Mahtab Bigverdi
@MahtabBg
Computer Science PhD student @uwcse | Prev-Research intern @Genentech
I'm exited to announce that our work (AURORA) got accepted into #CVPR2025🎉! Special thanks to my coauthors: @ch1m1m0ry0, @cydhsieh, @ethnlshn, @Dongping0612, Linda Shapiro and @RanjayKrishna, This work wouldn’t have been possible without them! See you all in Nashville 🎸!
Introducing AURORA 🌟: Our new training framework to enhance multimodal language models with Perception Tokens; a game-changer for tasks requiring deep visual reasoning like relative depth estimation and object counting. Let’s take a closer look at how it works.🧵[1/8]
If you feel the need you make the "I'm not stereotyping" disclaimer, maybe you should reconsider what you're saying She could have saved a lot of words by deleting "Chinese" and "NOTE: I am not a racist but blah blah blah blah"
Using racial labels to describe misconduct is harmful and inappropriate. @NeurIPSConf must not condone speech that targets specific ethnic groups. We urge Rosalind Picard @MIT @medialab to retract and apologize for her statement. Btw, most Rosalinds I know are honest and morally…
Post-tuning your LLM but can't afford A/B testing? This paper dives into how to use historical data without falling for spurious correlations. Smart causal corrections (like DECONFOUNDLM) can make all the difference. 👉[arxiv.org/pdf/2506.00152]
Can we align language models using observational data instead of costly experiments like A/B tests? In my latest research, we find that historical observational data *does* carry useful signals, but without causal care, models can learn the wrong things. Thread 🧵
Working on multimodal agents, foundation models, or AI systems that see👀, listen👂, and reason🧠? Submit to our ICCV 2025 Workshop on Multimodal Reasoning for Agents (MMRAgI). Explore the next frontier in LLM+vision+audio AI. 📅 Deadline: June 24 See you in Honolulu!🌴🌊
🚨 We’re thrilled to announce our ICCV 2025 Workshop: MMRAgI – Multi-Modal Reasoning for Agentic Intelligence! 🚨 🌐 Homepage: agent-intelligence.github.io/agent-intellig… 📥 Submit: openreview.net/group?id=thecv… 🗓️ Submission Deadline (Proceeding Track): June 24th 2025 23:59 AoE 🗓️ Submission Deadline…
I’m tired of the lies, the silence, and the way we’re told who to grieve for and who to ignore. Tehran is being bombed, and innocent people are dying. Children, families, everyday people; terrified, running for their lives. And yet, the world stays silent. Hiding behind the…
تصاویر دریافتی با شرح: "شهرک شهید باقری، بالای دریاچه. اینجا مجتمع تفریحی سپاهه به نام دوکوهه" #iran #israel
امیدوارم که خانواده هاتون سالم باشن، چشمهامون اشک آلوده برای ایران، برای کودکان و ادم های بیگناه که به خاک و خون کشیده شدن. برای همه دانشجویان ایرانی در زمینه هوش مصنوعی و بیوانفرماتیک و زیست شناسی محاسباتی که دچار مشکل شدن برای ادامه تحصیل یا تحقیقاتشون، به من ایمیل بزننین برای…
Excited to share our work Aurora at #CVPR2025! 🗓️ Tomorrow ( Friday June 13th) 🖼️ Poster #349 📍 Exhibit Hall D 🕥 10:30 AM – 12:30 PM Come by to chat and see what we’ve been working on! ✨
Introducing AURORA 🌟: Our new training framework to enhance multimodal language models with Perception Tokens; a game-changer for tasks requiring deep visual reasoning like relative depth estimation and object counting. Let’s take a closer look at how it works.🧵[1/8]
Calling all #CVPR2025 attendees! Join us at the SynData4CV Workshop at @CVPR (Jun 11 full day at Grand C2, starting at 9am) to learn more about recent advancements in synthetic data for CV! Explore more: syndata4cv.github.io
The 2nd Synthetic Data for Computer Vision workshop at @CVPR! We had a wonderful time last year, and we want to build on that success by fostering fresh insights into synthetic data for CV. Join us! We welcome submissions! Please consider submitting your work! (deadline: March…
🚨 We’re thrilled to announce our ICCV 2025 Workshop: MMRAgI – Multi-Modal Reasoning for Agentic Intelligence! 🚨 🌐 Homepage: agent-intelligence.github.io/agent-intellig… 📥 Submit: openreview.net/group?id=thecv… 🗓️ Submission Deadline (Proceeding Track): June 24th 2025 23:59 AoE 🗓️ Submission Deadline…
The 2nd Synthetic Data for Computer Vision workshop at @CVPR! We had a wonderful time last year, and we want to build on that success by fostering fresh insights into synthetic data for CV. Join us! We welcome submissions! Please consider submitting your work! (deadline: March…
🤩🤩
Thank you, @TobPolicy organizers! It was a pleasure presenting today. I truly appreciate the opportunity, and I enjoyed the great exchange of ideas during the discussion. Thank you, @jim_flynn9, for your insightful comments!
LLM agents are cool, but how good are they on planning & executing multi-step multi-modal tasks? Our benchmark m&ms enables systematic & finegrained evals of LLMs on multi-modal task planning & tool use. Check out our poster at #ECCV24 🤌 🕙 Oct 1, 10:30-12 📍Exhibition Area 179