Related papers: LaViPlan : Language-Guided Visual Path Planning wi…

Vision-and-Language Navigation (VLN) requires agents to navigate photo-realistic environments following natural language instructions. Current methods predominantly rely on imitation learning, which suffers from limited generalization and…

The rapid growth of autonomous driving datasets has enabled the scaling of powerful motion forecasting models. While large-scale pretraining provides strong performance, the standard imitation objective may not fully capture the complex…

Reinforcement learning (RL) has become a key technique for enhancing the reasoning abilities of large language models (LLMs), with policy-gradient algorithms dominating the post-training stage because of their efficiency and effectiveness.…

Reinforcement learning (RL) can refine the reasoning abilities of large language models (LLMs), but critically depends on a key prerequisite: the LLM can already generate high-utility reasoning paths with non-negligible probability. For…

Vision-language models (VLMs) have shown remarkable performance in various robotic tasks, as they can perceive visual information and understand natural language instructions. However, when applied to robotics, VLMs remain subject to a…

Maintaining good driving behavior in out-of-distribution scenarios remains a critical challenge in autonomous driving. A promising direction is to leverage the generalist knowledge and reasoning capabilities of large-language models by…

Vision-language navigation (VLN) requires intelligent agents to navigate environments by interpreting linguistic instructions alongside visual observations, serving as a cornerstone task in Embodied AI. Current VLN research for unmanned…

With the recent emergence of foundation models trained on internet-scale data and demonstrating remarkable generalization capabilities, such foundation models have become more widely adopted, leading to an expanding range of application…

Vision-Language Models (VLMs) often suffer from visual hallucinations: generating things that are not consistent with visual inputs and language shortcuts, where they skip the visual part and just rely on text priors. These issues arise…

Multimodal large language models via reinforcement learning (RL) have demonstrated remarkable capabilities in complex visual reasoning tasks, yet they remain limited in long-horizon multimodal scenarios, often suffering from visual…

Reinforcement Learning with Verifiable Rewards (RLVR) has recently emerged as a powerful paradigm for facilitating the self-improvement of large language models (LLMs), particularly in the domain of complex reasoning tasks. However,…

Large language models (LLMs) excel in tasks like question answering and dialogue, but complex tasks requiring interaction, such as negotiation and persuasion, require additional long-horizon reasoning and planning. Reinforcement learning…

The advancement of embodied intelligence is accelerating the integration of robots into daily life as human assistants. This evolution requires robots to not only interpret high-level instructions and plan tasks but also perceive and adapt…

Contrastively-trained Vision-Language Models (VLMs) like CLIP have become the de facto approach for discriminative vision-language representation learning. However, these models have limited language understanding, often exhibiting a "bag…

Recent large language models (LLMs) are promising for making decisions in grounded environments. However, LLMs frequently fail in complex decision-making tasks due to the misalignment between the pre-trained knowledge in LLMs and the actual…

Reinforcement learning from verifiable rewards (RLVR) has recently been extended from text-only LLMs to vision-language models (VLMs) to elicit long-chain multimodal reasoning. However, RLVR-trained VLMs still exhibit two persistent failure…

This technical report presents our solution for the RoboSense Challenge at IROS 2025, which evaluates Vision-Language Models (VLMs) on autonomous driving scene understanding across perception, prediction, planning, and corruption detection…

Visual Place Recognition (VPR) often fails under extreme environmental changes and perceptual aliasing. Furthermore, standard systems cannot perform "blind" localization from verbal descriptions alone, a capability needed for applications…

Vision Language Models (VLMs) show strong potential for visual planning but struggle with precise spatial and long-horizon reasoning, while Planning Domain Definition Language (PDDL) planners excel at formal long-horizon planning but cannot…

Process-supervised reward models serve as a fine-grained function that provides detailed step-wise feedback to model responses, facilitating effective selection of reasoning trajectories for complex tasks. Despite its advantages, evaluation…