相关论文: Learning Self-Correction in Vision-Language Models…

The generation of factually incorrect objects, commonly known as object hallucination, remains a persistent challenge in Large Vision-Language Models (LVLMs). Current approaches to address this issue - ranging from expensive data-driven…

Reinforcement learning (RL) is essential for enhancing the complex reasoning capabilities of large language models (LLMs). However, existing RL training pipelines are computationally inefficient and resource-intensive, with the rollout…

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,…

Despite significant progress, Vision-Language Models (VLMs) still struggle with complex visual reasoning, where multi-step dependencies cause early errors to cascade through the reasoning chain. Existing post-training paradigms are limited:…

Reinforcement Learning (RL) has shown promise in improving the reasoning abilities of Large Language Models (LLMs). However, the specific challenges of adapting RL to multimodal data and formats remain relatively unexplored. In this work,…

Designing reward functions for continuous-control robotics often leads to subtle misalignments or reward hacking, especially in complex tasks. Preference-based RL mitigates some of these pitfalls by learning rewards from comparative…

Reinforcement learning (RL) enables high-frequency, closed-loop control for robotic manipulation, but scaling to long-horizon tasks with sparse or imperfect rewards remains difficult due to inefficient exploration and poor credit…

Vision-Language Models (VLMs) often yield inconsistent descriptions of the same object across viewpoints, hindering the ability of embodied agents to construct consistent semantic representations over time. Previous methods resolved…

The development of autonomous agents for complex, long-horizon tasks is a central goal in AI. However, dominant training paradigms face a critical limitation: reinforcement learning (RL) methods that optimize solely for final task success…

Recent studies on reasoning models explore the meta-awareness of language models, the ability to know how to think by itself. We argue that large reasoning models lack this meta-awareness property by proving severe misalignment between true…

Vision-Language-Action (VLA) models excel in robotic manipulation but are constrained by their heavy reliance on expert demonstrations, leading to demonstration bias and limiting performance. Reinforcement learning (RL) is a vital…

Large Vision-Language Models (LVLMs) have experienced significant advancements in recent years. However, their performance still falls short in tasks requiring deep visual perception, such as identifying subtle differences between images. A…

Vision-Language-Action models have recently emerged as a powerful paradigm for general-purpose robot learning, enabling agents to map visual observations and natural-language instructions into executable robotic actions. Though popular,…

While recent advancements in reasoning optimization have significantly enhanced the capabilities of large language models (LLMs), existing efforts to improve reasoning have been limited to solving mathematical problems and focusing on…

Reinforcement learning (RL) for large language models (LLMs) is increasingly bottlenecked by rollout (generation), where long output sequence lengths make attention and KV-cache memory dominate end-to-end step time. FP8 offers an attractive…

Reinforcement Learning with Verifiable Rewards (RLVR) is an effective paradigm for improving the reasoning capabilities of large language models. However, existing RLVR methods utilize rollouts in an indiscriminate and short-horizon manner:…

Advancing Machine Learning (ML)-based perception models for autonomous systems necessitates addressing weak spots within the models, particularly in challenging Operational Design Domains (ODDs). These are environmental operating conditions…

Dropout is a widely used regularization technique which improves the generalization ability of a model by randomly dropping neurons. In light of this, we propose Dropout Prompt Learning, which aims for applying dropout to improve the…

Personalized driving refers to an autonomous vehicle's ability to adapt its driving behavior or control strategies to match individual users' preferences and driving styles while maintaining safety and comfort standards. However, existing…

Combining Large Language Models (LLMs) with Reinforcement Learning (RL) enables agents to interpret language instructions more effectively for task execution. However, LLMs typically lack direct perception of the physical environment, which…