🚀 #LitLLM demo is live! Try it here: litllm.onrender.com New features: • Export BibTeX citations • Add paper via URL Feedback welcome! GitHub: github.com/litllm/litllm Google Form: forms.gle/8WkULP6eho6zTq… Email: [email protected] Paper: arxiv.org/abs/2412.15249

All good science starts with a good literature review, and AI can help with that :) LitLLM, brought to you by the awesome team at ServiceNow Research.

StarVector poster happening now at CVPR! Come by poster #31 if you want to chat about vector graphics, image-to-code generation, or just say hi!

If you are at #CVPR, make sure to catch Joan Rodriguez and hear about scalable SVG generation straight from the source! 🚩Exhibition Hall D – Poster #31

New updates for olmOCR, our fully open toolkit for transforming documents (PDFs & images) into clean markdown. We released: 1️⃣ New benchmark for fair comparison of OCR engines and APIs 2️⃣ Improved inference that is faster and cheaper to run 3️⃣ Docker image for easy deployment

We open-sourced the codebase of Flextok. Flextok is an image tokenizer that produces flexible-length token sequences and represents image content in a compressed coarse-to-fine way. Like in PCA: the 1st token captures the most compressed representation of the image, the 2nd

📽️Expert-Level Cinematic Understanding in VLM📽️ #ShotBench: benchmark covering 8 core cinematography dimensions #ShotQA: 70k training dataset #ShotVL: 3B and 7B model surpassing GPT-4o on cinematic understanding - Project: vchitect.github.io/ShotBench-proj… - Code: github.com/Vchitect/ShotB…

Physicists and mathematicians really have the wriest humor.

Excited to share our new survey on the reasoning paradigm shift from "Think with Text" to "Think with Image"! 🧠🖼️ Our work offers a roadmap for more powerful & aligned AI. 🚀 📜 Paper: arxiv.org/pdf/2506.23918 ⭐ GitHub (400+🌟): github.com/zhaochen0110/A…

#NewPaperAlert Since we released VLM2Vec, we have received surprising amount of attention from the community. The most common request is to expand VLM2Vec to more modalities like docs, videos, screenshots. Today, we are so excited to introduce VLM2Vec & MMEB-v2! 🚀 We're

Perception-Aware Policy Optimization for Multimodal Reasoning

Oh wow, this VLM benchmark is pure evil, and I love it! "Vision Language Models are Biased" by An Vo, taesiri, Anh Totti Nguyen, etal. Also really good idea to have one-click copy-paste of images and prompts, makes trying it super easy.

Think about this talk a lot. There was a time when people were bullish on "feed all the modalities to the LLM," but it didn't really pan out as I would have expected. The discrete / continuous divide remains a interesting challenge in deep learning.

Check out our work at #EMNLP2025 tomorrow for building cultural post training dataset for Indian languages!

We’ve released VoiceAgentBench to evaluate whether voice assistants can function as true agents (not just ASR/QA). Multilingual (English + Indic), tool-driven workflows & safety. Proud of our team. See thread 👇 #VoiceAgents #AgenticAI #SpeechAI #MultilingualAI

ever been here? open overleaf → write a paragraph → "hmm...this needs a citation" → open 15 different tabs → skim 8 abstracts → find the 1 actually relevant paper → format bibtex → paste it back on overleaf if so, i built a plugin just for you. meet openleaf: → reads