XingYu

The paper introduces Constraint-Guided Semantic Testing (ConSeT), a novel framework that systematically finds critical, pre-authentication vulnerabilities in 5G User Equipment (UE) by exploiting semantically inconsistent, yet syntactically valid, RRC messages.

TrajGuard is a novel, training-free defense framework that detects jailbreaks by monitoring the progressive risk signals embedded in the hidden-state trajectories of tokens during the LLM decoding process, achieving a high defense rate with low latency.

The paper proposes ADAM, a novel and highly effective privacy attack that systematically extracts sensitive data from LLM agent memory by adaptively querying the victim agent's memory based on data distribution and entropy.

The paper argues that current search agents often verify existing knowledge rather than genuinely searching, and introduces LiveBrowseComp, a new benchmark to measure true evidence-driven discovery.

The paper introduces MemCog, a Memory-as-Cognition system that integrates memory access directly into the reasoning process, significantly improving agent performance, especially in proactive memory retrieval tasks.

VCap introduces a novel Witness-Adjudicator reward mechanism that provides highly precise, factually grounded feedback for visual captioning, enabling state-of-the-art performance in RL-trained multimodal models.

The paper introduces Semantic Flow Regularization (SFR), an auxiliary objective that significantly improves the diversity and quality of LLM responses when fine-tuned for specific styles or personas, without increasing deployment cost.

The paper proposes TCP-MCP, a co-evolution framework that jointly optimizes agent prompts and communication topologies to design highly efficient and effective multi-agent systems.

KairosAgent is a novel agentic framework that combines Large Language Models (LLMs) for semantic reasoning and Time Series Foundation Models (TSFMs) for numerical forecasting, achieving superior multimodal time series prediction.

OptSkills introduces an archetype-centric skill learning agent that improves the generalization of solving optimization problems from natural language by clustering problems by underlying archetypes and distilling reusable workflow skills.

UniScale proposes a unified framework that jointly optimizes model routing and test-time scaling to achieve a superior, fine-grained quality-cost trade-off for large language model inference.

TROPHIES introduces a unified framework to jointly reconstruct dynamic humans, static scenes, and camera poses from multi-view videos, achieving globally consistent and physically plausible 4D reconstructions.

This paper demonstrates that fusing multi-viewpoint data from multiple satellites significantly enhances the accuracy of space object detection in congested LEO constellations, establishing multi-view fusion as an effective strategy.