Related papers: PACEvolve: Enabling Long-Horizon Progress-Aware Co…

Large language models (LLMs) have been one of the most important discoveries in machine learning in recent years. LLM-based artificial intelligence (AI) assistants, such as ChatGPT, have consistently attracted the attention from…

Large Language Models (LLMs) exhibit remarkable human-like predictive capabilities. However, it is challenging to deploy LLMs to provide efficient and adaptive inference services at the edge. This paper proposes a novel Cloud-Edge…

Large language models (LLMs) are increasingly deployed as part of compound AI systems that coordinate multiple modules (e.g., retrievers, tools, verifiers) over long-horizon workflows. Recent approaches that propagate textual feedback…

This paper introduces ACTLLM (Action Consistency Tuned Large Language Model), a novel approach for robot manipulation in dynamic environments. Traditional vision-based systems often struggle to learn visual representations that excel in…

While Large Language Models (LLMs) form the cornerstone of sequential decision-making agent development, they have inherent limitations in high-frequency decision tasks. Existing research mainly focuses on discrete embodied decision…

Current alignment methods for Large Language Models (LLMs) rely on compressing vast amounts of human preference data into static, absolute reward functions, leading to data scarcity, noise sensitivity, and training instability. We introduce…

The advent of large language models (LLMs), such as GPT, Gemini, and DeepSeek, has significantly advanced natural language processing, giving rise to sophisticated chatbots capable of diverse language-related tasks. The transition from…

Large Language Models (LLMs) have demonstrated impressive capabilities in code completion tasks, where they assist developers by predicting and generating new code in real-time. However, existing LLM-based code completion systems primarily…

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…

LLM-based agents show strong potential for long-horizon reasoning, yet their context size is limited by deployment factors (e.g., memory, latency, and cost), yielding a constrained context budget. As interaction histories grow, this induces…

Large Language Models (LLMs) present a promising frontier in robotic task planning by leveraging extensive human knowledge. Nevertheless, the current literature often overlooks the critical aspects of robots' adaptability and error…

The adaptation of large-scale vision-language models (VLMs) to downstream tasks with limited labeled data remains a significant challenge. While parameter-efficient prompt learning methods offer a promising path, they often suffer from…

Planning in complex environments requires an agent to efficiently query a world model to find a feasible sequence of actions from start to goal. Recent work has shown that Large Language Models (LLMs), with their rich prior knowledge and…

Frontier model developers aim to train models continually to possess emergent, diverse capabilities. To extend capabilities, the current pre-training and post-training paradigm requires manually starting training runs with static datasets…

Recent advances in large Vision-Language Models (VLMs) have provided rich semantic understanding that empowers drones to search for open-set objects via natural language instructions. However, prior systems struggle to integrate VLMs into…

Large language models (LLMs) have achieved remarkable success in text-based tasks but often struggle to provide actionable guidance in real-world physical environments. This is because of their inability to recognize their limited…

The prevailing paradigm in Automated Heuristic Design (AHD) typically relies on the assumption that a single, fixed algorithm can effectively navigate the shifting dynamics of a combinatorial search. This static approach often proves…

Prompt engineering is a new paradigm for enhancing the performance of trained neural network models. For optimizing text-style prompts, existing methods usually individually operate small portions of a text step by step, which either breaks…

Multi-turn dialogues are essential in many real-world applications of large language models, such as chatbots and virtual assistants. As conversation histories become longer, existing large language models face increasing computational and…

Large Language Models (LLMs) have achieved remarkable capabilities, yet their improvement methods remain fundamentally constrained by human design. We present Self-Developing, a framework that enables LLMs to autonomously discover,…