Backdoor Decontamination Dynamics in LLM Agents
Explorar
Noticias de IA
21010 elementos — filtrados, clasificados y sin duplicados
Beyond Fixed Luminance: Towards Panchromatic and Orthochromatic Image Colorization
Self-evolving network verifiers
Class Activation Mapping in Explainable Computer Vision: A Method-Centered Review of CNN,…
Reinforcement Learning based DBMS Buffer Pool Auto-Tuning for Optimal Memory Utilization
VICBench: A Multi-Language Benchmark for Code Vulnerability Detection
Toward Meaningful Transparency for AI Chatbots: Disclosing Persuasive Intent Reduces Pers…
Do LLMs Take Care of Their Own? Similarity Signals Can Induce Cooperation
EnterpriseRAG: Benchmarking LLM Instruction Adherence and Robustness under Non-Ideal Ente…
MaSRead: Content-Addressed Reading of Replicated Latent Stores
Inverse Theory of Mind Modeling for Content Recommendation: From Web Browsing to Dynamic …
VLM2Rec: Resolving Modality Collapse in Vision-Language Model Embedders for Multimodal Se…
Every pooling rule has its world: matching probability combination rules to situations an…
Benchmarking LLM Judges for Mobile Agent Evaluation
Learning-Based Behavior Planning for Automated Driving: Real-World Integration and Deploy…
Large Language Models Reproduce Racial Stereotypes When Used for Text Annotation
Text Corpora as Concept Fields: Black-Box Hallucination and Novelty Measurement
Surfacing the Unsaid: CUE-Bench for Affective Stance in Chinese Discourse
SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attenti…
ViTOED: A Dataset for Target-Oriented Emotion Detection on Vietnamese Social Media Texts
Dual-Stream Cross-Anchor Correction Grounding Long-Form Captions and the Domain Limits of…
A Cloud-Edge System for Multimodal Clinical Screening in Resource-Constrained Rural Setti…
Error-Aware Reverse Auction Mechanism for Large Language Model Routing
What We Learned by Reproducing 2,200 papers from ICML
Drive-to-Music: Context-Aware Generative Audio for In-Vehicle Experiences
Attribute-Conditioned Multimodal Slot Factorization for Controllable Fashion Retrieval
Can Vision-Language Models Assess Proxemic Risk from Egocentric Robot Images?
DreamFly: Causal Memory and Receding-Horizon Diffusion Planning for Aerial Vision-Languag…
AI4AI at Test-Time: Strong-to-Weak Capability Transfer via Harnesses
Redistribution-based Cost Inference Improves Sparse Safe Offline RL