Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
Symmetry-Compatible Principle for Optimizer Design: Embeddings, LM Heads, SwiGLU MLPs, an…
arXiv cs.AI Research & Papers
Traceable Knowledge Graph Reasoning Enables LLM-Assisted Decision Support for Industrial …
arXiv cs.AI Research & Papers
Reliable Extraction of Clinical Follow-Up Instructions: A Hybrid Neural-Symbolic Pipeline
arXiv cs.AI Research & Papers
Scaling, Benchmarking, and Reasoning of Vision-Language Agents for Mobile GUI Navigation
arXiv cs.AI Research & Papers
StepOPSD: Step-Aware Online Preference Distillation for Agent Reinforcement Learning
arXiv cs.AI Research & Papers
Bilevel Optimization over Saddle Points of Zero-Sum Markov Games
arXiv cs.AI Research & Papers
A Physics-Informed Hierarchical Neural Network for Microwave Scattering Analysis of 3D PE…
arXiv cs.AI Research & Papers
Advancing Creative Physical Intelligence in Large Multimodal Models
arXiv cs.AI Research & Papers
ChainCaps: Composition-Safe Tool-Using Agents via Monotonic Capability Attenuation
arXiv cs.AI Research & Papers
Detecting Is Not Resolving: The Monitoring Control Gap in Retrieval Augmented LLMs
arXiv cs.AI Research & Papers
Query Symbolically or Retrieve Semantically? A Dataset and Method for Semi-Structured Que…
arXiv cs.AI Research & Papers
Uniboost: Global Coordination with Value Alignment for Fair and Efficient Traffic Allocat…
arXiv cs.AI Research & Papers
Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection
arXiv cs.AI Research & Papers
SIA: Self Improving AI with Harness & Weight Updates
arXiv cs.AI Research & Papers
Structure-Adaptive Conformal Inference for Large-Scale Out-of-Distribution Testing
arXiv cs.AI Research & Papers
Aperiodic and Low-Frequency Spectral Bias in Reconstruction based EEG Foundation Models
arXiv cs.AI Research & Papers
LURE: Live-Usage Replay Evaluations for Reducing Evaluation Awareness
arXiv cs.AI Research & Papers
Personalizing Embodied Multimodal Large Language Model Agents over Long-term User Interac…
arXiv cs.AI Research & Papers
FAST-GOAL: Fast and Efficient Global-local Object Alignment Learning
arXiv cs.AI Research & Papers
BrickAnything: Geometry-Conditioned Buildable Brick Generation with Structure-Aware Token…
arXiv cs.AI Research & Papers
Rethinking Weakly-supervised Video Temporal Grounding From a Game Perspective
arXiv cs.AI Research & Papers
The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Ret…
arXiv cs.AI Research & Papers
Alignment Tampering: How Reinforcement Learning from Human Feedback Is Exploited to Optim…
arXiv cs.AI Research & Papers
MedVol-R1: Reward-Driven Evidence Grounding for Volumetric Reasoning Segmentation
arXiv cs.AI Research & Papers
Geometry-Aware Contrastive Learning for Few-Shot Automatic Modulation Recognition
arXiv cs.AI Research & Papers
From Detection to Recovery: Operational Analysis on LLM Pre-training with 504 GPUs
arXiv cs.AI Research & Papers
Respecting Modality Gap in Post-hoc Out-of-distribution Detection with Pre-trained Vision…
arXiv cs.AI Research & Papers
VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning
arXiv cs.AI Research & Papers
ICCU: In-Context Continual Unlearning via Pattern-Induced Refusal Rules
arXiv cs.AI Research & Papers
Tool Calling is Linearly Readable and Steerable in Language Models