Related papers: RoboMemArena: A Comprehensive and Challenging Robo…

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…

Referring Multi-Object Tracking (RMOT) aims to track targets specified by language instructions. However, existing RMOT paradigms heavily rely on explicit visual-textual matching and consequently fail to generalize to complex instructions…

Large and small language models have been widely used for robotic task planning. At the same time, vision-language models (VLMs) have successfully tackled problems such as image captioning, scene understanding, and visual question…

Visual reasoning, the capability to interpret visual input in response to implicit text query through multi-step reasoning, remains a challenge for deep learning models due to the lack of relevant benchmarks. Previous work in visual…

Synthetic data generated by video generative models has shown promise for robot learning as a scalable pipeline, but it often suffers from inconsistent action quality due to imperfectly generated videos. Recently, vision-language models…

Large Vision-Language Models (LVLMs) have recently shown great promise in advancing robotics by combining embodied reasoning with robot control. A common approach involves training on embodied reasoning tasks related to robot control using…

Zero-shot object navigation requires agents to locate unseen target objects in unfamiliar environments without prior maps or task-specific training which remains a significant challenge. Although recent advancements in vision-language…

We present VRBench, the first long narrative video benchmark crafted for evaluating large models' multi-step reasoning capabilities, addressing limitations in existing evaluations that overlook temporal reasoning and procedural validity. It…

Large language models (LLMs) are increasingly used in interactive applications, and human evaluation remains the gold standard for assessing their performance in multi-turn conversations. Since human studies are costly, time-consuming, and…

Existing memory benchmarks for LLM agents evaluate explicit recall of facts, yet overlook implicit memory where experience becomes automated behavior without conscious retrieval. This gap is critical: effective assistants must automatically…

Despite remarkable progress in Vision--Language--Action (VLA) models, a central bottleneck remains underexamined: the data infrastructure that underlies embodied learning. In this survey, we argue that future advances in VLA will depend…

With the current surge in spatial reasoning explorations, researchers have made significant progress in understanding indoor scenes, but still struggle with diverse applications such as robotics and autonomous driving. This paper aims to…

Large language models (LLMs) have gained increasing popularity in robotic task planning due to their exceptional abilities in text analytics and generation, as well as their broad knowledge of the world. However, they fall short in decoding…

Long-term memory is essential for LLM agents that operate across multiple sessions, yet existing memory systems treat retrieval infrastructure as fixed: stored content evolves while scoring functions, fusion strategies, and…

Reasoning about Actions and Change (RAC) has historically played a pivotal role in solving foundational AI problems, such as the frame problem. It has driven advancements in AI fields, such as non-monotonic and commonsense reasoning. RAC…

Vision-Language-Action (VLA) models have emerged as a generalist robotic agent. However, existing VLAs are hindered by excessive parameter scales, prohibitive pre-training requirements, and limited applicability to diverse embodiments. To…

Process mining (PM) aims to construct, from event logs, process maps that can help discover, automate, improve, and monitor organizational processes. Robotic process automation (RPA) uses software robots to perform some tasks usually…

Fine-tuning vision-language models (VLMs) on robot teleoperation data to create vision-language-action (VLA) models is a promising paradigm for training generalist policies, but it suffers from a fundamental tradeoff: learning to produce…

Industrial robots are increasingly deployed in contact-rich construction and manufacturing tasks that involve uncertainty and long-horizon execution. While learning-based visuomotor policies offer a promising alternative to open-loop…

Vision-Language Models (VLMs) have revolutionized artificial intelligence and robotics due to their commonsense reasoning capabilities. In robotic manipulation, VLMs are used primarily as high-level planners, but recent work has also…