Nikolay Malkin

Outsourced Diffusion Sampling: Efficient Posterior Inference in Latent Spaces of Generative Models

Any well-behaved generative model over a variable …

2025-10-06

Proceedings of the 42nd International Conference on Machine Learning (published)

proceedings.mlr.press

Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models

Any well-behaved generative model over a variable …

2025-10-06

Proceedings of the 42nd International Conference on Machine Learning (published)

doi.org

openreview.net

Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models

Johan Samir Obando Ceron

Yoshua Bengio

Brian R. Bartoldson

Bhavya Kailkhura

Guillaume Lajoie

Glen Berseth

Nikolay Malkin

Moksh J. Jain

Test-time scaling methods improve the capabilities of large language models (LLMs) by increasing the amount of compute used during inference… (see more) to make a prediction. Inference-time compute can be scaled in parallel by choosing among multiple independent solutions or sequentially through self-refinement. We propose Recursive Self-Aggregation (RSA), a test-time scaling method inspired by evolutionary methods that combines the benefits of both parallel and sequential scaling. Each step of RSA refines a population of candidate reasoning chains through aggregation of subsets to yield a population of improved solutions, which are then used as the candidate pool for the next iteration. RSA exploits the rich information embedded in the reasoning chains -- not just the final answers -- and enables bootstrapping from partially correct intermediate steps within different chains of thought. Empirically, RSA delivers substantial performance gains with increasing compute budgets across diverse tasks, model families and sizes. Notably, RSA enables Qwen3-4B-Instruct-2507 to achieve competitive performance with larger reasoning models, including DeepSeek-R1 and o3-mini (high), while outperforming purely parallel and sequential scaling strategies across AIME-25, HMMT-25, Reasoning Gym, LiveCodeBench-v6, and SuperGPQA. We further demonstrate that training the model to combine solutions via a novel aggregation-aware reinforcement learning approach yields significant performance gains. Code available at https://github.com/HyperPotatoNeo/RSA.

2025-09-30

ArXiv (preprint)

arxiv.org

Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models

Johan Samir Obando Ceron

Yoshua Bengio

Brian R. Bartoldson

Bhavya Kailkhura

Guillaume Lajoie

Glen Berseth

Nikolay Malkin

Moksh J. Jain

Test-time scaling methods improve the capabilities of large language models (LLMs) by increasing the amount of compute used during inference… (see more) to make a prediction. Inference-time compute can be scaled in parallel by choosing among multiple independent solutions or sequentially through self-refinement. We propose Recursive Self-Aggregation (RSA), a test-time scaling method inspired by evolutionary methods that combines the benefits of both parallel and sequential scaling. Each step of RSA refines a population of candidate reasoning chains through aggregation of subsets to yield a population of improved solutions, which are then used as the candidate pool for the next iteration. RSA exploits the rich information embedded in the reasoning chains -- not just the final answers -- and enables bootstrapping from partially correct intermediate steps within different chains of thought. Empirically, RSA delivers substantial performance gains with increasing compute budgets across diverse tasks, model families and sizes. Notably, RSA enables Qwen3-4B-Instruct-2507 to achieve competitive performance with larger reasoning models, including DeepSeek-R1 and o3-mini (high), while outperforming purely parallel and sequential scaling strategies across AIME-25, HMMT-25, Reasoning Gym, LiveCodeBench-v6, and SuperGPQA. We further demonstrate that training the model to combine solutions via a novel aggregation-aware reinforcement learning approach yields significant performance gains. Code available at https://github.com/HyperPotatoNeo/RSA.

2025-09-30

ArXiv (preprint)

arxiv.org

Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models

Johan Samir Obando Ceron

Yoshua Bengio

Brian R. Bartoldson

Bhavya Kailkhura

Guillaume Lajoie

Glen Berseth

Nikolay Malkin

Moksh J. Jain

Test-time scaling methods improve the capabilities of large language models (LLMs) by increasing the amount of compute used during inference… (see more) to make a prediction. Inference-time compute can be scaled in parallel by choosing among multiple independent solutions or sequentially through self-refinement. We propose Recursive Self-Aggregation (RSA), a test-time scaling method inspired by evolutionary methods that combines the benefits of both parallel and sequential scaling. Each step of RSA refines a population of candidate reasoning chains through aggregation of subsets to yield a population of improved solutions, which are then used as the candidate pool for the next iteration. RSA exploits the rich information embedded in the reasoning chains -- not just the final answers -- and enables bootstrapping from partially correct intermediate steps within different chains of thought. Empirically, RSA delivers substantial performance gains with increasing compute budgets across diverse tasks, model families and sizes. Notably, RSA enables Qwen3-4B-Instruct-2507 to achieve competitive performance with larger reasoning models, including DeepSeek-R1 and o3-mini (high), while outperforming purely parallel and sequential scaling strategies across AIME-25, HMMT-25, Reasoning Gym, LiveCodeBench-v6, and SuperGPQA. We further demonstrate that training the model to combine solutions via a novel aggregation-aware reinforcement learning approach yields significant performance gains. Code available at https://github.com/HyperPotatoNeo/RSA.

2025-09-30

ArXiv (preprint)

doi.org

arxiv.org

Recursive Self-Aggregation Unlocks Deep Thinking in Large Language Models

Johan Samir Obando Ceron

Yoshua Bengio

Brian R. Bartoldson

Bhavya Kailkhura

Guillaume Lajoie

Glen Berseth

Nikolay Malkin

Moksh J. Jain

Test-time scaling methods improve the capabilities of large language models (LLMs) by increasing the amount of compute used during inference… (see more) to make a prediction. Inference-time compute can be scaled in parallel by choosing among multiple independent solutions or sequentially through self-refinement. We propose Recursive Self-Aggregation (RSA), a test-time scaling method inspired by evolutionary methods that combines the benefits of both parallel and sequential scaling. Each step of RSA refines a population of candidate reasoning chains through aggregation of subsets to yield a population of improved solutions, which are then used as the candidate pool for the next iteration. RSA exploits the rich information embedded in the reasoning chains -- not just the final answers -- and enables bootstrapping from partially correct intermediate steps within different chains of thought. Empirically, RSA delivers substantial performance gains with increasing compute budgets across diverse tasks, model families and sizes. Notably, RSA enables Qwen3-4B-Instruct-2507 to achieve competitive performance with larger reasoning models, including DeepSeek-R1 and o3-mini (high), while outperforming purely parallel and sequential scaling strategies across AIME-25, HMMT-25, Reasoning Gym, LiveCodeBench-v6, and SuperGPQA. We further demonstrate that training the model to combine solutions via a novel aggregation-aware reinforcement learning approach yields significant performance gains. Code available at https://github.com/HyperPotatoNeo/RSA.

2025-09-30

ArXiv (preprint)

arxiv.org

Can a Bayesian Oracle Prevent Harm from an Agent?

Michael K. Cohen

Is there a way to design powerful AI systems based on machine learning methods that would satisfy probabilistic safety guarantees? With the … (see more)long-term goal of obtaining a probabilistic guarantee that would apply in every context, we consider estimating a context-dependent bound on the probability of violating a given safety specification. Such a risk evaluation would need to be performed at run-time to provide a guardrail against dangerous actions of an AI. Noting that different plausible hypotheses about the world could produce very different outcomes, and because we do not know which one is right, we derive bounds on the safety violation probability predicted under the true but unknown hypothesis. Such bounds could be used to reject potentially dangerous actions. Our main results involve searching for cautious but plausible hypotheses, obtained by a maximization that involves Bayesian posteriors over hypotheses. We consider two forms of this result, in the i.i.d. case and in the non-i.i.d. case, and conclude with open problems towards turning such theoretical results into practical AI guardrails.

2025-07-11

Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence (published)

proceedings.mlr.press

Discrete Compositional Generation via General Soft Operators and Robust Reinforcement Learning

Bilun Sun

A major bottleneck in scientific discovery consists of narrowing an exponentially large set of objects, such as proteins or molecules, to a … (see more)small set of promising candidates with desirable properties. While this process can rely on expert knowledge, recent methods leverage reinforcement learning (RL) guided by a proxy reward function to enable this filtering. By employing various forms of entropy regularization, these methods aim to learn samplers that generate diverse candidates that are highly rated by the proxy function. In this work, we make two main contributions. First, we show that these methods are liable to generate overly diverse, suboptimal candidates in large search spaces. To address this issue, we introduce a novel unified operator that combines several regularized RL operators into a general framework that better targets peakier sampling distributions. Secondly, we offer a novel, robust RL perspective of this filtering process. The regularization can be interpreted as robustness to a compositional form of uncertainty in the proxy function (i.e., the true evaluation of a candidate differs from the proxy's evaluation). Our analysis leads us to a novel, easy-to-use algorithm we name trajectory general mellowmax (TGM): we show it identifies higher quality, diverse candidates than baselines in both synthetic and real-world tasks. Code: https://github.com/marcojira/tgm.

2025-06-20

ArXiv (preprint)

arxiv.org

Robust Reinforcement Learning for Discrete Compositional Generation via General Soft Operators

Bilun Sun

A major bottleneck in scientific discovery involves narrowing a large combinatorial set of objects, such as proteins or molecules, to a smal… (see more)l set of promising candidates. While this process largely relies on expert knowledge, recent methods leverage reinforcement learning (RL) to enhance this filtering. They achieve this by estimating proxy reward functions from available datasets and using regularization to generate more diverse candidates. These reward functions are inherently uncertain, raising a particularly salient challenge for scientific discovery. In this work, we show that existing methods, often framed as sampling proportional to a reward function, are inadequate and yield suboptimal candidates, especially in large search spaces. To remedy this issue, we take a robust RL approach and introduce a unified operator that seeks robustness to the uncertainty of the proxy reward function. This general operator targets peakier sampling distributions while encompassing known soft RL operators. It also leads us to a novel algorithm that identifies higher-quality, diverse candidates in both synthetic and real-world tasks. Ultimately, our work offers a new, flexible perspective on discrete compositional generation tasks. Code: https://github.com/marcojira/tgm.

2025-06-20

ArXiv (preprint)

arxiv.org

Robust Reinforcement Learning for Discrete Compositional Generation via General Soft Operators

Bilun Sun

A major bottleneck in scientific discovery involves narrowing a large combinatorial set of objects, such as proteins or molecules, to a smal… (see more)l set of promising candidates. While this process largely relies on expert knowledge, recent methods leverage reinforcement learning (RL) to enhance this filtering. They achieve this by estimating proxy reward functions from available datasets and using regularization to generate more diverse candidates. These reward functions are inherently uncertain, raising a particularly salient challenge for scientific discovery. In this work, we show that existing methods, often framed as sampling proportional to a reward function, are inadequate and yield suboptimal candidates, especially in large search spaces. To remedy this issue, we take a robust RL approach and introduce a unified operator that seeks robustness to the uncertainty of the proxy reward function. This general operator targets peakier sampling distributions while encompassing known soft RL operators. It also leads us to a novel algorithm that identifies higher-quality, diverse candidates in both synthetic and real-world tasks. Ultimately, our work offers a new, flexible perspective on discrete compositional generation tasks. Code: https://github.com/marcojira/tgm.

2025-06-01

arXiv (published)

doi.org

arxiv.org

Can a Bayesian Oracle Prevent Harm from an Agent?

Michael K. Cohen

Is there a way to design powerful AI systems based on machine learning methods that would satisfy probabilistic safety guarantees? With the … (see more)long-term goal of obtaining a probabilistic guarantee that would apply in every context, we consider estimating a context-dependent bound on the probability of violating a given safety specification. Such a risk evaluation would need to be performed at run-time to provide a guardrail against dangerous actions of an AI. Noting that different plausible hypotheses about the world could produce very different outcomes, and because we do not know which one is right, we derive bounds on the safety violation probability predicted under the true but unknown hypothesis. Such bounds could be used to reject potentially dangerous actions. Our main results involve searching for cautious but plausible hypotheses, obtained by a maximization that involves Bayesian posteriors over hypotheses. We consider two forms of this result, in the iid case and in the non-iid case, and conclude with open problems towards turning such theoretical results into practical AI guardrails.

2025-05-07

auai.org/UAI/2025/Conference (poster)

doi.org

openreview.net

Learning Decision Trees as Amortized Structure Inference

Mohammed Mahfoud

Ghait Boukachab

Michał Koziarski

Alex Hernandez-Garcia

Stefan Bauer

Yoshua Bengio

Nikolay Malkin

Building predictive models for tabular data presents fundamental challenges, notably in scaling consistently, i.e., more resources translati… (see more)ng to better performance, and generalizing systematically beyond the training data distribution. Designing decision tree models remains especially challenging given the intractably large search space, and most existing methods rely on greedy heuristics, while deep learning inductive biases expect a temporal or spatial structure not naturally present in tabular data. We propose a hybrid amortized structure inference approach to learn predictive decision tree ensembles given data, formulating decision tree construction as a sequential planning problem. We train a deep reinforcement learning (GFlowNet) policy to solve this problem, yielding a generative model that samples decision trees from the Bayesian posterior. We show that our approach, DT-GFN, outperforms state-of-the-art decision tree and deep learning methods on standard classification benchmarks derived from real-world data, robustness to distribution shifts, and anomaly detection, all while yielding interpretable models with shorter description lengths. Samples from the trained DT-GFN model can be ensembled to construct a random forest, and we further show that the performance of scales consistently in ensemble size, yielding ensembles of predictors that continue to generalize systematically.

2025-03-10

ArXiv (preprint)

doi.org

arxiv.org

Custom AI Learning Programs

Mil'Haq Fest 2025

Mila Community of Practice

Supervision Requests

Nikolay Malkin

Blog Posts

Publications

Custom AI Learning Programs

Mil'Haq Fest 2025

Mila Community of Practice

Supervision Requests

Popular keywords:

Nikolay Malkin

Blog Posts

Publications