Meddies-PII: A Multilingual Framework for Personally Identifiable Information Extraction …
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Open-Source AI and Open Models Reading List
Why are AI agents lying, cheating and coordinating?
Real-SWE: Benchmarking AI models on private, real-world, enterprise codebases
OpenAI just wants to win
Recognizing Is Not Reversing: A Controlled Inversion Test of Fact-Preserving News Framing
ORCH: Organizational Principles Enable Collective Intelligence in Embodied AI
LOCUS: Task-Aware Low-Rank Post-Training for Token-Efficient Language Generation
A Time-Based Readout for Vector-Matrix Multiplication in Fully Analog Memristive SNNs
Beyond Word Error Rate: A Switch Aware Evaluation of ASR and Audio Language Models on Eng…
AcFlow: Controlling Text-to-Image Diffusion Transformers via Learned Conditional Activati…
Adaptive Margin Ordinal Loss: Penalizing Center-Class Hedging in Ordinal Classification
ActSafeGuard: Differentiable and Training-Aligned Constraint Enforcement for Flow-Matchin…
Data-Efficient Language Modeling: From Frontier Advancement to Principle-Guided Model Imp…
Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis
Automated multi-class wound assessment using dedicated instance segmentation models for b…
Artificial Id: Drive and Persistent Alignment in Agentic AI
Language-Augmented Semantic Priors for B-Spline Surface Fitting
Sympathetic Framing: Evaluating AI Alignment across Sociodemographic Groups
Extending SMT Solving with Non-Ground Clause Learning
Causal Past Logic for Runtime Verification of Distributed LLM Agent Workflows
Output Embedding Centering for Stable LLM Pretraining
LLM-Ideoplasticity: Measuring Ideological Plasticity in the Political Behavior of LLMs as…
Portable Semantics, Private Dialects: Reuse and Negative Transfer in Latent Communication…
Federated Learning for Surgical Vision in Appendicitis Classification: Results of the Fed…
Beyond Confidence: Stability-Aware Test-Time Adaptation for LLM Reasoning
Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis
Evidence for Limited Metacognition in LLMs
Towards AI-Driven Policing: Interdisciplinary Knowledge Discovery from Police Body-Worn C…