Wei Chen

This paper systematically performs a differential fault analysis (DFA) on the lightweight block cipher Lilliput, demonstrating that it is significantly vulnerable to practical fault attacks even under relaxed adversarial assumptions.

FedDetox introduces a robust framework that sanitizes toxic data on edge devices during federated learning to maintain the safety alignment of Small Language Models (SLMs) without sacrificing utility.

The paper proposes Multi-Adapter Representation Interventions via Energy Calibration (MARI), a method that adaptively adjusts the strength and direction of interventions across different inputs to improve alignment without degrading general model capabilities.

The paper proposes the LLM-GNN Soft Prompt Framework (LGSPF) to enhance fraud detection by directly integrating graph structure and semantic information into LLMs, achieving state-of-the-art performance.

The paper proposes Meta-Team, an experience-driven framework that enables multi-agent systems (MAS) to collaboratively self-evolve by transforming complex execution experiences into reusable improvements for agent behaviors and coordination.

EviLink addresses the ambiguity of schema linking in Text-to-SQL by treating it as an uncertainty-aware inference over multiple plausible SQL paths, significantly improving recall and efficiency.

The paper introduces Battery-Sim-Agent, an LLM-based framework that reframes the difficult inverse problem of battery parameter estimation as a reasoning task, significantly outperforming traditional optimization methods.

The paper proposes TEMG-TTA, a novel framework that uses temporal motif-aware graph test-time adaptation to significantly improve Out-of-Distribution (OOD) anomaly detection on complex cryptocurrency blockchains.

The paper introduces MiraBench, a new benchmark that evaluates the action-conditioned reliability of robotic world models, finding that visual fidelity is insufficient and that optimism bias is a pervasive issue across current systems.

The paper proposes TEMG-TTA, a novel framework that combines temporal motif awareness and test-time adaptation to significantly improve Out-of-Distribution (OOD) anomaly detection in complex blockchain transaction graphs.

This paper re-examines the role of temperature ($ au$) in LLM distillation, demonstrating that while Reverse KL (RKL) is often preferred, Forward KL (FKL) significantly outperforms RKL at higher temperatures, overturning standard empirical conclusions.

The paper proposes DARTS, a distribution-aware active rollout trajectory shaping method that fundamentally accelerates LLM reinforcement learning by actively shaping the long-tail response distribution towards conciseness and certainty.

The paper introduces Canopy Entropy ($ ext{CE}^ ext{*}$), a novel metric that quantifies generation uncertainty across the entire output space, demonstrating that fine-tuning improves information conveyance by efficiently converting token uncertainty into semantic diversity.

GaMi is a multimodal material identification system that uses mmWave and acoustic sensing with a cross-modal subtractive disentanglement framework to achieve high accuracy (95.2%) for material identification regardless of geometric variations.

The paper proposes GRiD, a novel framework that uses a two-phase training strategy (supervised pre-training and RL fine-tuning) to discover complex, graph-like rules for knowledge graph reasoning, overcoming limitations of existing methods.

SIRIUS-SQL introduces a robust multi-candidate text-to-SQL system that addresses weaknesses in candidate generation, error handling, and selection, achieving state-of-the-art performance on complex benchmarks.

The paper proposes a novel, theoretically-grounded algorithm (HAMU) that addresses the challenge of machine unlearning by guaranteeing specified improvements in forget quality while minimizing retain utility degradation.