Español

Explorar

Noticias de IA

37834 elementos — filtrados, clasificados y sin duplicados

Todos Models & Releases Research & Papers Funding & M&A Policy & Regulation Product Launches Industry Moves Developer Tooling Opinion & Editorial Security & Safety Other
arXiv cs.AI Research & Papers
Language Models Learn Constructional Semantics, Not To Mention Syntax: Investigating LM U…
arXiv cs.AI Research & Papers
LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric R…
arXiv cs.AI Research & Papers
PithTrain: A Compact and Agent-Native MoE Training System
arXiv cs.AI Research & Papers
Skill Reuse as Compression in Agentic RL
arXiv cs.AI Research & Papers
Feature-Optimized Vision for Adaptive 3D Scene Reconstruction
arXiv cs.AI Research & Papers
What Gets Unmasked First? Trajectory Analysis of Diffusion Models for Graph-to-Text Gener…
arXiv cs.AI Research & Papers
Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified…
arXiv cs.AI Research & Papers
NEMO: Execution-Aware Optimization Modeling via Autonomous Coding Agents
arXiv cs.AI Research & Papers
BilliardPhys-Bench: Benchmarking Physical Reasoning and Visual Dynamics of Multimodal LLMs
arXiv cs.AI Research & Papers
GraphARC: A Comprehensive Benchmark for Graph-Based Abstract Reasoning
arXiv cs.AI Research & Papers
XOResNet: Exclusive-OR Meta-Residuals Facilitate Deep Spiking Neural Networks Learning
arXiv cs.AI Research & Papers
Human-Alignment and Calibration of Inference-Time Uncertainty in Large Language Models
arXiv cs.AI Research & Papers
PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Traini…
arXiv cs.AI Research & Papers
Inferring Events from Time Series using Language Models
arXiv cs.AI Research & Papers
Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
arXiv cs.AI Research & Papers
COMPASS: Cognitive MCTS-Guided Process Alignment for Safe Search Agents
arXiv cs.AI Research & Papers
CobSeg: Coherence Boundary Modeling for Dialogue Topic Segmentation
arXiv cs.AI Research & Papers
GaMi: Geometry-Agnostic Material Identification via Cross-Modal Subtractive Disentangleme…
arXiv cs.AI Research & Papers
Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Disti…
arXiv cs.AI Research & Papers
LLMs Without Deep Neural Networks: New Architecture, Benefits and Case Study
arXiv cs.AI Research & Papers
Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which …
arXiv cs.AI Research & Papers
Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized Use…
arXiv cs.AI Research & Papers
TUX: Measuring Human--AI Tacit Understanding
arXiv cs.AI Research & Papers
Learning to Solve and Optimize by Evolving Code
arXiv cs.AI Research & Papers
SWIM: Single-Instance Whole-Body Imitation for swiMming
arXiv cs.AI Research & Papers
FreeTimeGS++: Secrets of Dynamic Gaussian Splatting and Their Principles
arXiv cs.AI Research & Papers
SEMA-RAG: A Self-Evolving Multi-Agent Retrieval-Augmented Generation Framework for Medica…
arXiv cs.AI Research & Papers
The Terminal Representation in Reinforcement Learning
arXiv cs.AI Research & Papers
Envisioning Beyond the Few: Disentangled Semantics and Primitives for Few-Shot Atypical L…
arXiv cs.AI Research & Papers
Why Linear Recurrent Memory Works in Partially Observable Reinforcement Learning