Minsu Kim

Alex Hernandez-Garcia

2026-02-03

ArXiv (preprint)

Improved Off-policy Reinforcement Learning in Biological Sequence Design

Alex Hernandez-Garcia

Jinkyoo Park

Designing biological sequences with desired properties is a significant challenge due to the combinatorially vast search space and the high … (see more)cost of evaluating each candidate sequence. To address these challenges, reinforcement learning (RL) methods, such as GFlowNets, utilize proxy models for rapid reward evaluation and annotated data for policy training. Although these approaches have shown promise in generating diverse and novel sequences, the limited training data relative to the vast search space often leads to the misspecification of proxy for out-of-distribution inputs. We introduce

2025-10-06

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

Improved Off-policy Reinforcement Learning in Biological Sequence Design

Alex Hernandez-Garcia

Jinkyoo Park

Designing biological sequences with desired properties is challenging due to vast search spaces and limited evaluation budgets. Although rei… (see more)nforcement learning methods use proxy models for rapid reward evaluation, insufficient training data can cause proxy misspecification on out-of-distribution inputs. To address this, we propose a novel off-policy search,

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)

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)

openreview.net

Active Attacks: Red-teaming LLMs via Adaptive Environments

Taeyoung YUN

Pierre-Luc St-Charles

Jinkyoo Park

2025-09-26

ArXiv (preprint)

Active Attacks: Red-teaming LLMs via Adaptive Environments

Taeyoung YUN

Pierre-Luc St-Charles

Jinkyoo Park

We address the challenge of generating diverse attack prompts for large language models (LLMs) that elicit harmful behaviors (e.g., insults,… (see more) sexual content) and are used for safety fine-tuning. Rather than relying on manual prompt engineering, attacker LLMs can be trained with reinforcement learning (RL) to automatically generate such prompts using only a toxicity classifier as a reward. However, capturing a wide range of harmful behaviors is a significant challenge that requires explicit diversity objectives. Existing diversity-seeking RL methods often collapse to limited modes: once high-reward prompts are found, exploration of new regions is discouraged. Inspired by the active learning paradigm that encourages adaptive exploration, we introduce \textit{Active Attacks}, a novel RL-based red-teaming algorithm that adapts its attacks as the victim evolves. By periodically safety fine-tuning the victim LLM with collected attack prompts, rewards in exploited regions diminish, which forces the attacker to seek unexplored vulnerabilities. This process naturally induces an easy-to-hard exploration curriculum, where the attacker progresses beyond easy modes toward increasingly difficult ones. As a result, Active Attacks uncovers a wide range of local attack modes step by step, and their combination achieves wide coverage of the multi-mode distribution. Active Attacks, a simple plug-and-play module that seamlessly integrates into existing RL objectives, unexpectedly outperformed prior RL-based methods -- including GFlowNets, PPO, and REINFORCE -- by improving cross-attack success rates against GFlowNets, the previous state-of-the-art, from 0.07% to 31.28% (a relative gain greater than

2025-09-26

ArXiv (preprint)

Trajectory Balance with Asynchrony: Decoupling Exploration and Learning for Fast, Scalable LLM Post-Training

Brian Bartoldson

James Diffenderfer

Tal Ben-Nun

Johan Obando-Ceron

Bhavya Kailkhura

Reinforcement learning (RL) is a critical component of large language model (LLM) post-training. However, on-policy algorithms used for post… (see more)-training are not naturally robust to a diversified content of experience replay buffers, which asynchronous off-policy actors can efficiently populate in parallel to training. We propose efficiently learning on such off-policy data via Trajectory Balance with Asynchrony (TBA), an approach to asynchronous RL for LLMs that leverages the principled off-policy TB objective. On math, preference-tuning, and automated red-teaming tasks, we post-train models ranging from Pythia 410M to Qwen 2.5 7B, finding TBA offers speed and performance boosts over strong baselines like Online DPO and Dr. GRPO. Beyond TBA's performance benefits (high accuracy even as asynchrony grows) and speedups (

2025-09-17

NeurIPS.cc/2025/Conference (poster)

openreview.net

Adaptive Cyclic Diffusion for Inference Scaling

Gyubin Lee

Truong Nhat Nguyen Bao

Jaesik Yoon

Dongwoo Lee

2025-05-20

ArXiv (preprint)

Adaptive Inference-Time Scaling via Cyclic Diffusion Search

Gyubin Lee

Truong Nhat Nguyen Bao

Jaesik Yoon

Dongwoo Lee

Diffusion models have demonstrated strong generative capabilities across domains ranging from image synthesis to complex reasoning tasks. Ho… (see more)wever, most inference-time scaling methods rely on fixed denoising schedules, limiting their ability to allocate computation based on instance difficulty or task-specific demands adaptively. We introduce the challenge of adaptive inference-time scaling-dynamically adjusting computational effort during inference-and propose Adaptive Bi-directional Cyclic Diffusion (ABCD), a flexible, search-based inference framework. ABCD refines outputs through bi-directional diffusion cycles while adaptively controlling exploration depth and termination. It comprises three components: Cyclic Diffusion Search, Automatic Exploration-Exploitation Balancing, and Adaptive Thinking Time. Experiments show that ABCD improves performance across diverse tasks while maintaining computational efficiency.

2025-05-20

ArXiv (preprint)

Adaptive Inference-Time Scaling via Cyclic Diffusion Search

Gyubin Lee

Truong Nhat Nguyen Bao

Jaesik Yoon

Dongwoo Lee

Diffusion models have demonstrated strong generative capabilities across domains ranging from image synthesis to complex reasoning tasks. Ho… (see more)wever, most inference-time scaling methods rely on fixed denoising schedules, limiting their ability to allocate computation based on instance difficulty or task-specific demands adaptively. We introduce the challenge of adaptive inference-time scaling-dynamically adjusting computational effort during inference-and propose Adaptive Bi-directional Cyclic Diffusion (ABCD), a flexible, search-based inference framework. ABCD refines outputs through bi-directional diffusion cycles while adaptively controlling exploration depth and termination. It comprises three components: Cyclic Diffusion Search, Automatic Exploration-Exploitation Balancing, and Adaptive Thinking Time. Experiments show that ABCD improves performance across diverse tasks while maintaining computational efficiency.

2025-05-20

ArXiv (preprint)

Adaptive Inference-Time Scaling via Cyclic Diffusion Search

Gyubin Lee

Truong Nhat Nguyen Bao

Jaesik Yoon

Dongwoo Lee

Diffusion models have demonstrated strong generative capabilities across domains ranging from image synthesis to complex reasoning tasks. Ho… (see more)wever, most inference-time scaling methods rely on fixed denoising schedules, limiting their ability to allocate computation based on instance difficulty or task-specific demands adaptively. We introduce the challenge of adaptive inference-time scaling-dynamically adjusting computational effort during inference-and propose Adaptive Bi-directional Cyclic Diffusion (ABCD), a flexible, search-based inference framework. ABCD refines outputs through bi-directional diffusion cycles while adaptively controlling exploration depth and termination. It comprises three components: Cyclic Diffusion Search, Automatic Exploration-Exploitation Balancing, and Adaptive Thinking Time. Experiments show that ABCD improves performance across diverse tasks while maintaining computational efficiency.

2025-05-20

ArXiv (preprint)