We’re presenting our work on concept guidance today at 13:30’s ICML poster session (# 706). Come by and say hi! #ICML #ICML2024

come to the poster session at 12pm and our spotlight presentation at 3pm, both in Straus 3!

Ilan Fridman Rojas Sasha Rush Cosma Shalizi This is really nice! But the proof is very general and thus complicated. A simpler proof, together with a proof of what can go wrong when learning these next-token predictors with MLE, is given in this (IMHO underrated) paper arxiv.org/pdf/2403.06963 Gregor Bachmann Vaishnavh Nagarajan

We have an exciting line-up of keynote speakers at our workshop for open-vocabulary 3D scene understanding, OpenSUN3D☀️ at #ECCV2024! 🗓️Sept 29, Sunday 14:00-17:30 ✍️opensun3d.github.io Tim Meinhardt Or Litany Alex Bewley Krishna Murthy

Come by poster #2402 East hall at NeurIPS from 11am-2pm Friday to chat about why outlier features emerge during training and how we can prevent them!

🚀 Excited to share our preprint LoRACLR! TL;DR: LoRACLR merges multiple LoRA models into a unified diffusion model for seamless, high-fidelity multi-concept image synthesis with minimal interference. Thanks to Thomas Hofmann, Federico Tombari, and Pinar Yanardag! 🙌

BPE is a greedy method to find a tokeniser which maximises compression! Why don't we try to find properly optimal tokenisers instead? Well, it seems this is a very difficult—in fact, NP-complete—problem!🤯 New paper + P. Whittington, Gregor Bachmann :) arxiv.org/abs/2412.15210

Join us for the 4th edition of ☀️OpenSUN3D🌎 workshop on open-world 3D scene understanding at #CVPR2025! We will explore emerging trends in 3D scene understanding, and applications of language models in 3D vision. We're also hosting a challenge! 📚 opensun3d.github.io

I will be giving a talk on open-vocabulary 3D scene understanding at the next ZurichCV meetup! 🗓️ Date: Thursday, January 23rd 18:00 📍Location: ETH AI Center, please see zurichai.ch/events/zurichc… for additional details!

🚨 NEW PAPER DROP! Wouldn't it be nice if LLMs could spot and correct their own mistakes? And what if we could do so directly from pre-training, without any SFT or RL? We present a new class of discrete diffusion models, called GIDD, that are able to do just that: 🧵1/12

Nvidia just announced Towards Learning to Complete Anything in Lidar

Thanks AK for sharing! During my internship at NVIDIA AI, we explored zero-shot panoptic completion of Lidar scans — together with Cristiano Saltori Neehar Peri Tim Meinhardt Riccardo de Lutio Laura Leal-Taixe Aljosa!

François Fleuret Hey François Fleuret, we had formalized this very intuition here in this late-2023 work you may be interested in :-) arxiv.org/abs/2403.06963

Better LLM training? Gregor Bachmann & Vaishnavh Nagarajan showed next-token prediction causes shortcut learning. A fix? Multi-token prediction training (thanks Fabian Gloeckle) We use register tokens: minimal architecture changes & scalable prediction horizons x.com/NasosGer/statu…

📢 New paper on creativity & multi-token prediction! We design minimal open-ended tasks to argue: → LLMs are limited in creativity since they learn to predict the next token → creativity can be improved via multi-token learning & injecting noise ("seed-conditioning" 🌱) 1/ 🧵

Our workshop on open-world 3D scene understanding OpenSUN3D is taking place this afternoon at #CVPR2025!

What's some "must read" literature on generalisation in neural networks? I keep thinking about this paper and it really makes me want to understand better the link between optimisation and generalisation. arxiv.org/abs/2302.12091

Can we learn to complete anything in Lidar without any manual supervision? Excited to share our #ICML2025 paper “Towards Learning to Complete Anything in Lidar” from my time at NVIDIA with Cristiano Saltori Neehar Peri Tim Meinhardt Riccardo de Lutio Aljosa Laura Leal-Taixe! Thread🧵👇

Today Chen Wu and I will be presenting our #ICML work on creativity in the Oral 3A Reasoning session (West Exhibition Hall C) 10 - 11 am PT Or please stop by our poster right after @ East Exhibition Hall A-B #E-2505 11am-1:30pm. (Hope you enjoy some silly human drawings!)

Honoured to receive two (!!) Senior Area Chair awards at #ACL2025 😁 (Conveniently placed on the same slide!) With the amazing Philip Whittington, Gregor Bachmann and Ethan Gotlieb Wilcox, Cui Ding, Giovanni Acampa, Alex Warstadt, Tamar Regev