Related papers: ReflectDrive-2: Reinforcement-Learning-Aligned Sel…

End-to-end learning has emerged as a transformative paradigm in autonomous driving. However, the inherently multimodal nature of driving behaviors and the generalization challenges in long-tail scenarios remain critical obstacles to robust…

Recent advances in diffusion models have revolutionized text-guided image editing, yet existing editing methods face critical challenges in hyperparameter identification. To get the reasonable editing performance, these methods often…

Recently, the diffusion model has emerged as a powerful generative technique for robotic policy learning, capable of modeling multi-mode action distributions. Leveraging its capability for end-to-end autonomous driving is a promising…

Achieving safe and stylized trajectory planning in complex real-world scenarios remains a critical challenge for autonomous driving systems. This paper proposes the SDD Planner, a diffusion-based framework designed to effectively reconcile…

End-to-end autonomous driving via Vision-Language-Action (VLA) models demands a precarious balance between high-fidelity trajectory planning and efficient inference. Existing paradigms typically fall short: autoregressive (AR) VLAs are…

Reinforcement learning with stochastic optimal control offers a promising framework for diffusion fine-tuning, where a pre-trained diffusion model is optimized to generate paths that lead to a reward-tilted distribution. While these…

Standard masked discrete diffusion models face limitations in reasoning tasks due to their inability to correct their own mistakes on the masking path. Since they rely on a fixed number of denoising steps, they are unable to adjust their…

We introduce Reflectance Diffusion, a new neural text-to-texture model capable of generating high-fidelity SVBRDF maps from textual descriptions. Our method leverages a tandem neural approach, consisting of two modules, to accurately model…

We present a novel pipeline, ReflectEvo, to demonstrate that small language models (SLMs) can enhance meta introspection through reflection learning. This process iteratively generates self-reflection for self-training, fostering a…

Skills have been introduced to offline reinforcement learning (RL) as temporal abstractions to tackle complex, long-horizon tasks, promoting consistent behavior and enabling meaningful exploration. While skills in offline RL are…

Instructional video editing applies edits to an input video using only text prompts, enabling intuitive natural-language control. Despite rapid progress, most methods still require fixed-length inputs and substantial compute. Meanwhile,…

The goal of diffusion generative models is to align the learned distribution with the real data distribution through gradient score matching. However, inherent limitations in training data quality, modeling strategies, and architectural…

Discrete diffusion models have achieved success in tasks like image generation and masked language modeling but face limitations in controlled content editing. We introduce DICE (Discrete Inversion for Controllable Editing), the first…

We propose TraceRL, a trajectory-aware reinforcement learning framework for diffusion language models (DLMs) that incorporates preferred inference trajectory into post-training, and is applicable across different architectures. Equipped…

Autoregressive language models decode left-to-right with irreversible commitments, limiting revision during multi-step reasoning. We propose \textbf{VDLM}, a modular variable diffusion language model that separates semantic planning from…

Training autonomous agents with sparse rewards is a long-standing problem in online reinforcement learning (RL), due to low data efficiency. Prior work overcomes this challenge by extracting useful knowledge from offline data, often…

Trajectory prediction is critical for autonomous driving, enabling safe and efficient planning in dense, dynamic traffic. Most existing methods optimize prediction accuracy under fixed-length observations. However, real-world driving often…

Visual content generation has advanced from single-image to multi-image workflows, yet existing agents remain largely plan-driven and lack systematic reflection mechanisms to correct mid-trajectory visual errors. To address this limitation,…

World Model-based Reinforcement Learning (WMRL) enables sample efficient policy learning by reducing the need for online interactions which can potentially be costly and unsafe, especially for autonomous driving. However, existing world…

Recent advances in image editing models have shown remarkable progress. A common architectural design couples a multimodal large language model (MLLM) encoder with a diffusion decoder, as seen in systems such as Step1X-Edit and…