Related papers: Advances in GRPO for Generation Models: A Survey

Group Relative Policy Optimization (GRPO) has emerged as an effective and lightweight framework for post-training visual generative models. However, its performance is fundamentally limited by the ambiguity of textual visual correspondence:…

Recent advancements in multimodal reward models (RMs) have significantly propelled the development of visual generation. Existing frameworks typically adopt Bradley-Terry-style preference modeling or leverage generative VLMs as judges, and…

Reinforcement learning from verifiable rewards has emerged as a powerful technique for enhancing the complex reasoning abilities of Large Language Models (LLMs). However, these methods are fundamentally constrained by the ''learning cliff''…

While recent text-to-video (T2V) diffusion models have achieved impressive quality and prompt alignment, they often produce low-diversity outputs when sampling multiple videos from a single text prompt. We tackle this challenge by…

Recently, vision-language model (VLM) agents have shown promising progress in open-world tasks, where successful task completion often requires multiple turns of visual perception and action execution. However, existing methods still rely…

Visual-Language-Action (VLA) models have demonstrated strong cross-scenario generalization capabilities in various robotic tasks through large-scale pre-training and task-specific fine-tuning. However, their training paradigm mainly relies…

Video generation models produce visually coherent content but struggle with tasks requiring spatial reasoning and multi-step planning. Reinforcement learning (RL) offers a path to improve generalization, but its effectiveness in video…

Subject-driven image generation models face a fundamental trade-off between identity preservation (fidelity) and prompt adherence (editability). While online reinforcement learning (RL), specifically GPRO, offers a promising solution, we…

In user-agent interaction scenarios such as recommendation, brainstorming, and code suggestion, Large Language Models (LLMs) often generate sets of candidate recommendations where the objective is to maximize the collective utility of the…

Existing alignment paradigms remain limited in capturing the pluralistic nature of human values. Overton Pluralism addresses this gap by generating responses with diverse perspectives from a single query. This paper introduces OP-GRPO…

Recent advancements in Reinforcement Learning (RL), particularly Group Relative Policy Optimization (GRPO), have significantly enhanced the reasoning capabilities of Large Language Models. However, applying these problem-centric…

In an era where tool-augmented AI agents are becoming increasingly vital, our findings highlight the ability of Group Relative Policy Optimization (GRPO) to empower SLMs, which are traditionally constrained in tool use. The ability to use…

Recent advances at the intersection of reinforcement learning (RL) and visual intelligence have enabled agents that not only perceive complex visual scenes but also reason, generate, and act within them. This survey offers a critical and…

Large Language Models (LLMs) have made remarkable progress in enhancing step-by-step reasoning through reinforcement learning. However, the Group Relative Policy Optimization (GRPO) algorithm, which relies on sparse reward rules, often…

Reparameterization Policy Gradient (RPG) has emerged as a powerful paradigm for model-based reinforcement learning, enabling high sample efficiency by backpropagating gradients through differentiable dynamics. However, prior RPG approaches…

Recent progress in text-to-music generation has enabled models to synthesize high-quality musical segments, full compositions, and even respond to fine-grained control signals, e.g. chord progressions. State-of-the-art (SOTA) systems differ…

Reinforcement learning has emerged as a promising paradigm for aligning diffusion and flow-matching models with human preferences, yet practitioners face fragmented codebases, model-specific implementations, and engineering complexity. We…

Reinforcement learning in open-ended long-form generation is challenging because reliable reference answers and automatic metrics are often unavailable. Existing rubric-based methods typically rely on pointwise LLM-as-a-judge scoring, but…

Group-based reinforcement learning algorithms such as Group Reward Policy Optimization (GRPO) have proven effective for fine-tuning large language models (LLMs) with human feedback. However, generating and storing multiple responses per…

Recent advances in Large Language Models (LLMs) have transformed text-to-speech (TTS) synthesis, inspiring autoregressive frameworks that represent speech as sequences of discrete codec tokens. Among them, single-codebook TTS LLMs have…