Li
50 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces Hybrid Computer Use (HCU), a unified interface for general agents that combines programmatic, semantic, and visual interaction channels.
This paper introduces KITE, a vector-free framework for memory retrieval in LLM agents that formulates memory retrieval as an explicit decision procedure.
This paper develops a framework to study bargaining between autonomous and human-driven vehicles using large language models.
Develops a benchmark and language model to improve scientific reasoning in perovskite photovoltaics.
This paper introduces a benchmark for evaluating document parsing systems that output HTML, which is more suitable for editable and reusable documents.
This paper introduces SumOne, a standalone summarizer for long-horizon language-model agents that preserves information in agent histories through masked reconstruction.
EviSeek is a training-free framework that makes question-derived evidence demands explicit acquisition objectives.
This paper introduces BEAKER, a benchmark for evaluating embodied AI capabilities in self-driving chemical laboratories.
The paper introduces FrontierPhysics, an end-to-end benchmark for evaluating AI agents in physics research.
The paper proposes PSGAgent, a framework that enhances visual perception for Panoptic Scene Graph generation through a think-act-observe loop.
WeLM-Image is a unified image foundation model for text-to-image generation, instruction-guided editing, and multi-reference synthesis.
This paper proposes a method called EnvOpt for optimizing stationary environments for large language models, reducing their cost and improving their success.
A framework for selective retrieval in iterative graph repair is proposed to improve knowledge graph repair with the help of a researcher agent and a router.
PhysioWave-T is a token-efficient wavelet foundation model family for EEG, ECG, and sEMG.
The paper introduces Flex-RSI, a benchmark for evaluating the recursive self-improvement of agents on vision and robotics tasks.
This paper shows that generalist AI models can control manipulators more reliably than specialist policies.
This paper introduces Coding-Repository Memory (CoReMem), a framework that guides memory design and actor adaptation for coding agents.
The paper introduces vid2vid-long, a correspondence-based approach to improve long-range temporal consistency in video-to-video translation.
This paper introduces KuaiRecV2, a benchmark for recommender systems that addresses inconsistencies between offline and online evaluations.
The paper proposes AntEmbed, a dual-mode multimodal embedding model for efficient retrieval and reasoning-enhanced fine-grained matching.
Papers
CoReMem: Cost-Internalizing Memory for Successive Coding Tasks with Prospective Valuation
Peiwen Li, Harshit Verma, Sophia Zhou, Haiwen Wang +5 more
This paper introduces Coding-Repository Memory (CoReMem), a framework that guides memory design and actor adaptation for coding agents.