相关论文: TOPReward: Token Probabilities as Hidden Zero-Shot…
Current robot autonomy struggles to operate beyond the assumed Operational Design Domain (ODD), the specific set of conditions and environments in which the system is designed to function, while the real-world is rife with uncertainties…
Current vision-language models (VLMs) still exhibit inferior performance on knowledge-intensive tasks, primarily due to the challenge of accurately encoding all the associations between visual objects and scenes to their corresponding…
Video reasoning has emerged as a critical capability for multimodal large language models (MLLMs), requiring models to move beyond static perception toward coherent understanding of temporal dynamics in complex scenes. Yet existing MLLMs…
Vision-language-action (VLA) models represent a promising direction for developing general-purpose robotic systems, demonstrating the ability to combine visual understanding, language comprehension, and action generation. However,…
Specifying reward signals that allow agents to learn complex behaviors is a long-standing challenge in reinforcement learning. A promising approach is to extract preferences for behaviors from unlabeled videos, which are widely available on…
Vision-Language Navigation (VLN) enables robots to follow natural-language instructions in visually grounded environments, serving as a key capability for embodied robotic systems. Recent Vision-Language-Action (VLA) models have…
Reinforcement learning (RL) with continuous time and state/action spaces is often data-intensive and brittle under nuisance variability and shift, motivating methods that exploit value-preserving structures to stabilize and improve…
Vision-Language-Action (VLA) models have shown great potential for embodied AI by integrating visual perception, language understanding, and action execution. In real-time deployment, these models must process continuous visual streams,…
Reinforcement Learning (RL) agents require the specification of a reward signal for learning behaviours. However, introduction of corrupt or stochastic rewards can yield high variance in learning. Such corruption may be a direct result of…
Designing effective reward functions remains a fundamental challenge in reinforcement learning (RL), as it often requires extensive human effort and domain expertise. While RL from human feedback has been successful in aligning agents with…
For the majority of the machine learning community, the expensive nature of collecting high-quality human-annotated data and the inability to efficiently finetune very large state-of-the-art pretrained models on limited compute are major…
Reinforcement learning (RL) shows promise for enhancing LLM agentic reasoning, yet sparse terminal rewards hinder fine-grained optimization. Process reward modeling offers an alternative but incurs high computational costs, reward hacking…
Reinforcement learning with verifiable rewards has significantly advanced the reasoning capabilities of large language models, yet how to explicitly steer training toward exploration or exploitation remains an open problem. We introduce…
Reward models play an essential role in training vision-language models (VLMs) by assessing output quality to enable aligning with human preferences. Despite their importance, the research community lacks comprehensive open benchmarks for…
Large Language Models (LLMs) have excelled in various tasks but perform better in high-resource scenarios, which presents challenges in low-resource scenarios. Data scarcity and the inherent difficulty of adapting LLMs to specific tasks…
To meet the requirements of real-world applications, it is essential to control generations of large language models (LLMs). Prior research has tried to introduce reinforcement learning (RL) into controllable text generation while most…
Existing Video Anomaly Detection (VAD) methods typically rely on task-specific training, leading to strong domain dependency and high training costs. Moreover, most existing methods output only scalar anomaly scores, providing limited…
Self-paced reinforcement learning (RL) aims to improve the data efficiency of learning by automatically creating sequences, namely curricula, of probability distributions over contexts. However, existing techniques for self-paced RL fail in…
Training robust reasoning vision-language models (VLMs) in rare domains (such as geospatial) is fundamentally constrained by supervision scarcity. While raw geospatial imagery is abundant, the amount of task-direct supervision falls far…
Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a promising framework for improving reasoning abilities in Large Language Models (LLMs). However, policy optimized with binary verification prone to overlook…