News

AITHYRA at ICLR: 20 Papers, Including 3 Orals

AITHYRA has a strong presence at the upcoming International Conference on Learning Representations (ICLR), one of the premier AI conferences taking place in April in Rio de Janeiro, Brazil. Twenty papers accepted this year had at least one AITHYRA-affiliated author, reflecting our ongoing commitment to advancing foundational and applied machine learning. We are especially proud that three of these works have been selected for oral presentations (top 1.2%). 
Congratulations to all our team members and collaborators for their exceptional work!

Oral:

FALCON: Few-step Accurate Likelihoods for Continuous Flows by Danyal Rehman, Tara Akhound-Sadegh, Artem Gazizov, Yoshua Bengio, Alexander Tong

Planner Aware Path Learning in Diffusion Language Models Training by Fred Zhangzhi Peng, Zachary Bezemek, Jarrid Rector-Brooks, Shuibai Zhang, Michael M. Bronstein, Anru Zhang, Joey Bose, Alexander Tong

Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute by Kieran Didi, Zuobai Zhang, Guoqing Zhou, Danny Reidenbach, Zhonglin Cao, Sooyoung Cha, Tomas Geffner, Christian Dallago, Jian Tang, Michael M. Bronstein, Martin Steinegger, Emine Kucukbenli, Arash Vahdat, Karsten Kreis, Arash Vahdat, Karsten Kreis

Poster:

Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin by Enrique Queipo-de-Llano, Alvaro Arroyo, Federico Barbero, Xiaowen Dong, Michael M. Bronstein, Yann LeCun, Ravid Shwartz-Ziv

Branched Schrodinger Bridge Matching by Sophia Tang, Yinuo Zhang, Alexander Tong, Pranam Chatterjee

Carré du champ flow matching: better quality-generalisation tradeoff in generative models by Jacob Bamberger, Iolo Jones, Dennis Duncan, Michael M. Bronstein, Pierre Vandergheynst, Adam Gosztolai

Efficient Learning on Large Graphs using a Densifying Regularity Lemma by Jonathan Kouchly, Ben Finkelshtein, Michael M. Bronstein, Ron Levie

Efficient Regression-based Training of Normalizing Flows for Boltzmann Generators by Danyal Rehman, Oscar Davis, Jiarui Lu, Jian Tang, Michael M. Bronstein, Yoshua Bengio, Alexander Tong, Joey Bose

Flock: A knowledge Graph Foundation Model via Learning on Random Walks by Jinwoo Kim, Xingyue Huang, Krzysztof Olejniczak, Kyungbin Min, Michael M. Bronstein, Seunghoon Hong, Ismail Ilkan Ceylan

Generalised Flow Maps for Few-Step Generative Modelling on Riemannian Manifolds by Oscar Davis, Michael Samuel Albergo, Nicholas Matthew Boffi, Michael M. Bronstein, Joey Bose

gLSTM: Mitigating Over-Squashing by Increasing Storage Capacity by Hugh Blayney, Alvaro Arroyo, Xiaowen Dong, Michael M. Bronstein

HYPER: A Foundation Model for Inductive Link Prediction with Knowledge Hypergraphs by Xingyue Huang, Mikhail Galkin, Michael M. Bronstein, Ismail Ilkan Ceylan

Learning Escorted Protocols for Multistate Free-Energy Estimation by Lars Holdijk, Nithishwer Mouroug Anand, Michael M. Bronstein, Max Welling

LLMs Can Hide Text in Other Text of the Same Length by Antonio Norelli, Michael M. Bronstein

MarS-FM: Generative Modeling of Molecular Dynamics via Markov State Models by Kacper Kapuśniak, Cristian Gabellini, Michael M. Bronstein, Prudencio Tossou, Francesco Di Giovanni

OXtal: An All-Atom Diffusion Model for Organic Crystal Structure Prediction by Emily Jin, Andrei Cristian Nica, Mikhail Galkin, Jarrid Rector-Brooks, Kin Long Kelvin Lee, Santiago Miret, Frances H. Arnold, Michael M. Bronstein, Joey Bose, Alexander Tong, Cheng-Hao Liu

ResCP: Reservoir Conformal Prediction for Time Series Forcasting by Roberto Neglia, Andrea Cini, Michael M. Bronstein, Filippo Maria Bianchi

TGM: A Modular and Efficient Library for Machine Learning on Temporal Graphs by Jacob Chmura, Shenyang Huang, Tran Gia Bao Ngo, Ali Parviz, Farimah Poursafaei, Jure Leskovec, Michael M. Bronstein, Guillaume Rabusseau, Matthias Fey, Reihaneh Rabbany

Topological Flow Matching by Kacper Wyrwal, Ismail Ilkan Ceylan, Alexander Tong

Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement by Huidong Liang, Haitz Sáez de Ocáriz Borde, Baskaran Sripathmanathan, Michael M. Bronstein, Xiaowen Dong

Share this article