Related papers: PhySe-RPO: Physics and Semantics Guided Relative P…

Diffusion policies are a powerful paradigm for robotic control, but fine-tuning them with human preferences is fundamentally challenged by the multi-step structure of the denoising process. To overcome this, we introduce a Unified Markov…

Few-step diffusion models enable efficient high-resolution image synthesis but struggle to align with specific downstream objectives due to limitations of existing reinforcement learning (RL) methods in low-step regimes with limited state…

Minimally invasive and robot-assisted surgery relies heavily on endoscopic imaging, yet surgical smoke produced by electrocautery and vessel-sealing instruments can severely degrade visual perception and hinder vision-based functionalities.…

Robotic manipulation tasks often rely on static cameras for perception, which can limit flexibility, particularly in scenarios like robotic surgery and cluttered environments where mounting static cameras is impractical. Ideally, robots…

Recent advances in large language models (LLMs) have shown strong reasoning capabilities through large-scale pretraining and post-training reinforcement learning, demonstrated by DeepSeek-R1. However, current post-training methods, such as…

Large Protein Language Models have shown strong potential for generative protein design, yet they frequently produce structural hallucinations, generating sequences with high linguistic likelihood that fold into thermodynamically unstable…

The recent success and openness of DeepSeek-R1 have brought widespread attention to Group Relative Policy Optimization (GRPO) as a reinforcement learning method for large reasoning models (LRMs). In this work, we analyze the GRPO objective…

Proximal Policy Optimization (PPO) is widely used in reinforcement learning due to its strong empirical performance, yet it lacks formal guarantees for policy improvement and convergence. PPO's clipped surrogate objective is motivated by a…

Deep Reinforcement Learning (DRL) algorithms often require a large amount of data and struggle in sparse-reward domains with long planning horizons and multiple sub-goals. In this paper, we propose a neuro-symbolic extension of Proximal…

The recent remarkable progress of deep reinforcement learning (DRL) stands on regularization of policy for stable and efficient learning. A popular method, named proximal policy optimization (PPO), has been introduced for this purpose. PPO…

Diffusion-based policies have gained growing popularity in solving a wide range of decision-making tasks due to their superior expressiveness and controllable generation during inference. However, effectively training large diffusion…

Direct Preference Optimization (DPO) aligns text-to-image (T2I) generation models with human preferences using pairwise preference data. Although substantial resources are expended in collecting and labeling datasets, a critical aspect is…

Latent diffusion models are the state-of-the-art for synthetic image generation. To align these models with human preferences, training the models using reinforcement learning on human feedback is crucial. Black et. al 2024 introduced…

Diffusion policies have demonstrated strong performance in generative modeling, making them promising for robotic manipulation guided by natural language instructions. However, generalizing language-conditioned diffusion policies to…

Humans naturally develop preferences for how manipulation tasks should be performed, which are often subtle, personal, and difficult to articulate. Although it is important for robots to account for these preferences to increase…

Diffusion models have demonstrated remarkable generative capabilities in image processing tasks. We propose a Sparse condition Temporal Rewighted Integrated Distribution Estimation guided diffusion model (STRIDE) for sparse-view CT…

Diffusion large language models (dLLMs) offer a promising route to parallel and efficient text generation, but improving their reasoning ability requires effective post-training. Reinforcement learning with verifiable rewards (RLVR) is a…

Aligning large language models with human preferences has emerged as a critical focus in language modeling research. Yet, integrating preference learning into Text-to-Image (T2I) generative models is still relatively uncharted territory.…

Diffusion models have emerged as powerful priors for single-image restoration, but their application to zero-shot video restoration suffers from temporal inconsistencies due to the stochastic nature of sampling and complexity of…

Diffusion models have demonstrated remarkable success in various visual generation tasks, including image, video, and 3D content generation. Preference optimization (PO) is a prominent and growing area of research that aims to align these…