Related papers: From Competition to Synergy: Unlocking Reinforceme…

This paper provides a self-contained, from-scratch, exposition of key algorithms for instruction tuning of models: SFT, Rejection Sampling, REINFORCE, Trust Region Policy Optimization (TRPO), Proximal Policy Optimization (PPO), Group…

Large-scale foundation models, such as CLIP, have demonstrated remarkable success in visual recognition tasks by embedding images in a semantically rich space. Self-supervised learning (SSL) has also shown promise in improving visual…

Generative diffusion models (DM) have been extensively utilized in image super-resolution (ISR). Most of the existing methods adopt the denoising loss from DDPMs for model optimization. We posit that introducing reward feedback learning to…

Recent advancements in reinforcement learning, particularly through Group Relative Policy Optimization (GRPO), have significantly improved multimodal large language models for complex reasoning tasks. However, two critical limitations…

In safe reinforcement learning (SRL) problems, an agent explores the environment to maximize an expected total reward and meanwhile avoids violation of certain constraints on a number of expected total costs. In general, such SRL problems…

Blind Face Restoration (BFR) encounters inherent challenges in exploring its large solution space, leading to common artifacts like missing details and identity ambiguity in the restored images. To tackle these challenges, we propose a…

Advances in deep generative networks have led to impressive results in recent years. Nevertheless, such models can often waste their capacity on the minutiae of datasets, presumably due to weak inductive biases in their decoders. This is…

To fully uncover the great potential of deep neural networks (DNNs), various learning algorithms have been developed to improve the model's generalization ability. Recently, sharpness-aware minimization (SAM) establishes a generic scheme…

Reinforcement learning (RL) has emerged as a critical technique for enhancing LLM-based deep search agents. However, existing approaches primarily rely on binary outcome rewards, which fail to capture the comprehensiveness and factuality of…

Group Relative Policy Optimization (GRPO) has emerged as the de facto Reinforcement Learning (RL) objective driving recent advancements in Multimodal Large Language Models. However, extending this success to open-source multimodal…

Vision-based reinforcement learning requires efficient and robust representations of image-based observations, especially when the images contain distracting (task-irrelevant) elements such as shadows, clouds, and light. It becomes more…

Group Relative Policy Optimization (GRPO) has been shown to be an effective algorithm when an accurate reward model is available. However, such a highly reliable reward model is not available in many real-world tasks. In this paper, we…

Recent advances in flow matching models have significantly improved text-to-image generation quality, but also introduce growing safety risks due to the generation of harmful or undesirable content. Existing concept erasure methods are…

Hybrid Group Relative Policy Optimization (Hybrid GRPO) is a reinforcement learning framework that extends Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO) by incorporating empirical multi-sample action…

Recent research has shown that fine-tuning diffusion models (DMs) with arbitrary rewards, including non-differentiable ones, is feasible with reinforcement learning (RL) techniques, enabling flexible model alignment. However, applying…

Recent advances in video world modeling have enabled large-scale generative models to simulate embodied environments with high visual fidelity, providing strong priors for prediction, planning, and control. Yet, despite their realism, these…

Self-supervised reinforcement learning (RL) presents a promising approach for enhancing the reasoning capabilities of Large Language Models (LLMs) without reliance on expensive human-annotated data. However, we find that existing methods…

Existing post-training techniques are broadly categorized into supervised fine-tuning (SFT) and reinforcement learning (RL) methods; the former is stable during training but suffers from limited generalization, while the latter, despite its…

While Large Language Models (LLMs) can generate fluent text, producing high-quality creative stories remains challenging. Reinforcement Learning (RL) offers a promising solution but faces two critical obstacles: designing reliable reward…

Reinforcement learning from human feedback (RLHF) or verifiable rewards (RLVR), the standard paradigm for aligning LLMs or building recent SOTA reasoning models, is highly sensitive to noise from inconsistent or erroneous rewards. Yet, the…