Publications

LLMs for Experiment Design in Scientific Domains: Are We There Yet?
Rushil Gupta
Jason Hartford
Bang Liu
2025-06-11
ICML.cc/2025/Workshop/GenBio (poster)
openreview.net
openreview.net
Mapping Delayed Canopy Loss and Durable Fire Refugia for the 2020 Wildfires in Washington State Using Multiple Sensors
Anika M. Anderson
Meg A. Krawchuk
Flavie Pelletier
Jeff Cardille
2025-06-11
Fire (published)
doi.org
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Thinking
Sangmin Bae
Yujin Kim
Reza Bayat
Sungnyun Kim
Jiyoun Ha
Tal Schuster
Adam Fisch
Hrayr Harutyunyan
Ziwei Ji
Aaron Courville
Se-Young Yun
Scaling language models unlocks impressive capabilities, but the accompanying computational and memory demands make both training and deploy… (see more)ment expensive. Existing efficiency efforts typically target either parameter sharing or adaptive computation, leaving open the question of how to attain both simultaneously. We introduce Mixture-of-Recursions (MoR), a unified framework that combines the two axes of efficiency inside a single Recursive Transformer. MoR reuses a shared stack of layers across recursion steps to achieve parameter efficiency, while lightweight routers enable adaptive token-level thinking by dynamically assign recursion depth to tokens, thereby focusing quadratic attention computation only where it is most useful. Further enhancing its efficiency, MoR incorporates a recursion-wise key-value caching mechanism that eliminates redundant memory access across recursion steps by selectively storing only the key-value caches for designated tokens. Across pretraining runs at model scales ranging from 135M to 1.7B parameters, MoR forms a new Pareto frontier: at equal training FLOPs and smaller model sizes, it significantly lowers validation perplexity and improves few-shot accuracy, while delivering higher throughput compared with vanilla and existing recursive baselines. These gains demonstrate that MoR is an effective path towards large-model quality without incurring large-model cost.
2025-06-11
ICML.cc/2025/Workshop/ES-FoMo-III (published)
openreview.net
openreview.net
Model Parallelism With Subnetwork Data Parallelism
Vaibhav Singh
Zafir Khalid
Edouard Oyallon
Eugene Belilovsky
Distributed pre-training of large models at scale often imposes heavy memory demands on individual nodes and incurs significant intra-node c… (see more)ommunication costs. We propose a novel alternative approach that reduces the memory requirements by training small, structured subnetworks of the model on separate workers. Unlike pipelining, our method avoids inter-node activation communication and maintains bandwidth requirements that are comparable to or lower than standard data parallel communication schemes based on all-reduce. We evaluate two subnetwork construction strategies guided by the principle of ensuring uniform representation of each parameter across the distributed training setup. Our results show that the stochastic block dropping technique consistently outperforms the width-wise subnetwork construction previously explored in federated learning. We empirically attribute this superior performance to stronger gradient alignment in subnetworks that retain blocks having skip connections. Preliminary experiments highlight the promise of our approach, achieving a
2025-06-11
ICML.cc/2025/Workshop/ES-FoMo-III (published)
doi.org
openreview.net
MuLoCo: Muon is a practical inner optimizer for DiLoCo
Benjamin Therien
Xiaolong Huang
Irina Rish
Eugene Belilovsky
2025-06-11
ICML.cc/2025/Workshop/ES-FoMo-III (published)
doi.org
openreview.net
Next-Token Prediction Should be Ambiguity-Sensitive : A Meta-Learing Perspective
Leo Gagnon
Eric Elmoznino
Sarthak Mittal
Tom Marty
Tejas Kasetty
Dhanya Sridhar
Guillaume Lajoie
2025-06-11
ICML.cc/2025/Workshop/ES-FoMo-III (published)
openreview.net
openreview.net
NovoMolGen: Rethinking Molecular Language Model Pretraining
Kamran Chitsaz
Roshan Balaji
Quentin Fournier
Nirav Pravinbhai Bhatt
Sarath Chandar
2025-06-11
ICML.cc/2025/Workshop/GenBio (poster)
doi.org
openreview.net
Overcoming Long-Context Limitations of State-Space Models via Context-Dependent Sparse Attention
Zhihao Zhan
Jianan Zhao
Zhaocheng Zhu
Jian Tang
Efficient long-context modeling remains a critical challenge for natural language processing (NLP), as the time complexity of the predominan… (see more)t Transformer architecture scales quadratically with the sequence length. While state-space models (SSMs) offer alternative sub-quadratic solutions, they struggle to capture long-range dependencies effectively. In this work, we focus on analyzing and improving the long-context modeling capabilities of SSMs. We show that the widely used synthetic task, associative recall, which requires a model to recall a value associated with a single key without context, insufficiently represents the complexities of real-world long-context modeling. To address this limitation, we extend the associative recall to a novel synthetic task, \emph{joint recall}, which requires a model to recall the value associated with a key given in a specified context. Theoretically, we prove that SSMs do not have the expressiveness to solve multi-query joint recall in sub-quadratic time complexity. To resolve this issue, we propose a solution based on integrating SSMs with Context-Dependent Sparse Attention (CDSA), which has the expressiveness to solve multi-query joint recall with sub-quadratic computation. To bridge the gap between theoretical analysis and real-world applications, we propose locality-sensitive Hashing Attention with sparse Key Selection (HAX), which instantiates the theoretical solution and is further tailored to natural language domains. Extensive experiments on both synthetic and real-world long-context benchmarks show that HAX consistently outperforms SSM baselines and SSMs integrated with context-independent sparse attention (CISA).
2025-06-11
ICML.cc/2025/Workshop/ES-FoMo-III (published)
doi.org
openreview.net
Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities
Tara Akhound-Sadegh
Jungyoon Lee
Joey Bose
Valentin De Bortoli
Arnaud Doucet
Michael M. Bronstein
Dominique Beaini
Siamak Ravanbakhsh
Kirill Neklyudov
Alexander Tong
Sampling efficiently from a target unnormalized probability density remains a core challenge, with relevance across countless high-impact sc… (see more)ientific applications. A promising approach towards this challenge is the design of amortized samplers that borrow key ideas, such as probability path design, from state-of-the-art generative diffusion models. However, all existing diffusion-based samplers remain unable to draw samples from distributions at the scale of even simple molecular systems. In this paper, we propose Progressive Inference-Time Annealing (PITA), a novel framework to learn diffusion-based samplers that combines two complementary interpolation techniques: I.) Annealing of the Boltzmann distribution and II.) Diffusion smoothing. PITA trains a sequence of diffusion models from high to low temperatures by sequentially training each model at progressively higher temperatures, leveraging engineered easy access to samples of the temperature-annealed target density. In the subsequent step, PITA enables simulating the trained diffusion model to procure training samples at a lower temperature for the next diffusion model through inference-time annealing using a novel Feynman-Kac PDE combined with Sequential Monte Carlo. Empirically, PITA enables, for the first time, equilibrium sampling of N-body particle systems, Alanine Dipeptide, and tripeptides in Cartesian coordinates with dramatically lower energy function evaluations. Code available at: https://github.com/taraak/pita
2025-06-11
ICML.cc/2025/Workshop/GenBio (spotlight)
doi.org
openreview.net
Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning
Daniel Lawson
Adriana Hugessen
Charlotte Cloutier
Glen Berseth
Khimya Khetarpal
Behavioral cloning (BC) methods trained with supervised learning (SL) are an effective way to learn policies from human demonstrations in do… (see more)mains like robotics. Goal-conditioning these policies enables a single generalist policy to capture diverse behaviors contained within an offline dataset. While goal-conditioned behavior cloning (GCBC) methods can perform well on in-distribution training tasks, they do not necessarily generalize zero-shot to tasks that require conditioning on novel state-goal pairs, i.e. combinatorial generalization. In part, this limitation can be attributed to a lack of temporal consistency in the state representation learned by BC; if temporally related states are encoded to similar latent representations, then the out-of-distribution gap for novel state-goal pairs would be reduced. Hence, encouraging this temporal consistency in the representation space should facilitate combinatorial generalization. Successor representations, which encode the distribution of future states visited from the current state, nicely encapsulate this property. However, previous methods for learning successor representations have relied on contrastive samples, temporal-difference (TD) learning, or both. In this work, we propose a simple yet effective representation learning objective,
2025-06-11
ArXiv (preprint)
arxiv.org
arxiv.org
Task-Informed Meta-Learning for Remote Sensing
Gabriel Tseng
Hannah Kerner
David Rolnick
2025-06-11
2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (published)
doi.org
The 2025 PNPL Competition: Speech Detection and Phoneme Classification in the LibriBrain Dataset
Gilad Landau
Miran Ozdogan
Gereon Elvers
Francesco Mantegna
Pratik Somaiya
Dulhan Hansaja Jayalath
Luisa Kurth
Teyun Kwon
Brendan Shillingford
Greg Farquhar
Minqi Jiang
Karim Jerbi
Hamza Abdelhedi
Yorguin Mantilla Ramos
Caglar Gulcehre
M. Woolrich
Natalie Voets
Oiwi Parker Jones
The advance of speech decoding from non-invasive brain data holds the potential for profound societal impact. Among its most promising appli… (see more)cations is the restoration of communication to paralysed individuals affected by speech deficits such as dysarthria, without the need for high-risk surgical interventions. The ultimate aim of the 2025 PNPL competition is to produce the conditions for an"ImageNet moment"or breakthrough in non-invasive neural decoding, by harnessing the collective power of the machine learning community. To facilitate this vision we present the largest within-subject MEG dataset recorded to date (LibriBrain) together with a user-friendly Python library (pnpl) for easy data access and integration with deep learning frameworks. For the competition we define two foundational tasks (i.e. Speech Detection and Phoneme Classification from brain data), complete with standardised data splits and evaluation metrics, illustrative benchmark models, online tutorial code, a community discussion board, and public leaderboard for submissions. To promote accessibility and participation the competition features a Standard track that emphasises algorithmic innovation, as well as an Extended track that is expected to reward larger-scale computing, accelerating progress toward a non-invasive brain-computer interface for speech.
2025-06-11
ArXiv (preprint)
doi.org
arxiv.org