SAFEGuard: Detect Optimization-Based Jailbreak Attacks Through Harmful Semantic Analysis …
Explorar
Noticias de IA
37834 elementos — filtrados, clasificados y sin duplicados
API Benchmark Scores Do Not Reliably Transfer to Chatbot Interfaces
Data Scout: Targeted Web Crawling for Domain-Specific Pretraining Corpora
Revisiting Thinning Methods for Kernel Learning Problems
Bigger Text Encoders Can Hurt CLIP Zero-Shot Performance
Input-to-State Stability Framework for Fully Distributed Primal-Dual Dynamics for Quadrat…
BIO-MEMART: Biometric-Aware KV Cache Memory for Multi-User LLM Agents
GoAnt: Quality-Diversity Multi-Agent Search for Alpha Factor Discovery in Market Microstr…
It's All in the Way You Say It: The Role of Information Representation in LLM-Based Glyce…
PAGR: Proof-Carrying Algebraic-Geometric Retrieval: A Quiver-, Provenance-, and Sheaf-The…
Graph-Based Personalized Memory for LLM Agents: Representation, Evolution, Retrieval, and…
Do AI Coding Assistants Check Before They Install? A Pre-Registered Demand-Side Audit of …
ExecCritic: Learn to Test, Test to Improve for Coding Agents
Answer-Distribution Trajectories: A Stochastic-Dynamics View of LLM Reasoning
Concord: A Video Relational Algebra for Cross-Modal Query Optimization
LEBGen: An LLM-Enhanced Bayesian Network Framework for Few-Shot Travel Survey Data Genera…
CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation
SRPO: Setwise Relative Policy Optimization for Multi-Agent LLMs
Mind the Phase: Effective Rank and Representation Health in Legged Locomotion
Dual-Latent Memory Routing for Vision-Language Reasoning
Adaptive Cost-Sensitive Machine Learning for Autonomous Robot Navigation Failure Predicti…
Time-Varying Data as Sheaves: an Invitation to Narratives
Diffusion models for eye-gaze trajectory generation using position and velocity represent…
The Profit Alignment Problem: How Profit Mandates Induce Alignment Failures in LLMs
When Agent Governance Helps
Full-Page Optical Music Recognition of Handwritten Monophonic Scores
The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly Publishing
When Intelligence Becomes Agency: A Theory of Governed, Proactive Agency for Symbiotic AI…
Good Pretraining, Bad SFT: Checkpoint Quality Across the Training Stack
Who Maintains Agent Skills? A Longitudinal Study of Human-Governed, AI-Assisted Skill Mai…