Wei Ji

The paper introduces Spike-PTSD, a novel, biologically inspired adversarial attack framework that successfully compromises the robustness of Spiking Neural Networks (SNNs) by modeling abnormal neural firing patterns found in PTSD.

The paper proposes UniRule, a novel agentic RAG framework that unifies the detection rule generation process by mapping context and language to rules, significantly outperforming pure LLM generation.

The paper introduces TICoE, a text-image collaborative framework that achieves precise and faithful concept removal from text-to-image generative models, surpassing existing methods in both precision and content fidelity.

PhishSigma++ is a novel entity-relation-based detector that improves malicious email detection by focusing on invariant functional relationships between typed entities, significantly outperforming text-centric models under adversarial manipulation.

GiPL proposes a novel two-branch framework combining iterative pseudo-label self-training and generative data augmentation to significantly improve Cross-Domain Few-Shot Object Detection by better utilizing limited support set data and reducing overfitting.

The paper proposes a unified framework that decouples long-video reasoning into semantic and visual evidence, significantly improving performance on the HD-EPIC VQA Challenge.

This paper introduces LVCG, a novel self-supervised framework that learns unified, view-invariant latent representations of cardiac electrical activity directly in the physically grounded Vectorcardiogram (VCG) space, improving generalization over traditional ECG-space methods.

UniAudio-Token is a framework that enhances existing semantic speech tokenizers with general audio perception, allowing them to handle diverse audio types while maintaining high-fidelity speech capabilities.

The paper proposes In-Context Visual Contrastive Optimization (IC-VCO) to rigorously mitigate multimodal hallucinations in Vision-Language Models by optimizing contrastive learning within a shared multi-image context.

GIRL-DETR introduces Gradient-Isolated Reinforcement Learning to enhance temporal localization in lightweight Video Moment Retrieval models, achieving high accuracy by decoupling feature representation from metric optimization.

The paper introduces MiCU, a domain-specific LLM that significantly improves smart home command understanding, especially for ambiguous commands, by synthesizing training data and optimizing the model for efficiency.

The paper proposes a zero-shot reason-then-retrieve pipeline using Qwen3.5-27B to solve the challenging task of composed video retrieval (CoVR-R), achieving high performance on both validation and blind test splits.

This paper addresses the challenge of detecting and explaining AI-manipulated segments within long, untrimmed videos by proposing a new benchmark and a coarse-to-fine forensic detection framework.

Adaptive Auto-Harness introduces a framework that enables LLM agents to sustain self-improvement and maintain high performance over open-ended, shifting task streams, outperforming existing fixed-benchmark auto-harness systems.

The paper proposes a novel nonparametric mutual information estimator to robustly quantify dependence between heterogeneous temporal data, specifically continuous time series and discrete event sequences.

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.

The paper introduces CyberGym-E2E, a large-scale, end-to-end benchmark designed to comprehensively evaluate AI agents' capabilities across the entire lifecycle of real-world software vulnerability discovery, proof-of-concept generation, and patch creation.