相关论文: DACA-GRPO: Denoising-Aware Credit Assignment for R…

Reinforcement learning has become a powerful paradigm for post-training large language model agents, yet credit assignment in multi-turn environments remains a challenge. Agents often receive sparse, trajectory-level rewards only at the end…

Reinforcement learning (RL) has emerged as a powerful tool for aligning diffusion models with human preferences, typically by optimizing a single reward function under a KL regularization constraint. In practice, however, human preferences…

This study presents a systematic comparison of three Reinforcement Learning (RL) algorithms (PPO, GRPO, and DAPO) for improving complex reasoning in large language models (LLMs). Our main contribution is a controlled transfer-learning…

Online reinforcement learning is becoming increasingly important for aligning diffusion models with non-differentiable objectives. However, existing methods still face limitations in assigning fine-grained credit along denoising…

The success of denoising diffusion models raises important questions regarding their generalisation behaviour, particularly in high-dimensional settings. Notably, it has been shown that when training and sampling are performed perfectly,…

Intent detection, a critical component in task-oriented dialogue (TOD) systems, faces significant challenges in adapting to the rapid influx of integrable tools with complex interrelationships. Existing approaches, such as zero-shot…

Group-relative policy optimization methods train language models by generating multiple rollouts per prompt and normalizing rewards with a shared mean reward baseline. In resource-constrained settings where the rollout budget is small,…

Can we use reinforcement learning to learn general-purpose policies that can perform a wide range of different tasks, resulting in flexible and reusable skills? Contextual policies provide this capability in principle, but the…

Group Relative Policy Optimization (GRPO) has become the dominant method for reinforcement learning with verifiable rewards in large language models, but it suffers from two critical limitations: gradient vanishing and diversity collapse.…

Graph clustering is an essential aspect of network analysis that involves grouping nodes into separate clusters. Recent developments in deep learning have resulted in graph clustering, which has proven effective in many applications.…

Achieving fast and stable off-policy learning in deep reinforcement learning (RL) is challenging. Most existing methods rely on semi-gradient temporal-difference (TD) methods for their simplicity and efficiency, but are consequently…

Large language models (LLMs) are highly sensitive to even small amounts of unsafe training data, making effective detection and filtering essential for trustworthy model development. Current state-of-the-art (SOTA) detection approaches…

Recent advances in reinforcement learning (RL) have demonstrated the powerful exploration capabilities and multimodality of generative diffusion-based policies. While substantial progress has been made in offline RL and off-policy RL…

Diffusion models have been applied to improve adversarial robustness of image classifiers by purifying the adversarial noises or generating realistic data for adversarial training. However, diffusion-based purification can be evaded by…

Recent studies on reasoning models explore the meta-awareness of language models, the ability to know how to think by itself. We argue that large reasoning models lack this meta-awareness property by proving severe misalignment between true…

Diffusion models have recently shown strong potential in language modeling, offering faster generation compared to traditional autoregressive approaches. However, applying supervised fine-tuning (SFT) to diffusion models remains…

Capitalizing on the complementary advantages of generative and discriminative models has always been a compelling vision in machine learning, backed by a growing body of research. This work discloses the hidden semantic structure within…

In settings where labeled verifiable training data is the binding constraint, each checked example should be allocated to the model and reward density where it is most informative. We identify a reward-density principle that governs this…

Diffusion models have achieved remarkable success in conditional image generation, yet their outputs often remain misaligned with human preferences. To address this, recent work has applied Direct Preference Optimization (DPO) to diffusion…

Despite the strong performance achieved by reinforcement learning-trained information-seeking agents, learning in open-ended web environments remains severely constrained by low signal-to-noise feedback. Text-based parsers often discard…