9 accepted papers
Human-to-robot handover is a fundamental capability in human-robot interaction, critical for effective collaboration in service and assistive domains. Despite recent progress, ensuring both reliability and safety-particularly collision-free interaction with the human hand-remains a major challenge,
Dexterous functional tool-use grasping is essential for effective robotic manipulation of tools. However, existing approaches face significant challenges in efficiently constructing large-scale datasets and ensuring generalizability to everyday object scales. These issues primarily arise from size m
Reinforcement Learning with Human Feedback (RLHF) is the key to the success of large language models (LLMs) in recent years. In this work, we first introduce the concepts of knowledge breadth and knowledge depth, which measure the comprehensiveness and depth of an LLM or knowledge source respectivel…
Model Predictive Control (MPC) has been demonstrated to be effective in continuous control tasks. When a world model and a value function are available, planning a sequence of actions ahead of time leads to a better policy. Existing methods typically obtain the value function and the corresponding p…
Large language models have demonstrated outstanding performance in various natural language processing tasks, but their security capabilities in the financial domain have not been explored, and their performance on complex tasks like financial agent remains unknown. This paper presents FinEval, a be…
Modern code generation has made significant strides in functional correctness and execution efficiency. However, these systems often overlook a critical dimension in real-world software development: \textit{maintainability}. To handle dynamic requirements with minimal rework, we propose \textbf{Main…
Although fine-tuning Large Language Models (LLMs) with multilingual data can rapidly enhance the multilingual capabilities of LLMs, they still exhibit a performance gap between the dominant language (e.g., English) and non-dominant ones due to the imbalance of training data across languages. To furt…
Large language models (LLMs) have demonstrated striking reasoning capability. Recent works have shown the benefits to LLMs from fine-tuning golden-standard Chain-of-Thought (CoT) rationales or using them as correct examples in few-shot prompting. While humans can indeed imitate correct examples, lea…
Most existing light field (LF) disparity estimation algorithms focus on handling occlusion, texture-less or other areas that harm LF structure to improve accuracy, while ignoring other potential modeling ideas. In this paper, we propose a novel idea called Bad Pixel (BadPix) correction for method mo…