Related papers: Towards Unified Multimodal Interleaved Generation …

Generative models, particularly diffusion models, have achieved remarkable success in density estimation for multimodal data, drawing significant interest from the reinforcement learning (RL) community, especially in policy modeling in…

The field of advanced text-to-image generation is witnessing the emergence of unified frameworks that integrate powerful text encoders, such as CLIP and T5, with Diffusion Transformer backbones. Although there have been efforts to control…

Recent studies have demonstrated the efficacy of integrating Group Relative Policy Optimization (GRPO) into flow matching models, particularly for text-to-image and text-to-video generation. However, we find that directly applying these…

Recent progress in multimodal large language models has led to strong performance on reasoning tasks, but these improvements largely rely on high-quality annotated data or teacher-model distillation, both of which are costly and difficult…

State-of-the-art large multi-modal models (LMMs) face challenges when processing high-resolution images, as these inputs are converted into enormous visual tokens, many of which are irrelevant to the downstream task. In this paper, we…

Reinforcement learning from verifiable rewards (RLVR), especially with Group Relative Policy Optimization (GRPO), has shown strong potential for improving the reasoning capabilities of large vision-language models (LVLMs). However, in…

Despite their sophisticated general-purpose capabilities, Large Language Models (LLMs) often fail to align with diverse individual preferences because standard post-training methods, like Reinforcement Learning with Human Feedback (RLHF),…

Group Relative Policy Optimization (GRPO) has proven to be an effective tool for post-training language models (LMs). However, AI systems are increasingly expressed as modular programs that mix together multiple LM calls with distinct…

Flow-matching policies have emerged as a powerful paradigm for generalist robotics. These models are trained to imitate an action chunk, conditioned on sensor observations and textual instructions. Often, training demonstrations are…

Large Language Models (LLMs) have shown promise in solving complex mathematical problems, yet they still fall short of producing accurate and consistent solutions. Reinforcement Learning (RL) is a framework for aligning these models with…

Unified Multimodal Models (UMMs) excel in general tasks but struggle to bridge the gap between personalized understanding and generation. Prior works largely rely on implicit token-level alignment via supervised fine-tuning, which fails to…

Multimodal Large Language Models (MLLMs) have gained significant traction for their ability to process diverse input data types and generate coherent, contextually relevant outputs across various applications. While supervised fine-tuning…

Vision--language models (VLMs) are increasingly aligned via Group Relative Policy Optimization (GRPO)-style training. However, relying solely on terminal outcome rewards yields sparse credit assignment in multi-step reasoning, weakening the…

Creating an intelligent conversational system that understands vision and language is one of the ultimate goals in Artificial Intelligence (AI)~\cite{winograd1972understanding}. Extensive research has focused on vision-to-language…

The recently developed discrete diffusion models perform extraordinarily well in the text-to-image task, showing significant promise for handling the multi-modality signals. In this work, we harness these traits and present a unified…

Multimodal language models now integrate text, audio, and video for unified reasoning. Yet existing RL post-training pipelines treat all input signals as equally relevant, ignoring which modalities each task actually requires. This…

Unified multimodal large language models such as Show-o and Janus have achieved strong performance across both generation and understanding tasks. However, these models typically rely on large-scale datasets and require substantial…

Reinforcement learning based post-training paradigms for Video Large Language Models (VideoLLMs) have achieved significant success by optimizing for visual-semantic tasks such as captioning or VideoQA. However, while these approaches…

Text and time series data offer complementary views of financial markets: news articles provide narrative context about company events, while stock prices reflect how markets react to those events. However, despite their complementary…

We present UniGen-1.5, a unified multimodal large language model (MLLM) for advanced image understanding, generation and editing. Building upon UniGen, we comprehensively enhance the model architecture and training pipeline to strengthen…