相关论文: ReMoT: Reinforcement Learning with Motion Contrast…

Real world deployments often expose modern object recognition models to domain shifts that precipitate a severe drop in accuracy. Such shifts encompass (i) variations in low level image statistics, (ii) changes in object pose and viewpoint,…

Retargeting human kinematic reference motion onto a robot's morphology remains a formidable challenge. Existing methods often produce physical inconsistencies, such as foot sliding, self-collisions, or dynamically infeasible motions, which…

Vision language models (VLMs) have shown impressive capabilities across a variety of tasks, from logical reasoning to visual understanding. This opens the door to richer interaction with the world, for example robotic control. However, VLMs…

Reinforcement learning methods as a promising technique have achieved superior results in the motion planning of free-floating space robots. However, due to the increase in planning dimension and the intensification of system dynamics…

While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where…

We introduce MotionRL, the first approach to utilize Multi-Reward Reinforcement Learning (RL) for optimizing text-to-motion generation tasks and aligning them with human preferences. Previous works focused on improving numerical performance…

Vision-Language models (VLMs) that use contrastive language-image pre-training have shown promising zero-shot classification performance. However, their performance on imbalanced dataset is relatively poor, where the distribution of classes…

Text-guided motion editing enables high-level semantic control and iterative modifications beyond traditional keyframe animation. Existing methods rely on limited pre-collected training triplets, which severely hinders their versatility in…

Recent advances in Chain-of-Thought (CoT) prompting have substantially improved the reasoning capabilities of Large Language Models (LLMs). However, these methods often suffer from overthinking, leading to unnecessarily lengthy or redundant…

We study the theoretical aspects of Reinforced Language Models (RLMs) from a bi-objective optimization perspective. Specifically, we consider the RLMs as a Pareto optimization problem that maximizes the two conflicting objectives, i.e.,…

With respect to improving the reasoning accuracy of LLMs, the representative reinforcement learning (RL) method GRPO faces failure due to insignificant reward variance, while verification methods based on process reward models (PRMs) suffer…

Despite the recent advancements in offline reinforcement learning via supervised learning (RvS) and the success of the decision transformer (DT) architecture in various domains, DTs have fallen short in several challenging benchmarks. The…

Despite rapid advancements in large language models (LLMs), the token-level autoregressive nature constrains their complex reasoning capabilities. To enhance LLM reasoning, inference-time techniques, including…

Visual Reinforcement Learning is a popular and powerful framework that takes full advantage of the Deep Learning breakthrough. It is known that variations in input domains (e.g., different panorama colors due to seasonal changes) or task…

Designing effective reward functions remains a major challenge in reinforcement learning (RL), often requiring considerable human expertise and iterative refinement. Recent advances leverage Large Language Models (LLMs) for automated reward…

Despite the extensive adoption of machine learning on the task of visual object tracking, recent learning-based approaches have largely overlooked the fact that visual tracking is a sequence-level task in its nature; they rely heavily on…

Reinforcement learning with verifiable rewards (RLVR) has become a key technique for enhancing LLMs' reasoning abilities, yet its data inefficiency remains a major bottleneck. To address this critical yet challenging issue, we present a…

Owing to their ability to extract relevant spatio-temporal video embeddings, Vision Transformers (ViTs) are currently the best performing models in video action understanding. However, their generalization over domains or datasets is…

Vision-language alignment in multi-modal large language models (MLLMs) relies on supervised fine-tuning (SFT) or reinforcement learning (RL). To align multi-modal large language models (MLLMs) in the post-training stage, supervised…

Recent advances in video reward models and post-training strategies have improved text-to-video (T2V) generation. While these models typically assess visual quality, motion quality, and text alignment, they often overlook key structural…