📢 Introducing RotBench, which tests whether SoTA MLLMs (e.g., GPT-5, GPT-4o, o3, Gemini-2.5-pro) can identify the rotation of input images (0°, 90°, 180°, and 270°). Even frontier MLLMs struggle at this spatial reasoning task that humans solve with >98% Acc.
➡️ Models struggle…
🎉 Excited to share that TaCQ (Task-Circuit Quantization), our work on knowledge-informed mixed-precision quantization, has been accepted to #COLM2025@COLM_conf!
Happy to see that TaCQ was recognized with high scores and a nice shoutout from the AC – big thanks to @EliasEskin…
🎉 Excited to share that TaCQ (Task-Circuit Quantization), our work on knowledge-informed mixed-precision quantization, has been accepted to #COLM2025@COLM_conf!
Happy to see that TaCQ was recognized with high scores and a nice shoutout from the AC – big thanks to @EliasEskin…
Sharing some personal updates 🥳:
- I've completed my PhD at @unccs! 🎓
- Starting Fall 2026, I'll be joining the Computer Science dept. at Johns Hopkins University (@JHUCompSci) as an Assistant Professor 💙
- Currently exploring options + finalizing the plan for my gap year (Aug…
Extremely excited to announce that I will be joining @UTAustin@UTCompSci in August 2025 as an Assistant Professor! 🎉
I’m looking forward to continuing to develop AI agents that interact/communicate with people, each other, and the multimodal world. I’ll be recruiting PhD…
✈️ 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!
📆 Wed. 04/30…
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 @EliasEskin, @yilin_sung, and @mohitban47 for mentorship and collaboration. More to come!
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 @EliasEskin, @yilin_sung, and @mohitban47 for mentorship and collaboration. More to come!
Check out my first paper 🚨CAPTURe🚨 a new benchmark for testing spatial reasoning in VLMs, asking VLMs to count objects in occluded patterns.
Huge thanks to @EliasEskin@jmin__cho@mohitban47 for mentoring and helping me through the entire project. Excited for what's next!
Check out my first paper 🚨CAPTURe🚨 a new benchmark for testing spatial reasoning in VLMs, asking VLMs to count objects in occluded patterns.
Huge thanks to @EliasEskin@jmin__cho@mohitban47 for mentoring and helping me through the entire project. Excited for what's next!
Check out 🚨CAPTURe🚨 -- a new benchmark and task testing spatial reasoning by making VLMs count objects under occlusion.
Key Takeaways:
➡️ SOTA VLMs (GPT-4o, Qwen2-VL, Intern-VL2) have high error rates on CAPTURe (but humans get very low error ✅) and models struggle to reason…
124 Followers 1K FollowingOfficial journal of China Society of Image and Graphics (CSIG). The jouarnl is published by Springer, sponsored by CSIG. E-ISSN 2731-9008.
10 Followers 115 FollowingJeyam Real Estate, your trusted partner in property excellence, seamlessly blends innovation with reliability.we don't just sell properties; we craft lifestyles
356 Followers 343 FollowingCS PhD student @uncnlp @unc, Research Intern @salesforce | prev research intern @meta and @amazon, work on video reasoning , long videos.
91 Followers 522 FollowingUG Research Assistant at MURGe-Lab w/ @mohitban47, undergrad at @unccs. Interested in LLM Compression, interpretability, and embedded applications
166 Followers 437 FollowingPh.D. Student @unccs @uncnlp, advised by @mohitban47. Prev: @AmazonScience @VinAI_Research. Working on LLM post-training and mechanistic interpretability.
3K Followers 1K FollowingVisiting Scientist at Schmidt Sciences. Visiting Researcher at the Stanford NLP Group
Previously: Anthropic, AI2, Google, Meta, UNC Chapel Hill
11K Followers 63 FollowingOfficial account for the IEEE/CVF International Conference on Computer Vision. #ICCV2025 Honolulu 🇺🇸 Hosted by @natanielruizg @anfurnari @YVinker @CSProfKGD
64K Followers 1K FollowingCo-founder and CTO at @huggingface 🤗. ML/AI for everyone, building products to propel communities fwd. @Stanford + @Polytechnique
1.9M Followers 27K FollowingYes, I can see some risk that your threat to jail Internet company executives for not censorsing aggressively enough could backfire.
356 Followers 343 FollowingCS PhD student @uncnlp @unc, Research Intern @salesforce | prev research intern @meta and @amazon, work on video reasoning , long videos.
950K Followers 764 FollowingProfessor at NYU. Chief AI Scientist at Meta.
Researcher in AI, Machine Learning, Robotics, etc.
ACM Turing Award Laureate.
355K Followers 1K FollowingML/AI researcher & former stats professor turned LLM research engineer. Author of "Build a Large Language Model From Scratch" (https://t.co/O8LAAMRzzW).
264K Followers 670 FollowingBuilding with AI agents @dair_ai • Prev: Meta AI, Galactica LLM, Elastic, PaperswithCode, PhD • I share insights on how to build with AI Agents ↓
1.4M Followers 1K FollowingBuilding @EurekaLabsAI. Previously Director of AI @ Tesla, founding team @ OpenAI, CS231n/PhD @ Stanford. I like to train large deep neural nets.
166 Followers 437 FollowingPh.D. Student @unccs @uncnlp, advised by @mohitban47. Prev: @AmazonScience @VinAI_Research. Working on LLM post-training and mechanistic interpretability.
3K Followers 435 FollowingDepartment of Computer Science - University of North Carolina at Chapel Hill
Choose to #GIVE today - learn more here: https://t.co/cLdenfM5G5
3K Followers 416 FollowingAI Group (NLP/CV/ML etc) at @UNCCS @UNC
Faculty: @mohitban47+@gberta227+@snigdhac25+@shsriva+@tianlongchen4+@huaxiuyaoml+@dingmyu+@zhun_deng +@SenguptRoni et al