🔥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

Just a couple days until Cosyne - stop by [3-083] this Saturday and say hi! Nanda H Krishna Ximeng Mao

styll

My first time CosyneMeeting this week and I couldn't be more excited 😬 Tomorrow, I'll be presenting "Mood as an Extrapolation Engine for Decision-Making", a cognitive science perspective on "Functional Acceleration for Policy Mirror Descent" (arxiv.org/abs/2407.16602) Come chat!

was super fun TAing!

💖

Scenario Dreamer has been accepted at #CVPR2025! Website: …ceton-computational-imaging.github.io/scenario-dream… We train a vectorized latent diffusion model to synthesize high-fidelity driving simulation environments (agents+map). Scenario Dreamer enables fully data-driven closed-loop generative simulation!

If you're at #ICLR come check out our poster on symmetric crystal generation! We're at poster #07.

Are you a leafs fan currently watching game 7? You may be entitled to financial compensation

EUROPA LEAGUE CHAMPIONS!!!

It's very difficult to improve the *exponent* in scaling laws for loss vs compute, especially by changing the optimizer! Our new paper shows that scaling momentum correctly can *provably* improve the scaling exponent on a theoretical model. Empirically, it works on LSTMs too!

Is there a universal strategy to turn any generative model—GANs, VAEs, diffusion models, or flows—into a conditional sampler, or finetuned to optimize a reward function? Yes! Outsourced Diffusion Sampling (ODS) accepted to ICML Conference , does exactly that!

Is AdamW the best inner optimizer for DiLoCo? Does the inner optimizer affect the compressibility of the DiLoCo delta? Excited to introduce MuLoCo: Muon is a practical inner optimizer for DiLoCo! 🧵arxiv.org/abs/2505.23725 1/N

Preprint Alert 🚀 Multi-agent reinforcement learning (MARL) often assumes that agents know when other agents cooperate with them. But for humans, this isn’t always true. Example, plains indigenous groups used to leave resources for others to use at effigies called Manitokan. 1/8

(1/n)🚨You can train a model solving DFT for any geometry almost without training data!🚨 Introducing Self-Refining Training for Amortized Density Functional Theory — a variational framework for learning a DFT solver that predicts the ground-state solutions for different

Excited that our paper "Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimization" was accepted to ICML 2025! We show how Preference Optimization can reduce the impact of noisy concept labels in CBMs. 🧵/9

🚀 Our method, Poutine, was the best-performing entry in the 2025 Waymo Vision-based End-to-End Driving Challenge at #CVPR2025! Our 3 B-parameter VLM Poutine scored 7.99 RFS on the official test set—comfortably ahead of every other entry (see figure).

The worst part about the Panthers winning the Stanley Cup in 6 games is that Leafs fans will believe this makes them the 2nd best team

big fan of this line of work combining diffusion models at inference time - not an expert but the modularity + lack of extra training feels like an intuitive and elegant approach to more controllable generation