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

Gen Li

9 indexed papers

Recent (6 mo)
9
With code
0
Influential cites
0
Benchmarked
0

Publications per year

9
26

Top categories

AI×6Vision×2Multiagent×1Stats ML×1ML×1Stats Theory×1Robotics×1

Frequent co-authors

Yuwei Miao4×
Yunsheng Zeng4×
Xiandong Li4×
Yujin Wang4×
Siyu Chen4×
Luning Wang4×

Research Timeline

2026
C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis Reasoning

C-MIG is a novel retrieval-augmented generation framework that uses multi-view information gain to improve clinical diagnosis reasoning by providing richer, more nuanced reward signals than existing methods.

EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization in Open-Ended QA

The paper proposes EAPO, an entropy-driven adaptive weighting method that dynamically adjusts the influence of positive samples during policy optimization to improve both response diversity and stability in open-ended QA.

C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis Reasoning

C-MIG is a novel retrieval-augmented generation framework that uses multi-view information gain to improve clinical diagnosis reasoning by providing richer, more nuanced reward signals than existing methods.

EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization in Open-Ended QA

The paper proposes EAPO, an entropy-driven adaptive weighting method that dynamically adjusts the influence of positive samples during policy optimization to improve both response diversity and stability in open-ended QA.

OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning

OccamToken introduces a training-free, adaptive token pruning framework that replaces fixed token budgets with relative evidence testing against a register-based reference, significantly improving VLM efficiency while maintaining high accuracy.

OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning

OccamToken introduces a training-free, adaptive token pruning framework that replaces fixed token budgets with relative evidence testing against a register-based reference, significantly improving VLM efficiency while maintaining high accuracy.

GIVE: Grounding Human Gestures in Vision-Language-Action Models

This paper proposes GIVE, an approach that enhances VLA models with human gesture understanding to improve Human-Robot Interaction.

Diffusion Models Adapt to Low-Dimensional Structure Under Flexible Coefficient Choices

The paper proves that diffusion models adapt to low-dimensional structure robustly across various update coefficient choices.

GenWorld: Empirically Grounded Urban Simulation Infrastructure for Scalable LLM-Agent Studies

The paper presents GenWorld, an urban simulation infrastructure for LLM-agent studies, combining a synthetic city, agent-environment interface, and offline compilation of LLM-derived signals.

Highlighted terms show continued research focus across papers

Papers

cs.MAEmpiricalRecentJun 26, 2026

GenWorld: Empirically Grounded Urban Simulation Infrastructure for Scalable LLM-Agent Studies

Gen Li, Jieyuan Lan, Pengcheng Xu, Zongyuan Wu +2 more

The paper presents GenWorld, an urban simulation infrastructure for LLM-agent studies, combining a synthetic city, agent-environment interface, and offline compilation of LLM-derived signals.

View →
stat.MLcs.LGmath.STTheoretical
Recent
Jun 22, 2026

Diffusion Models Adapt to Low-Dimensional Structure Under Flexible Coefficient Choices

Changxiao Cai, Yuchen Jiao, Gen Li

The paper proves that diffusion models adapt to low-dimensional structure robustly across various update coefficient choices.

View →
cs.ROEmpiricalRecentJun 11, 2026

GIVE: Grounding Human Gestures in Vision-Language-Action Models

Pengfei Liu, Gen Li, Junqiao Fan, Boyu Ma +3 more

This paper proposes GIVE, an approach that enhances VLA models with human gesture understanding to improve Human-Robot Interaction.

View →
cs.CVcs.AIRecentMay 28, 2026

OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning

Geng Li, Guohao Chen, Ting Chen, Shilin Shan +5 more

OccamToken introduces a training-free, adaptive token pruning framework that replaces fixed token budgets with relative evidence testing against a register-based reference, significantly improving VLM…

View →
cs.CVcs.AIRecentMay 28, 2026

OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning

Geng Li, Guohao Chen, Ting Chen, Shilin Shan +5 more

OccamToken introduces a training-free, adaptive token pruning framework that replaces fixed token budgets with relative evidence testing against a register-based reference, significantly improving VLM…

View →
cs.AIRecentMay 27, 2026

C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis Reasoning

Yuwei Miao, Gen Li, Yunsheng Zeng, Xiandong Li +7 more

C-MIG is a novel retrieval-augmented generation framework that uses multi-view information gain to improve clinical diagnosis reasoning by providing richer, more nuanced reward signals than existing m…

View →
cs.AIRecentMay 27, 2026

EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization in Open-Ended QA

Yunsheng Zeng, Gen Li, Yuwei Miao, Xiandong Li +7 more

The paper proposes EAPO, an entropy-driven adaptive weighting method that dynamically adjusts the influence of positive samples during policy optimization to improve both response diversity and stabil…

View →
cs.AIRecentMay 27, 2026

C-MIG: Multi-view Information Gain-based Retrieval-Augmented Generation for Clinical Diagnosis Reasoning

Yuwei Miao, Gen Li, Yunsheng Zeng, Xiandong Li +7 more

C-MIG is a novel retrieval-augmented generation framework that uses multi-view information gain to improve clinical diagnosis reasoning by providing richer, more nuanced reward signals than existing m…

View →
cs.AIRecentMay 27, 2026

EAPO: Entropy-Driven Adaptive Positive-Negative Sample Weighting for Policy Optimization in Open-Ended QA

Yunsheng Zeng, Gen Li, Yuwei Miao, Xiandong Li +7 more

The paper proposes EAPO, an entropy-driven adaptive weighting method that dynamically adjusts the influence of positive samples during policy optimization to improve both response diversity and stabil…

View →