Jun Zhang

The paper introduces MEntA, a highly query-efficient and surrogate-free membership inference attack that uses natural-language entailment to detect if a specific document was used by a RAG system, achieving high accuracy with only five queries.

The paper introduces Code-QA-Bench, a novel framework that rigorously separates genuine code reasoning from mere documentation memorization in repository-level code understanding benchmarks.

The paper introduces Code-QA-Bench, a novel framework that rigorously separates genuine code reasoning from mere documentation memorization in repository-level code understanding benchmarks.

The paper proposes SWE-Future, a method for forecasting future coding tasks in software repositories and uses the forecasts to synthesize a dataset for coding-agents.

This paper proposes WISPA, a framework for automated terminal-side resource management in wireless networks based on large language model agents.

This paper introduces MeanFlowNFT, a method that applies reinforcement learning to MeanFlow generators to improve performance and consistency.

This paper proposes a statistical framework for designing task-aware multiple-input multiple-output (MIMO) precoders in future wireless networks using statistical channel state information and training-set feature statistics.

This paper investigates the performance impact of non-square uniform planar arrays (UPAs) on extremely large-scale multiple-input multiple-output (XL-MIMO) systems, deriving effective beamfocusing distances, asymptotic effective degrees of freedom, and bounds for distance estimation and position error.

The paper derives an explicit representation for the Euclidean dual of Hyperderivative Reed-Solomon codes and studies reverse self-dual HRS codes.