We're kicking off the awards session at #EMNLP2024 by announcing our (many) **Outstanding Reviewers**!

🤔 Why are VLMs (even GPT-4V) worse at image classification than CLIP, despite using CLIP as their vision encoder? Presenting VLMClassifier at #NeurIPS2024: ⏰ Dec 11 (Wed), 11:00-14:00 📍 East Hall #3710 Key findings: 1️⃣ VLMs dramatically underperform CLIP (>20% gap) 2️⃣ After

🔍 Vision language models are getting better - but how do we evaluate them reliably? Introducing AutoConverter: transforming open-ended VQA into challenging multiple-choice questions! Key findings: 1️⃣ Current open-ended VQA eval methods are flawed: rule-based metrics correlate

Biomedical datasets are often confined to specific domains, missing valuable insights from adjacent fields. To bridge this gap, we present BIOMEDICA: an open-source framework to extract and serialize PMC-OA. 📄Paper: lnkd.in/dUUgA6rR 🌐Website: lnkd.in/dnqZZW4M

🚀 Introducing Temporal Preference Optimization (TPO) – a video-centric post-training framework that enhances temporal grounding in long-form videos for Video-LMMs! 🎥✨ 🔍 Key Highlights: ✅ Self-improvement via preference learning – Models learn to differentiate well-grounded

🚀 Annnouncing XAI4CV Workshop at #CVPR2025! We look forward to gathering experts to explore challenges and opportunities in XAI for CV, advance new ideas, and push the field to its limits! Join us in Nashville, TN, this June. 🔗 xai4cv.github.io #CVPR2025 #XAI #CVPR2026

Submit your latest work (papers, demos) in #XAI to the 4th Explainable AI for Computer Vision (XAI4CV) Workshop at #CVPR2025! The deadline for the Proceedings Track is March 10, 2025 Details: xai4cv.github.io/workshop_cvpr25 Submission Site: cmt3.research.microsoft.com/XAI4CV2025 #CVPR2025 Explainable AI

🚨Large video-language models LLaVA-Video can do single-video tasks. But can they compare videos? Imagine you’re learning a sports skill like kicking: can an AI tell how your kick differs from an expert video? 🚀 Introducing "Video Action Differencing" (VidDiff), ICLR 2025 🧵

Excited to announce that AutoConverter has been accepted to #CVPR2025 and VMCBench is now supported by both VLMEvalKit and lmms-eval! 🎉 Try our tools: ▪️ AutoConverter demo: yuhui-zh15.github.io/AutoConverter-… ▪️ VMCBench: huggingface.co/datasets/suyc2… (supported by VLMEvalKit and lmms-eval)

🚨 Excited to co-organize our #CVPR2025 workshop on "Multimodal Foundation Models for Biomedicine: Challenges and Opportunities" — where vision, language, and health intersect! We’re bringing together experts from #CV, #NLP, and #healthcare to explore: 🧠 Technical challenges (e.g.

🚨 New benchmark drop: EquiBench 🚨 We introduce equivalence checking as a rigorous test of LLMs’ code reasoning ability, featuring 4 languages, 6 categories, and 2,400 program pairs. Top models still struggle with this task. 🔗 Website: anjiang-wei.github.io/EquiBench-Webs… 📝 Preprint:

Three papers being presented by my amazing collaborators at #ICLR2025! 🌟 (sadly I can't make it) 1. Mechanistic Interpretability Meets Vision Language Models: Insights and Limitations 🔍 A deep dive into mechanistic interpretation techniques for VLMs & future

I'm at #ICLR2025 presenting "Video Action Differencing". Keen to chat with anyone interested in MLLMs - both for general data & for scientific reasoning

📢 The First Workshop on Multimodal Foundation Models for Biomedicine (MMFM-BIOMED) at #CVPR2025 is still accepting submissions until May 7, 11:59 PM PT! Join speakers from Stanford, Google, MIT & more exploring the intersection of #CV, #NLP & #healthcare. Submit your 4-page

📢 Announcing our data-centric workshop at ICML 2025 on unifying data curation frameworks across domains! 📅 Deadline: May 24, AoE 🔗 Website: dataworldicml2025.github.io We have an amazing lineup of speakers + panelists from various institutions and application areas.

📢 Really excited to host the Data Curation for Vision Language Reasoning Challenge (DCVLR) @ NeurIPS 2025 and to include VMCBench as one of the evaluation sets! We’re looking forward to seeing the top solutions (with prize money!) — huge thanks to Benjamin Feuer and the team for

Join us on Saturday at West 208-209 for our ICML Conference workshop on data-centric AI! ✨ Looking forward to great discussions and meeting both old and new friends!