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

Guo

50 indexed papers

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

Publications per year

50
26

Top categories

AI×20ML×10NLP×9Distributed×6Vision×6Software Eng.×3Signal Processing×3Info Theory×3

Frequent co-authors

Tianhao Guo2×
Xianzhong Li2×
Hao Luo2×
Wei Wang2×
Yiwen Guo2×
Weidong Cai2×

Research Timeline

2026
From GAN-Based Models to GPT-5: A Taxonomy-Guided Study of Human Performance in Detecting Deepfake Face Images

This paper investigates human performance in detecting deepfake face images and evaluates the effectiveness of general-purpose and model-specific training.

LAW: Unifying Language, Action, and World Modeling for Agentic Physical Intelligence

This paper presents a closed-loop framework called LAW that integrates language reasoning, action generation, and world modeling for long-horizon manipulation tasks.

gKSM: GPU Memory Deduplication at Driver Layer for Serverless LLM Inference

gKSM is a transparent GPU memory deduplication framework for serverless LLM inference that reduces GPU memory usage and improves throughput.

Comparing Computer Use Behavior Across Multiple Levels of Abstraction

This paper presents MAP, a hierarchical semantic representation and annotation pipeline for comparing interaction traces across tasks, interfaces, and input modalities.

ZKPU: Zero-Knowledge Processing Unit for Heterogeneous Workloads

This paper presents a Zero-Knowledge Processing Unit (ZKPU) that accelerates zero-knowledge proofs for both curve-based and hash-based protocols.

Factual Access States in Diffusion Language Models: From Mechanism to Knowledge Editing and Retrieval

This paper introduces a new framework for understanding how autoregressive and masked diffusion language models access factual knowledge.

S$^2$-MAS: A Society-Scale Multi-Agent Simulation Framework with 500 Million Household Persona Agents

The authors introduce S$^2$-MAS, a society-scale multi-agent simulation framework that models household decisions and financial behaviors.

SMART: Semantic Segment Mapping and Assessment of Recognition Transcripts with Contextual Rubrics

The paper proposes a framework for traceable semantic evaluation and targeted ASR correction, called SMART, which maps reference-hypothesis discrepancies into coherent segments and assigns explicit consequence labels.

Deterministic Constructions of Reed-Solomon Codes Beyond the Johnson Bound

The paper presents deterministic constructions of Reed-Solomon codes that are list-decodable beyond the Johnson radius.

DexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection

This paper introduces DexPort, a portable data-collection interface for high-DoF robot hands that records both commanded joint targets and measured joint states.

Beyond Discrete Tokens: Preserving Numerical Continuity in Medical Vision-Language Models

This paper presents HAD-VLM, a unified vision-language model for prompt-conditioned quantitative ultrasound measurement.

The Complexity of Value Optimization in Sporadic Task Systems

This paper studies the complexity of Value-based Task Selection (VTS) in real-time systems.

GuardRAG: A Post-Retrieval Defense against Poisoning Attacks in Retrieval-Augmented Generation

A post-retrieval defense, GuardRAG, is proposed to mitigate corpus poisoning attacks on Large Language Models.

PipeLink: Contract-Guided Linking of GPU Kernel Components

PipeLink is a contract-guided linker for GPU kernel components that enables the creation of new compositions by linking separately compiled components.

Negative Results for Reciprocity-Based Over-the-Air Split Learning Under Channel Aging: Stability, Alignment, and Geometry

This paper investigates the performance of various methods in reciprocity-based over-the-air split learning.

Deep Holes and Aperture: Sign Laws for the Empirical Correlation of Lattice-Sampled Random Wave Fields

This paper studies the properties of Gaussian random wave fields on lattices and their implications for signal processing and communication systems.

Post-SQLFix: Property-Guided Repair of LLM-Generated SQL with Runtime Verification

The paper proposes a framework called Post-SQLFix to repair errors in Text-to-SQL queries generated by Large Language Models.

RadioTraj3D: Height-Aware Adaptive Sampling for 3D Radio-Map Reconstruction from Ultra-Sparse Trajectories

This paper proposes RadioTraj3D, a method for constructing three-dimensional radio maps using building-height information to guide measurement selection and reconstruction.

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.

On the Reliability of Majority-Vote Pseudo-Labels in Test-Time Reinforcement Learning

This paper improves test-time reinforcement learning by reducing errors and adapting to unlabeled target-domain data.

Highlighted terms show continued research focus across papers

Papers

cs.AIEmpiricalRecentNov 6, 2026

On the Reliability of Majority-Vote Pseudo-Labels in Test-Time Reinforcement Learning

Haoyu Wang, Ru Wang, Yuanyuan Wang, Jiaxian Guo +1 more

This paper improves test-time reinforcement learning by reducing errors and adapting to unlabeled target-domain data.

View →
cs.AIEmpiricalRecent
Nov 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.SEEmpiricalRecentOct 30, 2026

Post-SQLFix: Property-Guided Repair of LLM-Generated SQL with Runtime Verification

Zhihao Guo, Zonghan Wu, Yilei Shao, Haizhou Du +3 more

The paper proposes a framework called Post-SQLFix to repair errors in Text-to-SQL queries generated by Large Language Models.

View →
eess.SPEmpiricalRecentOct 30, 2026

RadioTraj3D: Height-Aware Adaptive Sampling for 3D Radio-Map Reconstruction from Ultra-Sparse Trajectories

Zixuan Guo, Xiucheng Wang, Wenshuo Chen, Conghao Zhou +3 more

This paper proposes RadioTraj3D, a method for constructing three-dimensional radio maps using building-height information to guide measurement selection and reconstruction.

View →
cs.DCEmpiricalRecentOct 27, 2026

PipeLink: Contract-Guided Linking of GPU Kernel Components

Jize Guo, Xupeng Miao

PipeLink is a contract-guided linker for GPU kernel components that enables the creation of new compositions by linking separately compiled components.

View →
eess.SPcs.ITEmpiricalRecentOct 27, 2026

Negative Results for Reciprocity-Based Over-the-Air Split Learning Under Channel Aging: Stability, Alignment, and Geometry

Tianhao Guo, Xianzhong Li, Hao Luo

This paper investigates the performance of various methods in reciprocity-based over-the-air split learning.

View →
cs.ITeess.SPEmpiricalRecentOct 27, 2026

Deep Holes and Aperture: Sign Laws for the Empirical Correlation of Lattice-Sampled Random Wave Fields

Tianhao Guo, Hao Luo, Xianzhong Li, Yuzhi Yang

This paper studies the properties of Gaussian random wave fields on lattices and their implications for signal processing and communication systems.

View →
cs.CCcs.DSTheoreticalRecentOct 26, 2026

The Complexity of Value Optimization in Sporadic Task Systems

Christopher Harbourne, Nathan Fisher, Kecheng Yang, Pontus Ekberg +2 more

This paper studies the complexity of Value-based Task Selection (VTS) in real-time systems.

View →
cs.CREmpiricalRecentOct 26, 2026

GuardRAG: A Post-Retrieval Defense against Poisoning Attacks in Retrieval-Augmented Generation

Linghui Jiao, Kang Wei, Fushuo Huo, Ruijie Zhao +4 more

A post-retrieval defense, GuardRAG, is proposed to mitigate corpus poisoning attacks on Large Language Models.

View →
cs.ROcs.AIcs.LGEmpiricalRecentOct 23, 2026

DexPort: A Hand-Held Skill Interface for Dexterous Hand Data Collection

Amber Xie, Jiawei Fu, Xiaofeng Guo, Carmelo Sferrazza +2 more

This paper introduces DexPort, a portable data-collection interface for high-DoF robot hands that records both commanded joint targets and measured joint states.

View →
cs.CVcs.AIEmpiricalRecentOct 23, 2026

Beyond Discrete Tokens: Preserving Numerical Continuity in Medical Vision-Language Models

Dianye Huang, Jiamei Guo, Yue Zhou, Mingde Li +4 more

This paper presents HAD-VLM, a unified vision-language model for prompt-conditioned quantitative ultrasound measurement.

View →
cs.CCTheoreticalRecentOct 22, 2026

Deterministic Constructions of Reed-Solomon Codes Beyond the Johnson Bound

Abhranil Chatterjee, Sumanta Ghosh, Zeyu Guo, Rohit Gurjar +1 more

The paper presents deterministic constructions of Reed-Solomon codes that are list-decodable beyond the Johnson radius.

View →
cs.AREmpiricalRecentOct 20, 2026

ZKPU: Zero-Knowledge Processing Unit for Heterogeneous Workloads

Jonathan Ku, Changchun Zhou, Jiawen Wu, Sangouk Jeon +7 more

This paper presents a Zero-Knowledge Processing Unit (ZKPU) that accelerates zero-knowledge proofs for both curve-based and hash-based protocols.

View →
cs.CLcs.AIcs.IREmpiricalRecentOct 20, 2026

Factual Access States in Diffusion Language Models: From Mechanism to Knowledge Editing and Retrieval

Yuchen Guo, Zhuoyuan Mao, Yiwen Guo

This paper introduces a new framework for understanding how autoregressive and masked diffusion language models access factual knowledge.

View →
cs.MAcs.AIEmpiricalRecentOct 20, 2026

S$^2$-MAS: A Society-Scale Multi-Agent Simulation Framework with 500 Million Household Persona Agents

Yang Li, Di Wan, Yike Wang, Chujun He +11 more

The authors introduce S$^2$-MAS, a society-scale multi-agent simulation framework that models household decisions and financial behaviors.

View →
cs.CLcs.AIeess.ASEmpiricalRecentOct 20, 2026

SMART: Semantic Segment Mapping and Assessment of Recognition Transcripts with Contextual Rubrics

Xiaoyu Gu, Chencheng Wang, Fuyang Li, Yu Xi +3 more

The paper proposes a framework for traceable semantic evaluation and targeted ASR correction, called SMART, which maps reference-hypothesis discrepancies into coherent segments and assigns explicit co…

View →
cs.HCEmpiricalRecentOct 19, 2026

Comparing Computer Use Behavior Across Multiple Levels of Abstraction

Ananya Gubbi Mohanbabu, Rosiana Natalie, Anhong Guo, Amy Pavel

This paper presents MAP, a hierarchical semantic representation and annotation pipeline for comparing interaction traces across tasks, interfaces, and input modalities.

View →
cs.OSEmpiricalRecentOct 18, 2026

gKSM: GPU Memory Deduplication at Driver Layer for Serverless LLM Inference

Shuheng Gao, Fan Guo, Yongkun Li, Ziye Yue +2 more

gKSM is a transparent GPU memory deduplication framework for serverless LLM inference that reduces GPU memory usage and improves throughput.

View →
cs.CVcs.CRcs.HCEmpiricalRecentOct 16, 2026

From GAN-Based Models to GPT-5: A Taxonomy-Guided Study of Human Performance in Detecting Deepfake Face Images

Zhiqing Guo, Lixin Jia, Luning Sun, Xiaowei Chen +6 more

This paper investigates human performance in detecting deepfake face images and evaluates the effectiveness of general-purpose and model-specific training.

View →
cs.ROEmpiricalRecentOct 16, 2026

LAW: Unifying Language, Action, and World Modeling for Agentic Physical Intelligence

Jiajun Cao, Kai Tang, Bohua Zhang, Zezhong Qian +16 more

This paper presents a closed-loop framework called LAW that integrates language reasoning, action generation, and world modeling for long-horizon manipulation tasks.

View →