Related papers: Generation Navigator: A State-Aware Agentic Framew…

Text-to-Image (T2I) generation has achieved remarkable progress in recent years. Meanwhile, reinforcement learning methods, particularly those based on Group Relative Policy Optimization (GRPO), have attracted widespread attention and been…

Recent progress in generative models has stimulated significant innovations in many fields, such as image generation and chatbots. Despite their success, these models often produce sketchy and misleading solutions for complex multi-agent…

While reinforcement learning has advanced the alignment of text-to-image (T2I) models, state-of-the-art policy gradient methods are still hampered by training instability and high variance, hindering convergence speed and compromising image…

While text-to-image (T2I) models can synthesize high-quality images, their performance degrades significantly when prompted with novel or out-of-distribution (OOD) entities due to inherent knowledge cutoffs. We introduce World-To-Image, a…

We introduce GenAgent, unifying visual understanding and generation through an agentic multimodal model. Unlike unified models that face expensive training costs and understanding-generation trade-offs, GenAgent decouples these capabilities…

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…

Multimodal text-to-image generation remains constrained by the difficulty of maintaining semantic alignment and professional-level detail across diverse visual domains. We propose a multi-agent reinforcement learning framework that…

Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning, persistent state, long-horizon consistency, and causal…

Reinforcement learning (RL) has garnered increasing attention in text-to-image (T2I) generation. However, most existing RL approaches are tailored to either diffusion models or autoregressive models, overlooking an important alternative:…

Text-to-image generation tasks have driven remarkable advances in diverse media applications, yet most focus on single-turn scenarios and struggle with iterative, multi-turn creative tasks. Recent dialogue-based systems attempt to bridge…

Unified models capable of interleaved generation have emerged as a promising paradigm, with the community increasingly converging on autoregressive modeling for text and flow matching for image generation. To advance this direction, we…

Group-based reinforcement learning (RL) methods have achieved remarkable success in improving the performance of large language models (LLMs) and have been rapidly extended to agentic tasks. However, their credit assignment relies heavily…

Recent image generation models have shown strong capabilities in generating high-fidelity and photorealistic images. However, they are fundamentally constrained by frozen internal knowledge, thus often failing on real-world scenarios that…

Recent text-to-image models produce high-quality results but still struggle with precise visual control, balancing multimodal inputs, and requiring extensive training for complex multimodal image generation. To address these limitations, we…

Text-to-image generation has evolved beyond single monolithic models to complex multi-component pipelines. These combine fine-tuned generators, adapters, upscaling blocks and even editing steps, leading to significant improvements in image…

Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this…

Multi-step LLM agents in interactive environments represent a crucial step toward long-horizon decision-making. To train such agents, group-based reinforcement learning is widely adopted, which reinforces trajectories with higher relative…

The default paradigm of post-training text-to-image generators includes post-hoc selection of generated images, and subsequent training with one reward model to align the generator to the reward, typically user preference. This discards…

Reinforcement learning, particularly Group Relative Policy Optimization (GRPO), has emerged as an effective framework for post-training visual generative models with human preference signals. However, its effectiveness is fundamentally…

Text-to-image (T2I) models have achieved remarkable progress, yet they continue to struggle with complex prompts that require simultaneously handling multiple objects, relations, and attributes. Existing inference-time strategies, such as…