🔥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

Our work on beating scaling laws via deliberate practice, a modified synthetic data-generation scheme wherein harder / more entropic examples are favored, has been accepted at ICML Conference #ICML2025.

"Compositional Risk Minimization" Tackling unseen attribute combinations with additive energy models at #ICML2025. 💡 Check out the excellent summary by Divyat Samadhiya

1/ Excited to share that I’m taking on the role of leading Fundamental AI Research (FAIR) at Meta. Huge thanks to Joelle for everything. Look forward to working closely again with Yann & team.

The review quality in TMLR is better because: 1. The authors suggest the AE. This means that the AE is more likely to be the right fit for the paper. 2. The AE selects the best reviewers for the paper who may or may not be in the reviewer pool. ...

If you submitted to ICML and TMLR as an author, where did you get higher review quality (grounded, fair, and helped improve your paper)? 𝐏𝐥𝐞𝐚𝐬𝐞 𝐝𝐞𝐜𝐨𝐮𝐩𝐥𝐞 𝐭𝐡𝐞 𝐮𝐥𝐭𝐢𝐦𝐚𝐭𝐞 𝐟𝐚𝐢𝐭𝐡 𝐨𝐟 𝐩𝐚𝐩𝐞𝐫 𝐟𝐫𝐨𝐦 𝐲𝐨𝐮𝐫 𝐣𝐮𝐝𝐠𝐞𝐦𝐞𝐧𝐭 𝐨𝐟 𝐪𝐮𝐚𝐥𝐢𝐭𝐲.

A great collab with former labmates Anthony GX-Chen & Dongyan! Interesting cognitive limitation in LMs: strong disjunctive bias leads to poor performance on conjunctive causal inference tasks. Mirrors adult human biases—possibly a byproduct of training data priors.

Instead of modelling the velocity at each time step t in the process, model the mean velocity across any time interval (r, t). Not the first work to try this, but using the gradient of the mean velocity to define the target is an interesting approach that I haven't seen before.

A new post with intuitions behind continuous-time Markov chains, a building block of diffusion language models, like Inception Labs 's Mercury and Gemini Diffusion. Touches on different perspectives on Markov chains, connections to point processes + more. inference.vc/discrete-diffu…

The deadline is postponed to June 2!

Today marks a big milestone for me. I'm launching LawZero - LoiZéro, a nonprofit focusing on a new safe-by-design approach to AI that could both accelerate scientific discovery and provide a safeguard against the dangers of agentic AI.

Less than one week away from the 2nd Workshop on Responsible Generative AI #CVPR2025! It’ll be on Thursday afternoon, and we’ve got a great set of presenters and participants! Check out the program & accepted work: sites.google.com/view/cvpr-resp… See you in Nashville! 🎶 #cvpr2025

Join us at #CVPR2025 Demographic Diversity in Computer Vision workshop tomorrow! 📅 Wednesday, June 11, 9am-6pm 📍 room 213 (main session) + Hall D (poster sessions), the Music City Center We have an amazing lineup of speakers and panelists! Can't wait to meet you all there :)

Join us Thursday afternoon in Room 106A for a great set of speakers, panelists, and contributed works focused on Responsible Generative AI #CVPR2025!! #CVPR2025

🚨 Applications are now open for WiML Symposium @ ICML 2025! 📍 Vancouver, Canada 📅 July 16, 2025 🎓 Present a poster 🙋 Volunteer ☕ Connect & network at talks, panels, and socials 📌 Deadline: June 25 (AoE) 📝 Apply now: tinyurl.com/3dbesr9t #WiML #ICML2025

In war, both sides lose. That we don’t learn this is the greatest tragedy.

#SG2RL returns to #ICCV2025 2025 at Honolulu, Hawai'i 🌴☀️ We call for full papers and extended abstracts on all topics around graphs and scene graphs. Deadline: 26 June (23:59PT) Website: sites.google.com/view/sg2rl With our amazing co-organizers: Ehsan Adeli Iro Armeni Federico Tombari

Anyone from #iran looking for a phd/postdoc/research internship in statistical learning theory, deep learning theory etc, contact me. Please retweet.

The submission deadline for #SG2RL #ICCV2025 Workshop has been extended to June 30th, 23:59 AoE. Looking forward to receiving your awesome submissions ✌️🤩 #ICCV2025 TUM CAMP Federico Tombari Iro Armeni Ehsan Adeli Munich Center for Machine Learning

This new work generalizes the recent Adjoint Sampling approach from Stochastic Control to Schrodinger Bridges, enabling measure transport between data and unnormalized densities. Achieves SOTA on large-scale energy-driven conformer generation. See thread by Guan-Horng Liu

AI Research Agents are becoming proficient at machine learning tasks, but how can we help them search the space of candidate solutions and codebases? Read our new paper looking at MLE-Bench: arxiv.org/pdf/2507.02554 #LLM #Agents #MLEBench