Huang

The paper reframes Parameter-Efficient Fine-Tuning (PEFT) from a mere cost-saving alternative to a robust architecture for creating persistent, personalized models that layer specific behaviors onto large shared foundation models.

This paper introduces Imaginative Perception Tokens (IPT) to improve spatial reasoning in vision language models.

This paper formalizes the binding problem using information theory and develops a probing method to measure binding information in deep learning representations, demonstrating that binding is crucial for strong visual recognition.

The paper proposes Skill-RM, a unified framework that treats reward modeling as an agentic task to consistently integrate diverse evaluation criteria, achieving superior performance over traditional methods.

MOSAIC is a novel scheduling framework that significantly accelerates Mixture-of-Agents (MoA) workloads by jointly optimizing expert placement and utilizing confidence-aware adaptive aggregation.

The paper demonstrates a novel, self-sustaining computer worm powered by AI agents that generates tailored attack strategies in real-time, representing a significant shift from traditional, vulnerability-exploiting malware.

The paper introduces a Contextual Integrity (CI) framework and a new benchmark (DelegateCI-Bench) to rewrite user queries sent to cloud LLMs, ensuring only task-essential information is retained while preserving utility and maximizing privacy.

The paper introduces RUBAS, a rubric-based reinforcement learning framework that improves agent safety by providing fine-grained, multi-dimensional rewards for complex tool-use scenarios.

This paper presents a unified framework for end-to-end co-design of neural network processors.

The paper proposes DIST-FL, a distributed system using multiple TEEs and an append-only ledger to enhance the security and robustness of federated learning aggregation against server-side adversaries.

The paper proposes DPSR-CG, a novel differentially private selective release mechanism that rigorously maintains strict privacy guarantees while significantly improving model utility compared to existing methods.

The paper proposes OneReason, a framework that enhances the reasoning capability of generative recommendation models by focusing on improving item perception and structuring user behavior into coherent latent interests.

This paper introduces Ghostwriter, an attack framework demonstrating that LLMs are highly vulnerable to adopting misleading viewpoints when provided with fabricated, yet credible-looking, evidence.

The paper introduces PriSrv+, an advanced service discovery protocol that significantly enhances privacy, usability, and efficiency in wireless networks through a novel matchmaking encryption scheme called FEME.

The paper proposes PriSrv, a novel private service discovery protocol that enhances wireless communication security and privacy by enabling fine-grained, multi-layered matching and mutual authentication.

This paper proposes a training-free framework called ReasonAlloc to mitigate inference bottlenecks in large language models by recasting decoding-time key-value compression as a hierarchical budget allocation problem.

This paper investigates the downlink performance of CoMS-NOMA networks from a system-level perspective.

This paper introduces CORE-Bench, a comprehensive benchmark for code retrieval in agentic coding.

This paper proposes CompRank, a token-efficient reranking framework for large language models that reduces redundant computation and achieves strong reranking performance.

This paper introduces Agents-K1, an end-to-end knowledge orchestration pipeline that converts raw documents into agent-native scientific knowledge graphs.