New from Meta Flex3D Flex3D is a two-stage pipeline that generates high-quality 3D assets from single images or text prompts.

Introducing 🦘🐲DreamBeast🦙🐉: a method for generating fantastical 3D animals composed of distinct parts! All codes are available. #3DV2025!

I keep saying that naming your research after OpenAI products is cringe. AutoGPT? Mini-Omni? LLaVA-o1? OpenSORA? You haven't seen the weights, you have little clue about the design, you're just latching onto the brand hype train. Have some dignity. At least go after Anthropic.

Don’t miss it!

Excited to co-organize the #ICLR2025 2nd Workshop on Foundation Models in the Wild. Big thanks to an amazing team and speaker lineup! We call for non-archival papers: 2-4 pages (tiny), or 6-9 pages (long). 📃Webpage: fm-wild-community.github.io 😀See you in Singapore!

📢 Announcing our new work "APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding" ICLR 2026 🚀 Enabling the efficient combination of multiple contexts with negligible prefilling cost 💅 Re-using the context window of LLMs to accommodate more and

😀We're delighted to announce that the review stage of our 2nd FM-Wild Workshop at ICLR has successfully concluded. We extend our sincere gratitude to all authors and reviewers for their valuable contributions. 👉The accepted papers are now available at: openreview.net/group?id=ICLR.…

Check this amazing work if interested in 3D reconstruction and geometry. One thought: co-scaling data +architecture (usually self-attn) is almost working in all AI tasks or ill-posed problems. It’s also for 3D. Since 3D data is limited, combine and co-train on multiple tasks!

We will be presenting "APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding", a novel encoding method that enables: 🚀Pre-caching Contexts for Fast Inference 🐍Re-using Positions for Long Context Our poster session is located in Hall 3 and Hall 2B,

🤩 It's happening today! Join us at the 2nd Workshop on Foundation Models in the Wild — Hall 4, #6, Singapore EXPO! 🔥 10 amazing invited talks 🔥 12 exciting oral presentations 🔥 Cutting-edge ideas and lively discussions 🚀 Don't miss it — come say hi and explore the future

A new framework for native parallel generation in LLMs! Natively parallel generation in LLMs, backed by a full-stack release (model, engine, data, and more).

Cool video generation project that leverages an explicit memory mechanism! Very exciting to see this as a big fan of memory in AI!