ToolGate: An Executable Acceptance Pipeline for Tool-Dependent Scientific Benchmark Const…
Explorar
Noticias de IA
27413 elementos — filtrados, clasificados y sin duplicados
Looped Transformers under the Jacobian Lens: Does the Global Workspace Survive Recurrence?
Fine-Grained Anomaly Perception in Wild UGC-Enhanced Images: A Comprehensive Dataset and …
ProbeMatchDTI: Probe-Driven Multi-Scale Biochemical Pattern Matching for Drug-Target Inte…
Induction and Inquiry via Probabilistic Reasoning over Language and Code
PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compi…
PolERo: Studying Political Evasion in Romanian
Evidence for Shared Routing Geometry and Dynamics in Sparse Mixture-of-Experts
MultiGhostBench: A Multilingual Benchmark for Long-Form LLM-Generated Text Attribution un…
Architecting Conversational Data Systems for Stateless LLM APIs: The Hydration Proxy Patt…
Meta-ethics and AI: exploring the novel meta-ethical questions in the era of AI
Retrosynthesis of Synthetic Media for Explainable AI Provenance Forensics
Competitive Market Behavior of LLMs
CrashDiffuser: VLM-Guided Collision Intent Reasoning for Fine-Grained Safety-Critical Tra…
DiffuSearch: How Hybrid Trajectory Planning Benefits from Aligned Objectives in Diffusion…
When Does Information Sharing Improve Decentralized Discovery? Aggregation, Independent R…
The Memory Trust Gap: Capability-Dependent Failures in Persistent-Memory Agents
Dictionary-Guided Mutation Operators for Automated HDL Repair
hLLM: Single Pass Decoding for Generative Reranking
Spectral Initialization and Scheduled Graph Smoothness for Uncertain Knowledge Graph Comp…
Language Diffusion Models are Associative Memories Capable of Retrieving Unseen Data
Automated Vulnerability Injection in Smart Contracts Using Large Language Models
NE-R1: Enhancing Named Entity Recognition Model via Reinforcement Learning
Blending Concepts: Benchmarking Visual Metaphor Generation in Text-to-Image Models
When Can a Machine Trust a Statute? A Survival Certificate for Machine-Extracted Legal Lo…
PGPO: Potential-Guided Policy Optimization for Multi-Turn Agentic Tasks
Percolation Dynamics in Optimization : Variance Cascades and Discrete Scale Invariance
FlatLands: Generative Floormap Completion From a Single Egocentric View
Belief-Calibrated Optimization: An Explicit World Model for Agentic Optimization
On-Policy Distillation Meets Off-Policy GRPO: Training Compact Instruction-Following Rera…