KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Causal Evidentiary Governance for High-Risk Machine Learning Systems
Explore More, Drift Less: Outcome-Only Reinforcement Learning Can Suffice for Long-Horizo…
Provably Efficient Federated Reinforcement Learning with Linear Function Approximation an…
Think Like a Doctor: Conversational Diagnosis through the Exploration of Diagnostic Knowl…
Individualized Algorithmic Advice as a Strategic Signal on Competitive Markets
EmbodiedSkills: A Unified Framework for Orchestrating, Training, and Deploying VLA Agents
Ontology-Guided Neuro-Symbolic Inference: Grounding Language Models with Mathematical Dom…
From Detection to Refusal: Safer LLMs via Circuit-Guided Weight Scaling
From Truncation to Commitment: Persistent Context in Uniform Discrete Diffusion
DISTAL: Distillation and Self-Supervised Pretraining for Structure-Agnostic Materials Pro…
Solaris: Towards Interfaces That Are Generated, Not Coded
One Prompt Is Enough: Watermark Laundering Through Foundation Image Models
Task-Specific Prompt with Global Context for Multi-Task Graph Pre-Training
Designing Proactive Thought Partners for Writing
The Rise of Verbal Reinforcement Learning
RAPIDMap: Rapid Multi-Agent Pipeline for Interpretable Disaster Mapping from Satellite an…
From Confusion to Clarity: Confusion-Aware Retrieval and Knowledge Injection for Text Cla…
Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation
Can LLMs Discover Scientific Laws in Real and Parallel Worlds?
Visual Attention Faithfulness in Vision-Language Models is Heterogeneous
Selective Agent Guidance via Entropy: Learning Autonomous Policies from Imperfect VLM Tea…
Operational Regimes in Non-Convex Optimization: A Multiplier-Based Taxonomy
Provably Safe Sim-to-Real Transfer
Autoresearch for Marketplace Catalogs: From Legacy Forms to AI-Native Matching
Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers
InteractBench: Benchmarking LLMs on Competitive Programming under Unrevealed Information
H3-World: Turning Language Understanding into World Control
Cheap Verifiers, Large Blind Spots: Measuring the Reliability Cost of Cost-Saving Cascades
LEAP: Likelihood Elicitation and Aggregation for LLM-based Probabilistic Forecasting