Español

Explorar

Noticias de IA

29670 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
Shared Doubt: Zero-shot Cross-Lingual Confidence Estimation for Language Models
arXiv cs.AI Research & Papers
Unraveling LoRA Interference: Orthogonal Subspaces for Robust Model Merging
arXiv cs.AI Security & Safety
Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack
arXiv cs.AI Research & Papers
Skill Availability and Presentation Granularity in Large-Language-Model Agents: A Control…
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
TUX: Measuring Human--AI Tacit Understanding
arXiv cs.AI Research & Papers
Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized Use…
arXiv cs.AI Research & Papers
Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which …
arXiv cs.AI Research & Papers
BilliardPhys-Bench: Benchmarking Physical Reasoning and Visual Dynamics of Multimodal LLMs
arXiv cs.AI Research & Papers
LLMs Without Deep Neural Networks: New Architecture, Benefits and Case Study
arXiv cs.AI Research & Papers
GraphARC: A Comprehensive Benchmark for Graph-Based Abstract Reasoning
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
GaMi: Geometry-Agnostic Material Identification via Cross-Modal Subtractive Disentangleme…
arXiv cs.AI Research & Papers
CobSeg: Coherence Boundary Modeling for Dialogue Topic Segmentation
arXiv cs.AI Research & Papers
XOResNet: Exclusive-OR Meta-Residuals Facilitate Deep Spiking Neural Networks Learning
arXiv cs.AI Research & Papers
SWIM: Single-Instance Whole-Body Imitation for swiMming
arXiv cs.AI Research & Papers
Learning to Solve and Optimize by Evolving Code
arXiv cs.AI Research & Papers
COMPASS: Cognitive MCTS-Guided Process Alignment for Safe Search Agents
arXiv cs.AI Research & Papers
Language Models Learn Constructional Semantics, Not To Mention Syntax: Investigating LM U…
arXiv cs.AI Research & Papers
On Efficient Scaling of GNNs via IO-Aware Layers Implementations
arXiv cs.AI Research & Papers
Fine-grained Verification via Diagnostic Reasoning Supervision for Aspect Sentiment Tripl…
arXiv cs.AI Research & Papers
Used Car Salesbots? Honesty and Credulity of LLMs as Bargaining Agents under Partial Info…
arXiv cs.AI Research & Papers
DOA: Training-Free Decoder-Only Attention Policy for Long-Form Simultaneous Translation w…
arXiv cs.AI Research & Papers
The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of La…
arXiv cs.AI Research & Papers
Target-Side Paraphrase Augmentation for Sign Language Translation with Large Language Mod…