Qing Wang

The paper proposes Look One Step Ahead (LOSA), a novel framework that enables efficient, privacy-preserving, and robust service provisioning in dynamic air-ground integrated networks by decoupling planning into a look-ahead phase and a real-time execution phase.

The paper introduces Safety Bottleneck Regularization (SBR), a novel defense mechanism that anchors LLM safety by constraining the unembedding layer, effectively preventing harmful fine-tuning (HFT) even when other defenses fail.

OrchJail introduces an orchestration-guided fuzzing framework to systematically jailbreak tool-calling text-to-image agents by exploiting unsafe multi-step tool-orchestration patterns.

Reflect-Guard enhances LLM safety classifiers by integrating logical self-reflection, significantly improving detection of sophisticated adversarial jailbreak prompts.

The paper develops a novel deep reinforcement learning framework, SMamba-DDPG, to accurately model vehicle-type-specific pedestrian crash avoidance behavior, finding that pedestrians react faster and more cautiously to automated vehicles (AVs) than to human-driven vehicles (HDVs).

This paper analyzes the decoding process of masked diffusion models for graph-to-text generation, finding that structural fine-tuning disrupts natural entity-first generation and proposing a structural decoding method to fix it.

MemPro introduces a system-level evolution framework that treats the entire memory construction-retrieval pipeline as an evolvable program, significantly improving long-horizon agent performance over fixed-pipeline baselines.

The paper introduces PROBE, an optimization framework that guides LLM agents in structure-based drug design by performing controlled 'probe edits' to assess how molecular changes affect both binding affinity and druggability simultaneously.

The paper introduces DrugClaw, a multi-agent system, and DrugAudit, a new benchmark, demonstrating that DrugClaw excels at answering drug-related questions by grounding answers in primary regulatory sources.

UniD$^3$ is a novel Knowledge Graph-enhanced RAG framework that processes vast biomedical literature to systematically extract, organize, and validate comprehensive drug-disease knowledge, achieving high accuracy in structured data generation.

The paper introduces Trust Region On-Policy Distillation (TrOPD), a robust method that stabilizes the on-policy distillation of large language models by restricting training to regions where teacher supervision is reliable.

The paper proposes a hierarchical framework, PHF (Practice-Habitus-Field), inspired by Bourdieu's Theory of Practice, to improve LLM personalization by modeling user behaviors at three distinct levels.

The paper introduces CRAB-Bench and RUSE, a rigorous evaluation framework that tests LLM agents on complex, interdependent tasks with realistic human user interactions, revealing significant performance gaps in current models.