Guo
50 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper investigates human performance in detecting deepfake face images and evaluates the effectiveness of general-purpose and model-specific training.
This paper presents a closed-loop framework called LAW that integrates language reasoning, action generation, and world modeling for long-horizon manipulation tasks.
gKSM is a transparent GPU memory deduplication framework for serverless LLM inference that reduces GPU memory usage and improves throughput.
This paper presents MAP, a hierarchical semantic representation and annotation pipeline for comparing interaction traces across tasks, interfaces, and input modalities.
This paper presents a Zero-Knowledge Processing Unit (ZKPU) that accelerates zero-knowledge proofs for both curve-based and hash-based protocols.
This paper introduces a new framework for understanding how autoregressive and masked diffusion language models access factual knowledge.
The authors introduce S$^2$-MAS, a society-scale multi-agent simulation framework that models household decisions and financial behaviors.
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.
The paper presents deterministic constructions of Reed-Solomon codes that are list-decodable beyond the Johnson radius.
This paper introduces DexPort, a portable data-collection interface for high-DoF robot hands that records both commanded joint targets and measured joint states.
This paper presents HAD-VLM, a unified vision-language model for prompt-conditioned quantitative ultrasound measurement.
This paper studies the complexity of Value-based Task Selection (VTS) in real-time systems.
A post-retrieval defense, GuardRAG, is proposed to mitigate corpus poisoning attacks on Large Language Models.
PipeLink is a contract-guided linker for GPU kernel components that enables the creation of new compositions by linking separately compiled components.
This paper investigates the performance of various methods in reciprocity-based over-the-air split learning.
This paper studies the properties of Gaussian random wave fields on lattices and their implications for signal processing and communication systems.
The paper proposes a framework called Post-SQLFix to repair errors in Text-to-SQL queries generated by Large Language Models.
This paper proposes RadioTraj3D, a method for constructing three-dimensional radio maps using building-height information to guide measurement selection and reconstruction.
The paper introduces FrontierPhysics, an end-to-end benchmark for evaluating AI agents in physics research.
This paper improves test-time reinforcement learning by reducing errors and adapting to unlabeled target-domain data.
Papers
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.