just delete documents — they rewrite them. Microsoft Research tested 19 models: even the best corrupted 25% of content. Agentic tools made it worse. venturebeat.com/ai/frontier-ai…
MyScholarQA is live! If you want a deep research system that actually knows about your work, check it out 👇 …rsonalized-scholarqa.apps.allenai.org
Now available in AstaLabs in limited research preview: MyScholarQA, a personalized version of ScholarQA for scientific deep research. ScholarQA helps synthesize evidence from 12M+ open-access papers. MyScholarQA adds user profiles to tailor that synthesis to you. 🧵
@tae_skim Great work, Tae Soo. The methodology is super clean and the paper was an incredible read!
Ask an LLM for a "post that'll pop off". Output misses so you say "more unique." It asks "unique how?" but you don't know yet. DiscoverLLM (ICML'26): trains LLMs to help users discover their intents, not just execute them. 📑 arxiv.org/abs/2602.03429 🌐 taesookim.com/discoverllm
We use LLMs to role-play "users" to train, evaluate, and improve AI assistants. How do you know if your user simulator is any good? We argue: rather than measuring how realistic it sounds, start measuring how the assistants it trains perform with real humans. 🧵👇
Today, we’re excited to launch Recursive (@Recursive_SI): an exceptional team across London and San Francisco, building AI systems that can safely improve their own capabilities over time.
User simulators have emerged as promising tools for building interactive AI, but what makes a “good” simulator? We reframe the problem as what creates downstream value for humans Our new simulator test: how an LLM assistant trained with the simulator performs with human users🧵
What happens when you compare the distributions of real and simulated user behaviors? 🔍 The gap is large. We introduce a method to measure this gap and evaluate 24 LLM-based user simulators across coding and writing tasks. @convai_uiuc @MSFTResearch @berkeley_ai 🧵 1/N
We've just released open source MTP style drafters for Gemma 4 models ⚡ Now Gemma 4 models are even faster on your choice of hardware, without losing quality! Grateful for the fruitful collaboration between my team, Gemma team, and many collaborators to enable this release!
Excited to introduce Gemma 4 Multi-Token Prediction Drafters⚡️Accelerated inference right in your pockets - Up to a 3x speedup - Same quality guarantees - Available in your favorite open-source tools
jason tang @Jasoncpit
0 Followers 39 Following
David Turturean @DavidTurturean
3K Followers 2K Following Physics & AI @ MIT. Hibernating for AGI Spring
青钢影 @Liuz_747
6 Followers 203 Following
Enamul Hoque Prince @Enamul_Hoque
238 Followers 232 Following Associate Professor at York University, former PostDoc @StanfordHCI, PhD from @UBC_CS. Interested in the areas of NLP, Visualizations, and HCI.Views are my own.
Az @c445319
0 Followers 54 Following
Einstein on oGPU @EinsteinXoGPU
1K Followers 7K Following EINSTEIN is a devnet Meme created on OpenGPU chain and loves science, fun and AI
Luis Cruz @1uiscruz_
59 Followers 299 Following Head of Talent @LiquidAI. Previously at Citadel, Stripe. All views are my own.
Romain Lopez @_romain_lopez_
2K Followers 246 Following Assistant Professor @ NYU Courant Institute & Biology
topdollar @topdollar3
28 Followers 383 Following
Charles Refort @CharlesRefort
82 Followers 539 Following
Youngseung Jeon @YoungseungJ
728 Followers 730 Following PhD candidate @UCLAengineering | AI and HCI for Science and Creativity | Research Scientist Intern @ToyotaResearchleelakrishna @leelakrishna
140 Followers 3K Following Technovating this world! - Making apps intelligent by playing data. Technology is no longer a passion, its an obsession. #iot #ml #k8s #ai
AIcontributors @aicontributors
12 Followers 2K Following
Angana Borah @AnganaBorah2
495 Followers 763 Following 3rd year Ph.D. @UMichCSE 〽️ advised by @radamihalcea. Language and Agents | current: @TechAtBloomberg Prev: @AmazonAlexa, @GeorgiaTech, @UTAustin, @DFKI & NITS
Vishal Thengane ( व... @vgthengane
281 Followers 586 Following PhD Student @UniOfSurrey; Working in 3D multi-modal 3D vision, continual learning, Previously @mbzuai @NTUsg, @IITRopar @CERN @SUTDsg
Phaedra Harmon @HarmonPhaedra
2 Followers 265 Following
Sanidhya @Sanidhya1325026
2 Followers 122 Following
Xuan Phi Nguyen (Phi) @xuanphinguyen
36 Followers 36 Following Agentic RL Training x Efficient Infra @Salesforce, Prev @Alibaba, Intern at @MetaAI & @Salesforce. The art of scaling compute is scaling without compute.
Aniket Vashishtha @AniketVashisht8
887 Followers 598 Following Working on Causality and LLMs | MSCS @IllinoisCDS | Prev Research Fellow @MSFTResearch
Itay Nakash | ACL-26 @itay__nakash
207 Followers 523 Following Research Scientists @ IBM | AI Safety | Agents, LLMs & NLP
Sumuk @sumukx
656 Followers 875 Following continual learning research @google / prev @PrimeIntellect @huggingface | opinions my own
Li Chuyuan @ChuyuanLi
155 Followers 419 Following Postdoc @UBC_NLP group, previously @labo_Loria, France 🤖 NLP, computational linguistics, LLMs❤️ Hiking, swimming, voyage
Aryo Pradipta Gema @aryopg
2K Followers 2K Following PhD student @BioMedAI_CDT @EdinburghNLP @EdiClinicalNLP | ex: AI Safety Fellow @Anthropic | Opinions are my own.
Arpandeep Khatua @ArpandeepKhatua
123 Followers 273 Following building coding agents @nvidia | Prev at @stanfordnlp @meta
Ali @s__haider1
27 Followers 367 Following working on agents & alignment @dartmouth | prev @nyuniversity shanghai
Daniela Fernandes @danielaDSF17
13 Followers 69 Following HCI Doctoral Researcher @ Aalto University
Ben Dickson @bendee983
6K Followers 671 Following Software Engineer | Tech analyst | Thinker | Student of life | Founder of @bdtechtalks
Koel Dutta Chowdhury @KoelDC
249 Followers 487 Following NLP Researcher @LstSaar | Saarland University
Niall McGuire @McguireNiall
150 Followers 754 Following PhD candidate - @UniStrathclyde @Strath_iSchool @StrathCIS @NeuraSearchLab Neural-Models for Neural Data
n8.made.it - agents, ... @n8ai0
17 Followers 296 Following https://t.co/jj78rw7pRz for agentic AI: agents, apps, open source and everything AI. Building in public with founders, engineers, and vibe coders. DMs open.
jianfeng @jianfengshike
200 Followers 6K Following
Brenno de Mello @BrennoMeello
91 Followers 4K Following
Subham De @SubhamDe2021
188 Followers 2K Following Founding Engineer at Sumble. Senior ML Research Scientist at Meta. CS PhD at UIUC. Previous DL intern at LinkedIN. Deep Learning. Natural Language Processing.
DataQuant Consulting @DataQuantAI
41 Followers 2K Following AI pricing, churn prediction & demand forecasting | Retail, FMCG & Logistics | Results in weeks | Deep dives → https://t.co/VLYfoYq8HH
Yifan Wu @yifannnwu
1K Followers 461 Following 吴奕凡; AI Research Scientist @Meta | Ph.D. @penn @picslupenn @GRASPlab.
David Turturean @DavidTurturean
3K Followers 2K Following Physics & AI @ MIT. Hibernating for AGI Spring
Julian Killingback @Julian_a42f9a
400 Followers 75 Following PhD Student at UMass Amherst working on Information Retrieval and Natural Language Processing
Pangram @pangram
12K Followers 21 Following Keeping the world free of AI slop. This account has automated replies: Tag @pangram with 'ai?' to get an AI check on any post.
Luis Cruz @1uiscruz_
59 Followers 299 Following Head of Talent @LiquidAI. Previously at Citadel, Stripe. All views are my own.
Shubhan Dua @defi_dua
7K Followers 3K Following Growth @quizlet | Built & exited @answersai_ai (2M users) | Prev @artemis @ucberkeley 24 @dormroomfund Ilahi
Youngseung Jeon @YoungseungJ
728 Followers 730 Following PhD candidate @UCLAengineering | AI and HCI for Science and Creativity | Research Scientist Intern @ToyotaResearch
Emma Brunskill @EmmaBrunskill
9K Followers 95 Following Associate professor, Computer Science. Stanford. Stanford's Human Centered AI (HAI) Institute. Opinions expressed are my own.
Angana Borah @AnganaBorah2
495 Followers 763 Following 3rd year Ph.D. @UMichCSE 〽️ advised by @radamihalcea. Language and Agents | current: @TechAtBloomberg Prev: @AmazonAlexa, @GeorgiaTech, @UTAustin, @DFKI & NITS
Vishal Thengane ( व... @vgthengane
281 Followers 586 Following PhD Student @UniOfSurrey; Working in 3D multi-modal 3D vision, continual learning, Previously @mbzuai @NTUsg, @IITRopar @CERN @SUTDsg
Nishant is at ACL �... @NishantBalepur
1K Followers 578 Following Intern @MSFTResearch, visitor @nyuniversity, and PhD-esperate @UofMaryland. Aligning and evaluating more helpful #LLMs. Prev @allen_ai @adobe @UofIllinois
Aniket Vashishtha @AniketVashisht8
887 Followers 598 Following Working on Causality and LLMs | MSCS @IllinoisCDS | Prev Research Fellow @MSFTResearch
Itay Nakash | ACL-26 @itay__nakash
207 Followers 523 Following Research Scientists @ IBM | AI Safety | Agents, LLMs & NLP
Sumuk @sumukx
656 Followers 875 Following continual learning research @google / prev @PrimeIntellect @huggingface | opinions my own
Li Chuyuan @ChuyuanLi
155 Followers 419 Following Postdoc @UBC_NLP group, previously @labo_Loria, France 🤖 NLP, computational linguistics, LLMs❤️ Hiking, swimming, voyage
Stephen Xie @stephenx_
774 Followers 918 Following working with actors and models @xai | views are my own
Arpandeep Khatua @ArpandeepKhatua
123 Followers 273 Following building coding agents @nvidia | Prev at @stanfordnlp @meta
Daniela Fernandes @danielaDSF17
13 Followers 69 Following HCI Doctoral Researcher @ Aalto University
Shangbin Feng @shangbinfeng
4K Followers 3K Following PhD student @uwcse @uwnlp. Model collaboration, for compositional intelligence and collaborative development. #水文学家
Ben Dickson @bendee983
6K Followers 671 Following Software Engineer | Tech analyst | Thinker | Student of life | Founder of @bdtechtalks
Koel Dutta Chowdhury @KoelDC
249 Followers 487 Following NLP Researcher @LstSaar | Saarland University
Subham De @SubhamDe2021
188 Followers 2K Following Founding Engineer at Sumble. Senior ML Research Scientist at Meta. CS PhD at UIUC. Previous DL intern at LinkedIN. Deep Learning. Natural Language Processing.
Isha Chaudhary @Ish_cha_
128 Followers 906 Following Ph.D. student in CS at UIUC, IITD'22, Working on making foundation models trustworthy.
Yujin Zhang @yujin__o
26 Followers 330 Following PhD Student @UCIrvine | human-centered AI, Software Engineering
Isadora White @isadorcw
523 Followers 364 Following PhD at @ucsd_cse| Prev Berkeley CS & Math Undergrad | LLM Agent Interactions, Multi-Agent and Multi-Turn RL
Jing Yu Koh @kohjingyu
7K Followers 391 Following ML PhD @CarnegieMellon. Previously: computer use and multimodal at MSL TBD Lab, text-to-image generation @GoogleAI. Opinions my own. 🇸🇬
Vineet Tiruvadi, MD P... @vineettiruvadi
1K Followers 2K Following Health AI ← Control Theory. I actually enjoy writing and drawing so... Prev @harvardmed @GeorgiaTech @emorymedicine @hume_ai
Mohamed Salem (On the... @msalemnlp
400 Followers 1K Following PhD candidate @PittCompSci. Ex Applied Scientist Intern @zillow Ex Research Intern @Microsoft ROAR and @tiktok_us SAMI. opinions are my own
Johan Obando-Ceron �... @johanobandoc
2K Followers 4K Following Graduate student @Mila_Quebec @UMontrealDIRO | RL/Deep Learning/AI | De Cali/Colombia pal’ Mundo 🇨🇴 | #JuntosProsperamos⚡#TogetherWeThrive| 🌱🌎
Laura Gomezjurado Gon... @LauraPGomez_
349 Followers 1K Following Robust & Trustworthy AI @stanford | Research @LilaSciences; views my own | Prev. @MSFTresearch | https://t.co/UHLf9HNGq8
Manoj @manoja328
585 Followers 7K Following helping founders @ https://t.co/8Yy9CmSFwr | Interested in productive AI; previously PhD research, Amazon, Stanford Research Institute (SRI)
Inna Lin @iwylin
1K Followers 1K Following Final-year PhD Student in AI/NLP @uwcse @uwnlp | Visiting Researcher @Meta Superintelligence Lab | Prev: @jpmorgan @cornell_tech @columbia
Bruno Ribeiro @brunofmr
2K Followers 275 Following Associate Professor of Computer Science @Purdue, interested in graphs, invariances, causality, and OOD robustness in ML
Ofir Press @OfirPress
19K Followers 9K Following I push the AI frontier by building tough benchmarks with amazing people. SWE-bench, SWE-agent, SciCode, AlgoTune. Postdoc @Princeton. PhD @nlpnoah @UW.
Mo @atmoio
72K Followers 18 Following Exploring what AI actually is. Building @shapeworkspace, prev @standardnotes. Talking at https://t.co/814DpgwSzr and https://t.co/vlHyF3gEjn.
Jianfeng Gao @JianfengGao0217
1K Followers 26 Following Distinguished Scientist & Vice President, Microsoft Research. IEEE Fellow.
Dylan HadfieldMenell @dhadfieldmenell
5K Followers 3K Following Associate Prof @MITEECS working on value (mis)alignment in AI systems; Safety & Alignment Advisor at https://t.co/vt2gVrVr9f; @[email protected]; he/him
Manuel Cherep @manuelcherep
209 Followers 403 Following PhD student @MIT working on behavioral machine learning
Teortaxes▶️ (Deep... @teortaxesTex
69K Followers 3K Following We're in a race. It's not USA vs China but humans and AGIs vs ape power centralization. @deepseek_ai stan #1, 2023–Deep Time «C’est la guerre.» ®1
Mengting Wan @mengtingwan
734 Followers 206 Following Scientist at @Microsoft #OAR #AppliedResearch | PhD from @ucsd_cse
Ash Paul @pash22
33K Followers 36K Following Public Hlth Dr,interested in evid-based health services commissioning,clinical leadership & hlth policy.My views are my own,RTs are no endorsements
Gagan Bansal @bansalg_
3K Followers 566 Following Researching multi-agent stuff and human-agent interaction @msftresearch @ms_aifrontiers | Co-built AutoGen | Previously @uwcse, @iitdelhi
Pavel Izmailov @Pavel_Izmailov
9K Followers 1K Following Researcher @AnthropicAI 🤖 Assistant Professor @nyuniversity 🏙️ Previously @OpenAI #StopWar 🇺🇦
Andrew Lee @a_jy_l
1K Followers 1K Following postdoc-ing at harvard, phd-ed at UMich. Interested in model interpretability
Roberto Dailey @RobertoDailey1
353 Followers 2K Following Research Scientist at @CognizantAILab. Prev: PhD in Semiconductor Data Analytics at UT Operations Research.


































