Related papers: TRACE: A Self-Improving Framework for Robot Behavi…

Eye-tracking data reveals valuable insights into users' cognitive states but is difficult to analyze due to its structured, non-linguistic nature. While large language models (LLMs) excel at reasoning over text, they struggle with temporal…

Numerous large language model (LLM) agents have been built for different tasks like web navigation and online shopping due to LLM's wide knowledge and text-understanding ability. Among these works, many of them utilize in-context examples…

Visual Language Models (VLMs), with powerful multimodal reasoning capabilities, are gradually integrated into autonomous driving by several automobile manufacturers to enhance planning capability in challenging environments. However, the…

Autonomous driving policy learning with reinforcement learning (RL) is fundamentally limited by low sample efficiency, weak generalization, and a dependence on unsafe online trial-and-error interactions. Although safe RL introduces explicit…

Evaluating open-ended outputs from large language models (LLMs) remains challenging due to the absence of ground truth. Existing metrics rely on final-answer accuracy or surface-level statistics, leaving the reasoning process itself…

Recent advances in large language models (LLMs) and agent system designs have empowered agents with unprecedented levels of capability. However, existing agent benchmarks are showing a trend of rapid ceiling-hitting by newly developed…

The use of Large Language Models (LLMs) for generating Behavior Trees (BTs) has recently gained attention in the robotics community, yet remains in its early stages of development. In this paper, we propose a novel framework that leverages…

Predicting future trajectories for other road agents is an essential task for autonomous vehicles. Established trajectory prediction methods primarily use agent tracks generated by a detection and tracking system and HD map as inputs. In…

Vision language models (VLMs) are increasingly deployed as controllers with access to external tools for complex reasoning and decision-making, yet their effectiveness remains limited by the scarcity of high-quality multimodal trajectories…

Visual Language Models (VLMs) achieve promising results in medical reasoning but struggle with hallucinations, vague descriptions, inconsistent logic and poor localization. To address this, we propose a agent framework named Medical Visual…

Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved performance on tasks such as visual grounding and visual question answering. However, the reasoning processes of these models remain largely opaque;…

To navigate partially observable visual environments, recent VLM agents increasingly internalize world modeling capabilities into their policies via explicit CoT reasoning, enabling them to mentally simulate futures before acting. However,…

Vision-language models demonstrate unprecedented performance and generalization across a wide range of tasks and scenarios. Integrating these foundation models into robotic navigation systems opens pathways toward building general-purpose…

Multi-video event understanding demands models that can locate and attribute query-relevant evidence scattered across long, heterogeneous video corpora. Existing large vision-language models (LVLMs) often underperform in this regime because…

Large Language Model-driven (LLM-driven) social bots pose a growing threat to online discourse by generating human-like content that evades conventional detection. Existing methods suffer from limited detection accuracy due to overreliance…

The alignment of Large Language Models (LLMs) for multi-turn conversations typically relies on reward signals derived from the content of the text. This approach, however, overlooks a rich, complementary source of signal: the dynamics of…

Advancements in large language models (LLMs) have demonstrated their potential in facilitating high-level reasoning, logical reasoning and robotics planning. Recently, LLMs have also been able to generate reward functions for low-level…

The use of Vision-Language Models (VLMs) in automated driving applications is becoming increasingly common, with the aim of leveraging their reasoning and generalisation capabilities to handle long tail scenarios. However, these models…

Vision-Language Models (VLMs) exhibit strong visual reasoning capabilities, yet they still struggle with 3D understanding. In particular, VLMs often fail to infer a text-consistent goal 6D pose of a target object in a 3D scene. However, we…

Large language models (LLMs) have recently gained significant attention as a promising approach to accelerate scientific discovery. However, their application in open-ended scientific domains such as biology remains limited, primarily due…