Investigating the Interplay between Contextual and Parametric Chain-of-Thought Faithfulne…
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
OrpQuant: Geometric Orthogonal Residual Projection for Multiplier-Free Power-of-Two Trans…
Rethinking Weak Supervision in Anomaly Detection: A Comprehensive Benchmark
ChaosBench-Logic v2: Evaluating LLM Logical Reasoning over Dynamical Systems at Scale
Beyond Summaries: Structure-Aware Labeling of Code Changes with Large Language Models
Squeezing Capacity from Multimodal Large Language Models for Subject-driven Generation
Hybrid Deep Searcher: Scalable Parallel and Sequential Search Reasoning
From Multi-Agent Systems and the Semantic Web to Agentic AI: A Unified Narrative of the W…
Hide-and-Shill: A Reinforcement Learning Framework for Market Manipulation Detection in S…
FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations
Efficient and Scalable Neural Symbolic Search for Knowledge Graph Complex Query Answering
MX-SAFE: Versatile Inference- and Training-Proof Microscaling Format with On-the-Fly Expo…
Voting with the Graph: Stable RLAIF via Topological Consistency Maximization
False Fixed Points: Kantian Feedback, Stable Miscalibration, and Representational Compres…
Agent Learning via Early Experience
Momentum Streams for Optimizer-Inspired Transformers
PennySynth: RAG-Driven Data Synthesis for Automated Quantum Code Generation
BC Protocol: Structured Dual-Expert Dialogue for Eliciting High-Quality Chain-of-Thought …
AGI Requires a Coordination Layer on Top of Pattern Repositories
Actionable and diverse counterfactual explanations incorporating domain knowledge and pla…
NSR-Boost: A Neuro-Symbolic Residual Boosting Framework for Industrial Legacy Models
MMUEChange: A Generalized LLM Agent Framework for Intelligent Multi-Modal Urban Environme…
Emergent Analogical Reasoning in Transformers
MedBeads: An Agent-Native, Immutable Data Substrate for Trustworthy Medical AI
OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Re…
Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning
PathMem: Toward Cognition-Aligned Memory Transformation for Pathology MLLMs
AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications
INDUCTION: Finite-Structure Concept Synthesis in First-Order Logic
AI in the Enterprise: How People Use M365 Copilot Chat