Publications

In-context learning and Occam's razor
Eric Elmoznino
Tom Marty
Tejas Kasetty
Leo Gagnon
Sarthak Mittal
Mahan Fathi
Dhanya Sridhar
Guillaume Lajoie
A central goal of machine learning is generalization. While the No Free Lunch Theorem states that we cannot obtain theoretical guarantees fo… (voir plus)r generalization without further assumptions, in practice we observe that simple models which explain the training data generalize best: a principle called Occam's razor. Despite the need for simple models, most current approaches in machine learning only minimize the training error, and at best indirectly promote simplicity through regularization or architecture design. Here, we draw a connection between Occam's razor and in-context learning: an emergent ability of certain sequence models like Transformers to learn at inference time from past observations in a sequence. In particular, we show that the next-token prediction loss used to train in-context learners is directly equivalent to a data compression technique called prequential coding, and that minimizing this loss amounts to jointly minimizing both the training error and the complexity of the model that was implicitly learned from context. Our theory and the empirical experiments we use to support it not only provide a normative account of in-context learning, but also elucidate the shortcomings of current in-context learning methods, suggesting ways in which they can be improved. We make our code available at https://github.com/3rdCore/PrequentialCode.
2025-10-05
Proceedings of the 42nd International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
Incorporating Spatial Information into Goal-Conditioned Hierarchical Reinforcement Learning via Graph Representations
Shuyuan Zhang
Zihan Wang
Xiao-Wen Chang
Doina Precup
The integration of graphs with Goal-conditioned Hierarchical Reinforcement Learning (GCHRL) has recently gained attention, as intermediate g… (voir plus)oals (subgoals) can be effectively sampled from graphs that naturally represent the overall task structure in most RL tasks. However, existing approaches typically rely on domain-specific knowledge to construct these graphs, limiting their applicability to new tasks. Other graph-based approaches create graphs dynamically during exploration but struggle to fully utilize them, because they have problems passing the information in the graphs to newly visited states. Additionally, current GCHRL methods face challenges such as sample inefficiency and poor subgoal representation. This paper proposes a solution to these issues by developing a graph encoder-decoder to evaluate unseen states. Our proposed method, Graph-Guided sub-Goal representation Generation RL (G4RL), can be incorporated into any existing GCHRL method when operating in environments with primarily symmetric and reversible transitions to enhance performance across this class of problems. We show that the graph encoder-decoder can be effectively implemented using a network trained on the state graph generated during exploration. Empirical results indicate that leveraging high and low-level intrinsic rewards from the graph encoder-decoder significantly enhances the performance of state-of-the-art GCHRL approaches with an extra small computational cost in dense and sparse reward environments.
2025-10-05
Transactions on Machine Learning Research (accepté)
doi.org
openreview.net
Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks?
Rishika Bhagwatkar
Kevin Kasa
Abhay Puri
Gabriel Huang
Irina Rish
Graham W. Taylor
Krishnamurthy Dj Dvijotham
Alexandre Lacoste
AI agents are vulnerable to indirect prompt injection attacks, where malicious instructions embedded in external content or tool outputs cau… (voir plus)se unintended or harmful behavior. Inspired by the well-established concept of firewalls, we show that a simple, modular and model-agnostic defense operating at the agent--tool interface achieves perfect security (0% or the lowest possible attack success rate) with high utility (task success rate) across four public benchmarks: AgentDojo, Agent Security Bench, InjecAgent and tau-Bench, while achieving a state-of-the-art security-utility tradeoff compared to prior results. Specifically, we employ a defense based on two firewalls: a Tool-Input Firewall (Minimizer) and a Tool-Output Firewall (Sanitizer). Unlike prior complex approaches, this firewall defense makes minimal assumptions on the agent and can be deployed out-of-the-box, while maintaining strong performance without compromising utility. However, our analysis also reveals critical limitations in these existing benchmarks, including flawed success metrics, implementation bugs, and most importantly, weak attacks, hindering significant progress in the field. To foster more meaningful progress, we present targeted fixes to these issues for AgentDojo and Agent Security Bench while proposing best-practices for more robust benchmark design. Further, we demonstrate that although these firewalls push the state-of-the-art on existing benchmarks, it is still possible to bypass them in practice, underscoring the need to incorporate stronger attacks in security benchmarks. Overall, our work shows that existing agentic security benchmarks are easily saturated by a simple approach and highlights the need for stronger agentic security benchmarks with carefully chosen evaluation metrics and strong adaptive attacks.
2025-10-05
ArXiv (prépublication)
doi.org
arxiv.org
Language Models over Canonical Byte-Pair Encodings
Tim Vieira
Tianyu Liu
Clemente Pasti
Yahya Emara
Brian DuSell
Benjamin LeBrun
Mario Giulianelli
Juan Luis Gastaldi
Timothy J. O'Donnell
Ryan Cotterell
Modern language models represent probability distributions over character strings as distributions over (shorter) token strings derived via … (voir plus)a deterministic tokenizer, such as byte-pair encoding. While this approach is highly effective at scaling up language models to large corpora, its current incarnations have a concerning property: the model assigns nonzero probability mass to an exponential number of
2025-10-05
Proceedings of the 42nd International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
Thomas Schmied
Thomas Adler
Vihang P. Patil
Maximilian Beck
Korbinian Poppel
Johannes Brandstetter
Günter Klambauer
Razvan Pascanu
Sepp Hochreiter
In recent years, there has been a trend in the field of Reinforcement Learning (RL) towards large action models trained offline on large-sca… (voir plus)le datasets via sequence modeling. Existing models are primarily based on the Transformer architecture, which result in powerful agents. However, due to slow inference times, Transformer-based approaches are impractical for real-time applications, such as robotics. Recently, modern recurrent architectures, such as xLSTM and Mamba, have been proposed that exhibit parallelization benefits during training similar to the Transformer architecture while offering fast inference. In this work, we study the aptitude of these modern recurrent architectures for large action models. Consequently, we propose a Large Recurrent Action Model (LRAM) with an xLSTM at its core that comes with linear-time inference complexity and natural sequence length extrapolation abilities. Experiments on 432 tasks from 6 domains show that LRAM compares favorably to Transformers in terms of performance and speed.
2025-10-05
Proceedings of the 42nd International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
Leveraging Per-Instance Privacy for Machine Unlearning
Nazanin Mohammadi Sepahvand
Anvith Thudi
Berivan Isik
Ashmita Bhattacharyya
Nicolas Papernot
Eleni Triantafillou
Daniel M. Roy
Gintare Karolina Dziugaite
2025-10-05
Proceedings of the 42nd International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces
Rashid Mushkani
Shravan Nayak
Hugo Berard
Allison Cohen
Shin Koseki
Hadrien Bertrand
We introduce the Local Intersectional Visual Spaces (LIVS) dataset, a benchmark for multi-criteria alignment, developed through a two-year p… (voir plus)articipatory process with 30 community organizations to support the pluralistic alignment of text-to-image (T2I) models in inclusive urban planning. The dataset encodes 37,710 pairwise comparisons across 13,462 images, structured along six criteria - Accessibility, Safety, Comfort, Invitingness, Inclusivity, and Diversity - derived from 634 community-defined concepts. Using Direct Preference Optimization (DPO), we fine-tune Stable Diffusion XL to reflect multi-criteria spatial preferences and evaluate the LIVS dataset and the fine-tuned model through four case studies: (1) DPO increases alignment with annotated preferences, particularly when annotation volume is high; (2) preference patterns vary across participant identities, underscoring the need for intersectional data; (3) human-authored prompts generate more distinctive visual outputs than LLM-generated ones, influencing annotation decisiveness; and (4) intersectional groups assign systematically different ratings across criteria, revealing the limitations of single-objective alignment. While DPO improves alignment under specific conditions, the prevalence of neutral ratings indicates that community values are heterogeneous and often ambiguous. LIVS provides a benchmark for developing T2I models that incorporate local, stakeholder-driven preferences, offering a foundation for context-aware alignment in spatial design.
2025-10-05
Proceedings of the 42nd International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D
Sergio Arnaud
Paul McVay
Ada Martin
Arjun Majumdar
Krishna Murthy
Phillip Thomas
Ruslan Partsey
Daniel Dugas
Abha Gejji
Alexander Sax
Vincent-Pierre Berges
Mikael Henaff
Ayush Jain
Ang Cao
Ishita Prasad
Mrinal Kalakrishnan
Michael G. Rabbat
Nicolas Ballas
Mahmoud Assran
Oleksandr Maksymets … (voir 2 de plus)
Aravind Rajeswaran
Franziska Meier
2025-10-05
Proceedings of the 42nd International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization
Phillip Huang Guo
Aaquib Syed
Abhay Sheshadri
Aidan Ewart
Gintare Karolina Dziugaite
2025-10-05
Proceedings of the 42nd International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
Monte Carlo Tree Diffusion for System 2 Planning
Jaesik Yoon
Hyeonseo Cho
Doojin Baek
Yoshua Bengio
Sungjin Ahn
Diffusion models have recently emerged as a powerful tool for planning. However, unlike Monte Carlo Tree Search (MCTS)-whose performance nat… (voir plus)urally improves with inference-time computation scaling-standard diffusion-based planners offer only limited avenues for the scalability. In this paper, we introduce Monte Carlo Tree Diffusion (MCTD), a novel framework that integrates the generative strength of diffusion models with the adaptive search capabilities of MCTS. Our method reconceptualizes denoising as a tree-structured process, allowing partially denoised plans to be iteratively evaluated, pruned, and refined. By selectively expanding promising trajectories while retaining the flexibility to revisit and improve suboptimal branches, MCTD achieves the benefits of MCTS such as controlling exploration-exploitation trade-offs within the diffusion framework. Empirical results on challenging long-horizon tasks show that MCTD outperforms diffusion baselines, yielding higher-quality solutions as inference-time computation increases.
2025-10-05
Proceedings of the 42nd International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press
Multivariate Conformal Selection
Tian Bai
Yue Zhao
Xiang Yu
Archer Yang
Selecting high-quality candidates from large datasets is critical in applications such as drug discovery, precision medicine, and alignment … (voir plus)of large language models (LLMs). While Conformal Selection (CS) provides rigorous uncertainty quantification, it is limited to univariate responses and scalar criteria. To address this, we propose Multivariate Conformal Selection (mCS), a generalization of CS designed for multivariate response settings. Our method introduces regional monotonicity and employs multivariate nonconformity scores to construct conformal
2025-10-05
Proceedings of the 42nd International Conference on Machine Learning (publié)
proceedings.mlr.press
proceedings.mlr.press
Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement Learning
Guozheng Ma
Lu Li
Zilin Wang
Li Shen
Pierre-Luc Bacon
Dacheng Tao
Effectively scaling up deep reinforcement learning models has proven notoriously difficult due to network pathologies during training, motiv… (voir plus)ating various targeted interventions such as periodic reset and architectural advances such as layer normalization. Instead of pursuing more complex modifications, we show that introducing static network sparsity alone can unlock further scaling potential beyond their dense counterparts with state-of-the-art architectures. This is achieved through simple one-shot random pruning, where a predetermined percentage of network weights are randomly removed once before training. Our analysis reveals that, in contrast to naively scaling up dense DRL networks, such sparse networks achieve both higher parameter efficiency for network expressivity and stronger resistance to optimization challenges like plasticity loss and gradient interference. We further extend our evaluation to visual and streaming RL scenarios, demonstrating the consistent benefits of network sparsity.
2025-10-05
Proceedings of the 42nd International Conference on Machine Learning (publié)
doi.org
proceedings.mlr.press