Some personal updates: - I've completed my PhD at @unccs.bsky.social! 🎓 - Starting Fall 2026, I'll be joining the CS dept. at Johns Hopkins University @jhucompsci.bsky.social as an Assistant Professor 💙 - Currently exploring options for my gap year (Aug 2025 - Jul 2026), so feel free to reach out! 🔎

📢 The SoLaR workshop will be collocated with COLM! @colmweb.org SoLaR is a collaborative forum for researchers working on responsible development, deployment and use of language models. We welcome both technical and sociotechnical submissions, deadline July 5th!

🚨 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.

🔥 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! 💙

Elias Stengel-Eskin@esteng.bsky.social · last yr.

Extremely excited to announce that I will be joining @utaustin.bsky.social Computer Science in August 2025 as an Assistant Professor! 🎉

Extremely excited to announce that I will be joining @utaustin.bsky.social Computer Science in August 2025 as an Assistant Professor! 🎉

🌵 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

Elias Stengel-Eskin@esteng.bsky.social · 2y ago

🎉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

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!

Justin Chih-Yao Chen@cyjustinchen.bsky.social · 2y ago

🚨 Reverse Thinking Makes LLMs Stronger Reasoners We can often reason from a problem to a solution and also in reverse to enhance our overall reasoning. RevThink shows that LLMs can also benefit from reverse thinking 👉 13.53% gains + sample efficiency + strong generalization (on 4 OOD datasets)!

✈️ 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!

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 🧵👇

🚨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 🧵⬇️

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

Elias Stengel-Eskin@esteng.bsky.social · last yr.

🚨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

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). 🧵👇

🚨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

🥳🥳 Honored and grateful to be awarded the 2025 Apple Scholars in AI/ML PhD Fellowship! ✨ Huge shoutout to my advisor @mohitbansal.bsky.social, & many thanks to my lab mates @unccs.bsky.social , past collaborators + internship advisors for their support ☺️🙏 machinelearning.apple.com/updates/appl...

Introducing VEGGIE 🥦—a unified, end-to-end, and versatile instructional video generative model. VEGGIE supports 8 skills, from object addition/removal/changing, and stylization to concept grounding/reasoning. It exceeds SoTA and shows 0-shot multimodal instructional & in-context video editing.

🚨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!

Vaidehi Patil@vaidehipatil.bsky.social · last yr.

🚨 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. 🧵👇

🚨 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. 🧵👇

🚨 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

Archiki Prasad@archiki.bsky.social · last yr.

🚨 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: 🧵👇

🚨 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! 🧵👇

Archiki Prasad@archiki.bsky.social · last yr.

🚨 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: 🧵👇

🚨 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: 🧵👇

🎉 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 ... 🧵

🎉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

🎉Congratulations to Prof. @mohitbansal.bsky.social on being named a 2025 @RealAAAI Fellow for "significant contributions to multimodal AI foundations & faithful language generation and summarization." 👏 16 Fellows chosen worldwide by cmte. of 9 past fellows & ex-president: aaai.org/about-aaai/a...

Congrats @mohitbansal.bsky.social for being selected to be part of this prestigious #AAAI Fellows group! Very well-deserved recognition of long-term contributions 🎉🎉

Mohit Bansal@mohitbansal.bsky.social · 2y ago

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...

Congrats on this huge (and well-deserved) accomplishment @mohitbansal.bsky.social!

Mohit Bansal@mohitbansal.bsky.social · 2y ago

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 💙

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 💙

UNC-Chapel Hill Computer Science@unccs.bsky.social · 2y ago

🎉 Congratulations to Prof. @mohitbansal.bsky.social for receiving the Presidential #PECASE Award by @WhiteHouse, which is the highest honor bestowed by US govt. on outstanding scientists/engineers who show exceptional potential for leadership early in their careers! whitehouse.gov/ostp/news-up...

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!

Mohit Bansal@mohitbansal.bsky.social · 2y ago

🚨 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 🙏

🚨 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 🙏

✈️ I've landed in Vancouver for #NeurIPS2024 11/12: LACIE, a pragmatic speaker-listener method for training LLMs to express calibrated confidence: arxiv.org/abs/2405.21028 12/12: GTBench, a benchmark for game-theoretic abilities in LLMs: arxiv.org/abs/2402.12348 P.s. I'm on the faculty market👇

Elias Stengel-Eskin@esteng.bsky.social · 2y ago

🚨 I am on the faculty job market this year 🚨 I will be presenting at #NeurIPS2024 and am happy to chat in-person or digitally! I work on developing AI agents that can collaborate and communicate robustly with us and each other. More at: esteng.github.io and in thread below 🧵👇

Working with Elias has been an absolute pleasure! His passion for research and dedication to mentoring are inspiring. Can’t wait to see all the amazing work his lab will do as he becomes a professor! ✨

Elias Stengel-Eskin@esteng.bsky.social · 2y ago

🚨 I am on the faculty job market this year 🚨 I will be presenting at #NeurIPS2024 and am happy to chat in-person or digitally! I work on developing AI agents that can collaborate and communicate robustly with us and each other. More at: esteng.github.io and in thread below 🧵👇