🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

ArXiv arxiv.org/abs/2204.08442: Optical flow estimation by deep equilibrium models. 4 to 6× times less memory than recurrent networks since using cheap inexact gradient makes backward pass almost for free. Improves SOTA methods on Sintel and KITTI with less compute and memory.

Deep Equilibrium Optical Flow Estimation Shaojie Bai, Zhengyang Geng, Yash Savani, Zico Kolter tl;dr: DEQ ("infinite depth aka single layer", arxiv.org/abs/1909.01377) look like natural fit for optical flow estimation. arxiv.org/abs/2204.08442 github.com/locuslab/deq-f…

Stop using RNNs for optical flow!🧐 Introducing DEQ-flow that directly models a **fixed point** flow estimate, is super memory efficient, leads to significant error reduction on KITTI-15, and is compatible with prior modeling efforts (e.g., RAFT). Paper: arxiv.org/abs/2204.08442

Learning to represent objects is a major research direction towards representing the causal structure of the world. In our oral at #iclr2022 workshop on Objects Structure & Causality, we present a new way to conceptualize objects: as stable points of a fixed-point procedure: 👇

I realize this is seemingly an unpopular opinion, but I can't get onboard with these Twitter criticisms of some of the recent #ICML2022 best paper awardees. I've been thinking about this all day. A thread... 🧵 1/N

I just posted our Deep Learning Systems Lecture 6 on Fully Connected Networks, Optimization, and Initialization: youtu.be/CukpVt-1PA4 However, the real topic of interest here is that I used OpenAI's whisper to caption it entirely. A thread 🧵on my experience. 1/N

🆕📜When can **Equilibrium Models** learn from simple examples to handle complex ones? We identify a property — Path Independence — that enables this by letting EMs think for longer on hard examples. (NeurIPS) 📝: [arxiv.org/abs/2211.09961](arxiv.org/abs/2211.09961)

NeurIPS!!! First in-person meeting after 3yrs starting my research. 🥳 Glad to have any chats, neural dynamics, deep equilibrium models (DEQ), symmetries, protein folding/AF2, etc. Will be working on the intersection of DEQ and AF2 and expect to see all the collaboration chances!

Cade Metz at the New York Times just published a piece on a new paper we are releasing today, on adversarial attacks against LLMs. You can read the piece here: nytimes.com/2023/07/27/tec… And find more info and the paper at: llm-attacks.org [1/n]

My core ML team (AI at Meta) is hiring research interns! Our projects span optimization, optimal transport, optimal control, generative modeling, complex systems, and geometry. Please apply here and reach out ([email protected]) if you're interested: metacareers.com/jobs/627997209…

Exciting new work with Evonne, Alexander Richard et al! 🤯 We (generatively) animate photorealistic full-body avatars using conversational audio (of anyone!). Next step, seeing GPT4 + photorealistic avatar [argue with]/[point a finger at]/[mock] you in VR?😏

I feel like a lot of people leverage LLMs suboptimally, especially for long-form interactions that span a whole project. So I wrote a VSCode extension that supports what I think is a better use paradigm. 🧵 1/N Extension: marketplace.visualstudio.com/items?itemName… Code: github.com/locuslab/chatl…

🚀Our latest blog post unveils the power of Consistency Models and introduces Easy Consistency Tuning (ECT), a new way to fine-tune pretrained diffusion models to consistency models. SoTA fast generative models using 1/32 training cost! 🔽 Get ready to speed up your generative

Say hello to GPT-4o, our new flagship model which can reason across audio, vision, and text in real time: openai.com/index/hello-gp… Text and image input rolling out today in API and ChatGPT with voice and video in the coming weeks.

I'm thrilled to share that I will become the next Director of the Machine Learning Department at Carnegie Mellon. MLD is a true gem, a department dedicated entirely to ML. Faculty and past directors have been personal role models in my career. cs.cmu.edu/news/2024/kolt…

I am very excited to start working with GenAI team at Meta, focusing on multimodal LLM agents, joining together with my amazing CMU colleagues Jing Yu Koh Jing Yu Koh and Daniel Fried Daniel Fried!

I'm excited to announce that I am joining the OpenAI Board of Directors. I'm looking forward to sharing my perspectives and expertise on AI safety and robustness to help guide the amazing work being done at OpenAI.

Mitigating racial bias from LLMs is a lot easier than removing it from humans! Can’t believe this happened at the best AI conference NeurIPS Conference We have ethical reviews for authors, but missed it for invited speakers? 😡

Introducing our first set of Llama 4 models! We’ve been hard at work doing a complete re-design of the Llama series. I’m so excited to share it with the world today and mark another major milestone for the Llama herd as we release the *first* open source models in the Llama 4

We’ll be mixing ideas, cocktails and discussions for a night of *neural-networking* at Singapore! Come learn more about Thinking Machines at our happy hour at #iclr2025 😎