相关论文: RoboGolf: Mastering Real-World Minigolf with a Ref…

A pressing question when designing intelligent autonomous systems is how to integrate the various subsystems concerned with complementary tasks. More specifically, robotic vision must provide task-relevant information about the environment…

Task planning for robotic manipulation with large language models (LLMs) is an emerging area. Prior approaches rely on specialized models, fine tuning, or prompt tuning, and often operate in an open loop manner without robust environmental…

Vision-Language-Action (VLA) models have demonstrated potential in autonomous driving. However, two critical challenges hinder their development: (1) Existing VLA architectures are typically based on imitation learning in open-loop setup…

Visual Language Models (VLMs) are powerful generative tools but often produce factually inaccurate outputs due to a lack of robust reasoning capabilities. While extensive research has been conducted on integrating external knowledge for…

Evaluating robot control policies is difficult: real-world testing is costly, and handcrafted simulators require manual effort to improve in realism and generality. We propose a world-model-based policy evaluation environment (WorldGym), an…

Deeply understanding sports requires an intricate blend of fine-grained visual perception and rule-based reasoning - a challenge that pushes the limits of current multimodal models. To succeed, models must master three critical…

Vision-language models (VLMs) have shown strong performance on static visual understanding, yet they still struggle with dynamic spatial reasoning that requires imagining how scenes evolve under egocentric motion. Recent efforts address…

Video temporal grounding (VTG) aims to locate precise segments in videos based on language queries, which is a fundamental challenge in video understanding. While recent Multimodal Large Language Models (MLLMs) have shown promise in…

While Large Language Models (LLMs) demonstrate remarkable capabilities, they remain susceptible to sophisticated, multi-step jailbreak attacks that circumvent conventional surface-level safety alignment by exploiting the internal generation…

The advancement of foundation models fosters new initiatives for policy learning in achieving safe and efficient autonomous driving. However, a critical bottleneck lies in the manual engineering of reward functions and training curricula…

Small Language Models (SLMs) are a cost-effective alternative to Large Language Models (LLMs), but often struggle with complex reasoning due to their limited capacity and a tendency to produce mistakes or inconsistent answers during…

The evolution of Remote Sensing Vision-Language Models(RS-VLMs) emphasizes the importance of transitioning from perception-centric recognition toward high-level deductive reasoning to enhance cognitive reliability in complex spatial tasks.…

The deployment of artificial intelligence models at the edge is increasingly critical for autonomous robots operating in GPS-denied environments where local, resource-efficient reasoning is essential. This work demonstrates the feasibility…

An important function of autonomous microrobots is the ability to perform robust movement over terrain. This paper explores an edge ML approach to microrobot locomotion, allowing for on-device, lower latency control under compute, memory,…

Current deep reinforcement learning (RL) approaches incorporate minimal prior knowledge about the environment, limiting computational and sample efficiency. \textit{Objects} provide a succinct and causal description of the world, and many…

Recent "Thinking with Video" approaches use Video Generation Models (VGMs) for visual reasoning by producing temporally coherent Chain-of-Frames as reasoning artifacts. Even strong VGMs, however, exhibit two recurring failure modes on…

While large language models (LLMs) have demonstrated impressive performance in question-answering tasks, their performance is limited when the questions require knowledge that is not included in the model's training data and can only be…

Contemporary AI systems achieve extraordinary performance yet remain opaque and non-verifiable, creating a crisis of trust for safety-critical deployment. We introduce MathLedger, a substrate for verifiable machine cognition that integrates…

This paper introduces a new hybrid framework that combines Reinforcement Learning (RL) and Large Language Models (LLMs) to improve robotic manipulation tasks. By utilizing RL for accurate low-level control and LLMs for high level task…

Reinforcement Learning is a promising tool for learning complex policies even in fast-moving and object-interactive domains where human teleoperation or hard-coded policies might fail. To effectively reflect this challenging category of…