Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Li

Li

50 indexed papers

Recent (6 mo)
50
With code
0
Influential cites
0
Benchmarked
0

Publications per year

50
26

Top categories

AI×21NLP×7Info Retrieval×7Vision×6Multiagent×5Audio and Speech Processing×4Signal Processing×4Crypto×4

Frequent co-authors

Han Li2×
Zhiheng Fu2×
Zixu Li2×
Zhiwei Chen2×
Yupeng Hu2×
Tianhao Guo2×

Research Timeline

2026
Hybrid Computer Use: A Unified Programmatic, Semantic, and Visual Interface for General Agents

The paper introduces Hybrid Computer Use (HCU), a unified interface for general agents that combines programmatic, semantic, and visual interaction channels.

KITE: Retrieval as a Decision Procedure for Long-Term Conversational Memory

This paper introduces KITE, a vector-free framework for memory retrieval in LLM agents that formulates memory retrieval as an explicit decision procedure.

Understanding LLM-Based Bargaining of Driving Agents in Mixed-Autonomy Traffic

This paper develops a framework to study bargaining between autonomous and human-driven vehicles using large language models.

Evidence-grounded large language models guide perovskite solar cell design and optimization

Develops a benchmark and language model to improve scientific reasoning in perovskite photovoltaics.

AmbiHTMLBench: A Benchmark for HTML-based Visually Rich Document parsing

This paper introduces a benchmark for evaluating document parsing systems that output HTML, which is more suitable for editable and reusable documents.

SUMONE: A Simple and Efficient Summarizer for Plug-and-Play Agent Memory

This paper introduces SumOne, a standalone summarizer for long-horizon language-model agents that preserves information in agent histories through masked reconstruction.

EviSeek: An Evidence-Centric Agentic Framework for Embodied Active Information Seeking

EviSeek is a training-free framework that makes question-derived evidence demands explicit acquisition objectives.

BEAKER: An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical Laboratories

This paper introduces BEAKER, a benchmark for evaluating embodied AI capabilities in self-driving chemical laboratories.

FrontierPhysics: Evaluating Agents for End-to-End Physics Research

The paper introduces FrontierPhysics, an end-to-end benchmark for evaluating AI agents in physics research.

PSGAgent: Enhancing MLLMs' Dynamic Visual Perception for Panoptic Scene Graph Generation via Agentic Reasoning

The paper proposes PSGAgent, a framework that enhances visual perception for Panoptic Scene Graph generation through a think-act-observe loop.

WeLM-Image: A Unified Image Generation Model towards Visual Intelligence

WeLM-Image is a unified image foundation model for text-to-image generation, instruction-guided editing, and multi-reference synthesis.

EnvOpt: Automated Optimization for Agent Environments

This paper proposes a method called EnvOpt for optimizing stationary environments for large language models, reducing their cost and improving their success.

Selective Retrieval Routing for Multi-Violation Knowledge Graph Repair

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: Token-Efficient Wavelet Foundation Models for Biosignals

PhysioWave-T is a token-efficient wavelet foundation model family for EEG, ECG, and sEMG.

Flex-RSI: Benchmarking Recursive Self-Improvement of Frontier Agents

The paper introduces Flex-RSI, a benchmark for evaluating the recursive self-improvement of agents on vision and robotics tasks.

On Agentic Manipulation Policies

This paper shows that generalist AI models can control manipulators more reliably than specialist policies.

CoReMem: Cost-Internalizing Memory for Successive Coding Tasks with Prospective Valuation

This paper introduces Coding-Repository Memory (CoReMem), a framework that guides memory design and actor adaptation for coding agents.

Consistent Video-to-Video Translation via Explicit Correspondences

The paper introduces vid2vid-long, a correspondence-based approach to improve long-range temporal consistency in video-to-video translation.

KuaiRecV2: Benchmarking Large-Scale Continual Learning for Diversified and Multi-task Recommendation

This paper introduces KuaiRecV2, a benchmark for recommender systems that addresses inconsistencies between offline and online evaluations.

AntEmbed: Dual-Mode Multimodal Embedding Model for Efficient and Fine-Grained Retrieval

The paper proposes AntEmbed, a dual-mode multimodal embedding model for efficient retrieval and reasoning-enhanced fine-grained matching.

Highlighted terms show continued research focus across papers

Papers

cs.AIcs.CLcs.SEEmpiricalRecentNov 12, 2026

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.

View →
cs.CVcs.AIcs.GREmpirical
Recent
Nov 12, 2026

Consistent Video-to-Video Translation via Explicit Correspondences

Gaurav Parmar, Zhengqi Li, Richard Zhang, Jun-Yan Zhu +3 more

The paper introduces vid2vid-long, a correspondence-based approach to improve long-range temporal consistency in video-to-video translation.

View →
cs.IREmpiricalRecentNov 12, 2026

KuaiRecV2: Benchmarking Large-Scale Continual Learning for Diversified and Multi-task Recommendation

Chenxu Li, Shuchang Liu, Hantao Shu, Wei Yuan +14 more

This paper introduces KuaiRecV2, a benchmark for recommender systems that addresses inconsistencies between offline and online evaluations.

View →
cs.IREmpiricalRecentNov 12, 2026

AntEmbed: Dual-Mode Multimodal Embedding Model for Efficient and Fine-Grained Retrieval

Kehang Jia, Teng Liu, Juntao Li, Hua Chen +3 more

The paper proposes AntEmbed, a dual-mode multimodal embedding model for efficient retrieval and reasoning-enhanced fine-grained matching.

View →
cs.AIEmpiricalRecentNov 6, 2026

PhysioWave-T: Token-Efficient Wavelet Foundation Models for Biosignals

Yanlong Chen, Simone Benatti, Luca Benini, Cuntai Guan +1 more

PhysioWave-T is a token-efficient wavelet foundation model family for EEG, ECG, and sEMG.

View →
cs.AIcs.CVcs.ROEmpiricalRecentNov 6, 2026

Flex-RSI: Benchmarking Recursive Self-Improvement of Frontier Agents

Jingdong Zhang, Jionghao Wang, Zhengming Yu, Yancheng Cai +18 more

The paper introduces Flex-RSI, a benchmark for evaluating the recursive self-improvement of agents on vision and robotics tasks.

View →
cs.ROcs.AIcs.CVEmpiricalRecentNov 6, 2026

On Agentic Manipulation Policies

Chen Chen, Omid Bagherieh, Naveen Nikamanth Appiah Balaji, Jesse T. Gonzalez +9 more

This paper shows that generalist AI models can control manipulators more reliably than specialist policies.

View →
cs.CVcs.AIEmpiricalRecentNov 5, 2026

PSGAgent: Enhancing MLLMs' Dynamic Visual Perception for Panoptic Scene Graph Generation via Agentic Reasoning

Qingyun Liu, Yuankun Liu, Jiaye Feng, Jie Huang +5 more

The paper proposes PSGAgent, a framework that enhances visual perception for Panoptic Scene Graph generation through a think-act-observe loop.

View →
cs.CVcs.AIEmpiricalRecentNov 5, 2026

WeLM-Image: A Unified Image Generation Model towards Visual Intelligence

Canmiao Fu, Chen Li, Guohui Zhang, Hao Lu +12 more

WeLM-Image is a unified image foundation model for text-to-image generation, instruction-guided editing, and multi-reference synthesis.

View →
cs.AIcs.CLEmpiricalRecentNov 5, 2026

EnvOpt: Automated Optimization for Agent Environments

Mingxuan Li, Huanzhi Mao, Qiuyang Mang, Hanchen Li +2 more

This paper proposes a method called EnvOpt for optimizing stationary environments for large language models, reducing their cost and improving their success.

View →
cs.DBcs.AIEmpiricalRecentNov 5, 2026

Selective Retrieval Routing for Multi-Violation Knowledge Graph Repair

Tung-Wei Lin, Gabe Fierro, Han Li, Tianzhen Hong +2 more

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.

View →
cs.AIEmpiricalRecentNov 4, 2026

AmbiHTMLBench: A Benchmark for HTML-based Visually Rich Document parsing

Boyu Niu, Yingjie Xiong, Shurui Li, Linhan Pang +7 more

This paper introduces a benchmark for evaluating document parsing systems that output HTML, which is more suitable for editable and reusable documents.

View →
cs.AIEmpiricalRecentNov 4, 2026

SUMONE: A Simple and Efficient Summarizer for Plug-and-Play Agent Memory

Jizhe Zhang, Ang Li, Chenheng Zhang, Yisen Wang

This paper introduces SumOne, a standalone summarizer for long-horizon language-model agents that preserves information in agent histories through masked reconstruction.

View →
cs.AIEmpiricalRecentNov 4, 2026

EviSeek: An Evidence-Centric Agentic Framework for Embodied Active Information Seeking

Jintao Li, Zhiyong Cao, Baihua Xiao, Yu Bai +1 more

EviSeek is a training-free framework that makes question-derived evidence demands explicit acquisition objectives.

View →
cs.AIEmpiricalRecentNov 4, 2026

BEAKER: An Expert-Curated Benchmark for Embodied Brains in Self-Driving Chemical Laboratories

Fei Lin, Tengchao Zhang, Ziyang Gong, Xiaotong Yu +14 more

This paper introduces BEAKER, a benchmark for evaluating embodied AI capabilities in self-driving chemical laboratories.

View →
cs.AIEmpiricalRecentNov 4, 2026

FrontierPhysics: Evaluating Agents for End-to-End Physics Research

Bingran You, Wenjun Ke, Ria Rosenauer, Bo Liu +68 more

The paper introduces FrontierPhysics, an end-to-end benchmark for evaluating AI agents in physics research.

View →
cs.AIEmpiricalRecentOct 31, 2026

Evidence-grounded large language models guide perovskite solar cell design and optimization

YanKai Chen, Zhi Wan, ZiHao Li, Tao Jing

Develops a benchmark and language model to improve scientific reasoning in perovskite photovoltaics.

View →
cs.HCcs.CLEmpiricalRecentOct 30, 2026

Hybrid Computer Use: A Unified Programmatic, Semantic, and Visual Interface for General Agents

Haoqing Wang, Xiaoyi Zhang, Sicheng Fan, Zhexin Zhang +4 more

The paper introduces Hybrid Computer Use (HCU), a unified interface for general agents that combines programmatic, semantic, and visual interaction channels.

View →
cs.IREmpiricalRecentOct 30, 2026

KITE: Retrieval as a Decision Procedure for Long-Term Conversational Memory

Feng Li, Kailun Tan, Zhibo Zhou, Youxiang Wang +4 more

This paper introduces KITE, a vector-free framework for memory retrieval in LLM agents that formulates memory retrieval as an explicit decision procedure.

View →
physics.soc-phcs.MAEmpiricalRecentOct 30, 2026

Understanding LLM-Based Bargaining of Driving Agents in Mixed-Autonomy Traffic

Lingxiao Zhou, Di Chen, Jia Li

This paper develops a framework to study bargaining between autonomous and human-driven vehicles using large language models.

View →