OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Det…
Distilling Linearized Behavior into Non-Linear Fine-Tuning for Effective Task Arithmetic
Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models
Atom-level Protein Representation Learning Improves Protein Structure Prediction
Preisach Attention: A Hysteretic Model of Sequential Memory
Towards Generalization of Block Attention via Automatic Segmentation and Block Distillati…
BOHM: Zero-Cost Hierarchical Attribution for Compound AI Systems
NeuroNL2LTL: A Neurosymbolic Framework for Natural Language Translation of Linear Tempora…
RMA: an Agentic System for Research-Level Mathematical Problems
Mediative Fuzzy Logic: From Type-1 Foundations to Type-2, Type-3 and Quantum Extensions
EVE-Agent: Evidence-Verifiable Self-Evolving Agents
Foundation Protocol: A Coordination Layer for Agentic Society
EDGE-OPD: Internalizing Privileged Context with Evidence Guided On-Policy Distillation
CP or DP? Why Not Both: A Case Study in the Partial Shop Scheduling Problem
An AI-Driven Framework for Energy-Efficient Environmental Monitoring in Smart Cities Usin…
Evaluating Large Language Models in a Complex Hidden Role Game
PrefBench: Evaluating Zero-Shot LLM Agents in Hidden-Preference Personalized Pricing Nego…
MedExpMem: Adapting Experience Memory for Differential Diagnosis
How Far Will They Go? Red-Teaming Online Influence with Large Language Models
Test-Time Training Undermines Safety Guardrails
Robots That Know What to Ask: Recovering Misaligned Rewards through Targeted Explanations
MadEvolve: Evolutionary Optimization of Trading Systems with Large Language Models
Sparse Autoencoders Map Brain-LLM Alignment onto Cortical Semantic Topography
The TIME Machine: On The Power of Motion for Efficient Perception
Model Collapse as Cultural Evolution
KAPLAN: Kolmogorov-Arnold Prognostic Learnable Activation Networks for Survival Analysis
MUSEKG: A Knowledge Graph Over Museum Collections
Exploiting Longitudinal Context in Clinician-Verified Interactive Lesion Tracking
Infra-Bayesian Reinforcement Learning Agents Outperform Classical RL For Worst-Case Robus…