iiinova — where your digital self keeps evolving

Mohit Bansal @mohitbansal.bsky.social · 15/07/2025

🎉 Congrats @peterbhase.bsky.social + best wishes for the @schmidtsciences.bsky.social scientist + @stanfordnlp.bsky.social visiting researcher roles! 🙂 Looking forward to your continued exciting research contributions in AI safety & interpretability, and your new grant-making contributions 🔥

020

Reposted by Mohit Bansal

Peter Hase @peterbhase.bsky.social · 14/07/2025

Overdue job update — I am now: - A Visiting Scientist at @schmidtsciences.bsky.social, supporting AI safety & interpretability - A Visiting Researcher at Stanford NLP Group, working with @cgpotts.bsky.social So grateful to keep working in this fascinating area—and to start supporting others too :)

351

Reposted by Mohit Bansal

AthNLP - Athens Natural Language Processing Summer School @athnlp.bsky.social · 27/06/2025

📢 Speakers Announcement #AthNLP2025 We’re thrilled to welcome a new lineup of brilliant minds to the ATHNLP stage!🚀 Meet our new NLP speakers shaping the future. 📅 Dates: 4-10 September 2025 athnlp.github.io/2025/speaker... #ATHNLP #NLP #AI #MachineLearning #Athens

171

Reposted by Mohit Bansal

Andreas Vlachos @andreasvlachos.bsky.social · 06/06/2025

Looking forward to this year's edition! With great speakers: Ryan McDonald Yulan He @vn-ml.bsky.social @antonisa.bsky.social Raquel Fernandez @annarogers.bsky.social Preslav Nakov @mohitbansal.bsky.social @eunsol.bsky.social Marie-Catherine de Marnefffe !

063

Mohit Bansal @mohitbansal.bsky.social · 21/05/2025

the journey has been a great pleasure for me too @jmincho.bsky.social 🤗, and looking forward to your exciting work in the future! 💙

010

Mohit Bansal @mohitbansal.bsky.social · 20/05/2025

🔥 Huge CONGRATS to Jaemin + @jhucompsci.bsky.social! 🎉 Very proud of his journey as an amazing researcher (covering groundbreaking, foundational research on important aspects of multimodality+other areas) & as an awesome, selfless mentor/teamplayer 💙 -- Apply to his group & grab him for gap year!

171

Reposted by Mohit Bansal

Vaidehi Patil @vaidehipatil.bsky.social · 07/05/2025

🚨 Introducing our @tmlrorg.bsky.social paper “Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation” We present UnLOK-VQA, a benchmark to evaluate unlearning in vision-and-language models, where both images and text may encode sensitive or private information.

1128

Mohit Bansal @mohitbansal.bsky.social · 06/05/2025

aww thanks for the kind words @esteng.bsky.social -- completely my pleasure 🤗💙

010

Mohit Bansal @mohitbansal.bsky.social · 05/05/2025

🔥 BIG CONGRATS to Elias (and UT Austin)! Really proud of you -- it has been a complete pleasure to work with Elias and see him grow into a strong PI on *all* axes 🤗 Make sure to apply for your PhD with him -- he is an amazing advisor and person! 💙

1124

Reposted by Mohit Bansal

Elias Stengel-Eskin @esteng.bsky.social · 30/04/2025

🌵 I'm going to be presenting PBT at #NAACL2025 today at 2PM! Come by poster session 2 if you want to hear about: -- balancing positive and negative persuasion -- improving LLM teamwork/debate -- training models on simulated dialogues With @mohitbansal.bsky.social and @peterbhase.bsky.social

0103

Reposted by Mohit Bansal

Justin Chih-Yao Chen @cyjustinchen.bsky.social · 30/04/2025

I will be presenting ✨Reverse Thinking Makes LLMs Stronger Reasoners✨at #NAACL2025! In this work, we show - Improvements across 12 datasets - Outperforms SFT with 10x more data - Strong generalization to OOD datasets 📅4/30 2:00-3:30 Hall 3 Let's chat about LLM reasoning and its future directions!

153

Reposted by Mohit Bansal

Elias Stengel-Eskin @esteng.bsky.social · 29/04/2025

✈️ Heading to #NAACL2025 to present 3 main conf. papers, covering training LLMs to balance accepting and rejecting persuasion, multi-agent refinement for more faithful generation, and adaptively addressing varying knowledge conflict. Reach out if you want to chat!

1155

Reposted by Mohit Bansal

Elias Stengel-Eskin @esteng.bsky.social · 24/04/2025

Check out 🚨CAPTURe🚨 -- a new benchmark testing spatial reasoning by making VLMs count objects under occlusion. SOTA VLMs (GPT-4o, Qwen2-VL, Intern-VL2) have high error rates on CAPTURe (but humans have low error ✅) and models struggle to reason about occluded objects. arxiv.org/abs/2504.15485 🧵👇

164

Mohit Bansal @mohitbansal.bsky.social · 21/04/2025

PS. and here are the presentation time slots/details of all the @iclr-conf.bsky.social and @tmlrorg.bsky.social papers 👇

020

Mohit Bansal @mohitbansal.bsky.social · 21/04/2025

In Singapore for #ICLR2025 this week to present papers + keynotes 👇, and looking forward to seeing everyone -- happy to chat about research, or faculty+postdoc+phd positions, or simply hanging out (feel free to ping)! 🙂 Also meet our awesome students/postdocs/collaborators presenting their work.

1194

Reposted by Mohit Bansal

Archiki Prasad @archiki.bsky.social · 18/04/2025

🚨Real-world retrieval is messy: queries are ambiguous or docs conflict & have incorrect/irrelevant info. How can we jointly address these problems? ➡️RAMDocs: challenging dataset w/ ambiguity, misinformation & noise ➡️MADAM-RAG: multi-agent framework, debates & aggregates evidence across sources 🧵⬇️

3167

Reposted by Mohit Bansal

hanqix.bsky.social @hanqix.bsky.social · 16/04/2025

Excited to share my first paper as first author: "Task-Circuit Quantization" 🎉 I led this work to explore how interpretability insights can drive smarter model compression. Big thank you to @esteng.bsky.social, Yi-Lin Sung, and @mohitbansal.bsky.social for mentorship and collaboration. More to come

052

Reposted by Mohit Bansal

Zaid Khan @codezakh.bsky.social · 15/04/2025

What if we could transform advanced math problems into abstract programs that can generate endless, verifiable problem variants? Presenting EFAGen, which automatically transforms static advanced math problems into their corresponding executable functional abstractions (EFAs). 🧵👇

1165

Reposted by Mohit Bansal

Elias Stengel-Eskin @esteng.bsky.social · 12/04/2025

🚨Announcing TaCQ 🚨 a new mixed-precision quantization method that identifies critical weights to preserve. We integrate key ideas from circuit discovery, model editing, and input attribution to improve low-bit quant., w/ 96% 16-bit acc. at 3.1 avg bits (~6x compression) 📃 arxiv.org/abs/2504.07389

1157

Reposted by Mohit Bansal

Vaidehi Patil @vaidehipatil.bsky.social · 02/04/2025

🚨Exciting @icmlconf.bsky.social workshop alert 🚨 We’re thrilled to announce the #ICML2025 Workshop on Machine Unlearning for Generative AI (MUGen)! ⚡Join us in Vancouver this July to dive into cutting-edge research on unlearning in generative AI with top speakers and panelists! ⚡

141

Mohit Bansal @mohitbansal.bsky.social · 27/03/2025

🎉🎉 Big congrats to @archiki.bsky.social on being awarded the @Apple AI/ML PhD Fellowship, for her extensive contributions in evaluating+improving reasoning in language/reward models and their applications to new domains (ReCEval, RepARe, System-1.x, ADaPT, ReGAL, ScPO, UTGen, GrIPS)! #ProudAdvisor

131

Reposted by Mohit Bansal

Rada Mihalcea @radamihalcea.bsky.social · 12/03/2025

We had a blast at the NLP@Michigan Day! Many thanks to our outstanding keynote speakers Parisa Kordjamshidi & @mohitbansal.bsky.social, our fantastic organizers Muhammad Khalifa & Siyang Liu, and all the engaged participants from across campus and beyond. So much positive NLP energy! 💛💙

071

Reposted by Mohit Bansal

Elias Stengel-Eskin @esteng.bsky.social · 25/02/2025

🚨UPCORE is our new method for balancing unlearning/forgetting with maintaining model performance. Best part is it works by selecting a coreset from the data rather than changing the model, so it is compatible with any unlearning method, with consistent gains for 3 methods + 2 tasks!

042

Reposted by Mohit Bansal

Vaidehi Patil @vaidehipatil.bsky.social · 25/02/2025

🚨 Introducing UPCORE, to balance deleting info from LLMs with keeping their other capabilities intact. UPCORE selects a coreset of forget data, leading to a better trade-off across 2 datasets and 3 unlearning methods. 🧵👇

2115

Mohit Bansal @mohitbansal.bsky.social · 05/02/2025

Next, UTDebug enlarges UTGen’s sweet-spot with two key innovations: 1⃣ Boosts unit test accuracy through test-time scaling. 2⃣ Validates code by accepting edits only if the pass rate improves—and backtracking otherwise. 4/4

030

Mohit Bansal @mohitbansal.bsky.social · 05/02/2025

Key finding --> trade-off in UT generation: if UTs made too easy, they only catch trivial errors/don’t raise any errors; but if UTs made too hard, then the generator can’t predict the output! UTGen finds the sweet-spot between these two where the model generates tests that help in debugging. 3/4

130

Mohit Bansal @mohitbansal.bsky.social · 05/02/2025

Generating good unit tests is challenging (even for humans) and requires: 1⃣ Error uncovering → Unit tests must target edge cases to catch subtle bugs. 2⃣ Code understanding → Knowing the correct output corresponding to a UT input. 2/4

130

Mohit Bansal @mohitbansal.bsky.social · 05/02/2025

🚨 Check out "UTGen & UTDebug" for learning to automatically generate unit tests (i.e., discovering inputs which break your code) and then applying them to debug code with LLMs, with strong gains (>12% pass@1) across multiple models/datasets! (see details in 🧵👇) 1/4

174

Reposted by Mohit Bansal

Elias Stengel-Eskin @esteng.bsky.social · 04/02/2025

🚨 Excited to announce UTGen and UTDebug, where we first learn to generate unit tests and then apply them to debugging generated code with LLMs, with strong gains (+12% pass@1) on LLM-based debugging across multiple models/datasets via inf.-time scaling and cross-validation+backtracking! 🧵👇

085

Reposted by Mohit Bansal

Archiki Prasad @archiki.bsky.social · 04/02/2025

🚨 Excited to share: "Learning to Generate Unit Tests for Automated Debugging" 🚨 which introduces ✨UTGen and UTDebug✨ for teaching LLMs to generate unit tests (UTs) and debugging code from generated tests. UTGen+UTDebug yields large gains in debugging (+12% pass@1) & addresses 3 key questions: 🧵👇

1187

Mohit Bansal @mohitbansal.bsky.social · 27/01/2025

-- positional bias of faithfulness for long-form summarization -- improving generation faithfulness via multi-agent collaboration (PS. Also a big thanks to ACs+reviewers for their effort!)

021

Mohit Bansal @mohitbansal.bsky.social · 27/01/2025

-- safe T2I/T2V gener -- generative infinite games -- procedural+predictive video repres learning -- bootstrapping VLN via self-refining data flywheel -- automated preference data synthesis -- diagnosing cultural bias of VLMs -- adaptive decoding to balance contextual+parametric knowl conflicts 🧵

131

Mohit Bansal @mohitbansal.bsky.social · 27/01/2025

-- adapting diverse ctrls to any diffusion model -- balancing fast+slow sys-1.x planning -- balancing agents' persuasion resistance+acceptance -- multimodal compositional+modular video reasoning -- reverse thinking for stronger LLM reasoning -- lifelong multimodal instruc tuning via dyn data selec 🧵

111

Mohit Bansal @mohitbansal.bsky.social · 27/01/2025

🎉 Congrats to the awesome students, postdocs, & collaborators for this exciting batch of #ICLR2025 and #NAACL2025 accepted papers (FYI some are on the academic/industry job market and a great catch 🙂), on diverse, important topics such as: -- adaptive data generation environments/policies ... 🧵

1189

Reposted by Mohit Bansal

Elias Stengel-Eskin @esteng.bsky.social · 23/01/2025

🎉Very excited that our work on Persuasion-Balanced Training has been accepted to #NAACL2025! We introduce a multi-agent tree-based method for teaching models to balance: 1️⃣ Accepting persuasion when it helps 2️⃣ Resisting persuasion when it hurts (e.g. misinformation) arxiv.org/abs/2410.14596 🧵 1/4

1218

Mohit Bansal @mohitbansal.bsky.social · 21/01/2025

Thanks @AAAI for selecting me as a #AAAI Fellow! Very humbled+excited to be a part of the respected cohort of this+past years' fellows (& congrats everyone)! 🙏 100% credit goes to my amazing past/current students+postdocs+collab for their work (& thanks to mentors+family)!💙 aaai.org/about-aaai/a...

0175

Mohit Bansal @mohitbansal.bsky.social · 16/01/2025

thanks for the kind words @esteng.bsky.social, all the credit goes to y'all awesome postdocs+students, and making it such a fun journey 💙

040

Mohit Bansal @mohitbansal.bsky.social · 15/01/2025

Deeply honored & humbled to have received the Presidential #PECASE Award by the @WhiteHouse and @POTUS office! 🙏 Most importantly, very grateful to my amazing mentors, students, postdocs, collaborators, and friends+family for making this possible, and for making the journey worthwhile + beautiful 💙

5438

Reposted by Mohit Bansal

Archiki Prasad @archiki.bsky.social · 28/12/2024

✨ Collaborating with our amazing postdocs in our lab over the past year has been a great learning experience, with lots of fun + exciting research in LLM agents, reasoning, & multimodality! Check out the new postdoc openings and become a part of the vibrant research @unccs.bsky.social !⬇️

081

Reposted by Mohit Bansal

Jaemin Cho @jmincho.bsky.social · 26/12/2024

Check out our postdoc openings at UNC-CH! In addition to the valuable research opportunities, please also note that Chapel Hill and the research triangle are great places to live, with nice weather, food, and people! I truly have enjoyed living here 😊

071

Reposted by Mohit Bansal

Elias Stengel-Eskin @esteng.bsky.social · 26/12/2024

Apply soon to - work with tons of extremely talented and strong students and get hands-on experience mentoring - benefit from expert mentorship - be in a great department and live in an area with high quality of life and more! Feel free to ping me if you want to hear more from a current postdoc!

092

Mohit Bansal @mohitbansal.bsky.social · 23/12/2024

Links: cs.unc.edu/~mbansal/pos... unc.peopleadmin.com/postings/272... cs.unc.edu/~mbansal/ murgelab.cs.unc.edu nlp.cs.unc.edu

cs.unc.edu

010

Mohit Bansal @mohitbansal.bsky.social · 23/12/2024

** -- multimodal generative models -- grounded+embodied semantics -- LLM reasoning+planning agents -- agent calibration+collaboration -- faithfulness+hallucination -- interpretability+model editing -- efficiency+model merging -- generalizability/OOD, etc. (details of our pubs/talks/lab in links 👇)

110

Mohit Bansal @mohitbansal.bsky.social · 23/12/2024

🚨 We have postdoc openings at UNC 🙂 Exciting+diverse NLP/CV/ML topics**, freedom to create research agenda, competitive funding, very strong students, mentorship for grant writing, collabs w/ many faculty+universities+companies, superb quality of life/weather. Please apply + help spread the word 🙏

13715