Explorar

Noticias de IA

37834 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
Stratified Consistency Distillation for Natural Language Formalization
arXiv cs.AI Research & Papers
Taking the Whys Seriously: Limitations of Counterfactual Explanations in Justification an…
arXiv cs.AI Research & Papers
Towards Stream Learning on Embedded Systems: Benchmarking the Memory Consumption of Strea…
arXiv cs.AI Research & Papers
Stick to What You Know: A Study of Knowledge-Aligned Supervised Fine-Tuning
arXiv cs.AI Research & Papers
Safety Screening for Voltage Control in Active Distribution Grids via Distributionally Ro…
arXiv cs.AI Research & Papers
LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation
arXiv cs.AI Research & Papers
HumanStudy-Bench: Towards AI Agent Design for Participant Simulation
arXiv cs.AI Research & Papers
On the Prospects of Dynamic LLM Conversations in Software Development
arXiv cs.AI Research & Papers
Stride-k Subsampling: Train-Free Audio Token Reduction for Whisper
arXiv cs.AI Research & Papers
GMTS: Gradient Magnitude-based Token Selection Improves RLVR Training for LLM Reasoning
arXiv cs.AI Research & Papers
Centering before Pruning: Lightweight Geometry Correction for Diversity-Based Visual Toke…
arXiv cs.AI Research & Papers
Tail-Replay: Escaping the Curse of Linear Attention in Prefix Caching for Hybrid LLMs
arXiv cs.AI Research & Papers
TAMI: Temporally Aligned, Missingness-Aware, and Interpretable Multimodal Fusion for Ment…
arXiv cs.AI Research & Papers
Zero-shot Generalizable Graph Anomaly Detection with Mixture of Riemannian Experts
arXiv cs.AI Research & Papers
PRISM: Predictive Recomposition via Semantic Latent Decomposition for View-invariant Vide…
arXiv cs.AI Research & Papers
BAITBENCH: Measuring Agent Reward Hacking with Optional Shortcuts Planted in ML Tasks
arXiv cs.AI Research & Papers
Learning to Evaluate Before Improving: Automatic Rubric Induction for Automatic Research …
arXiv cs.AI Research & Papers
EReCu: Pseudo-label Evolution Fusion and Refinement with Multi-Cue Learning for Unsupervi…
arXiv cs.AI Research & Papers
Evaluating and Mitigating Anti-LGBTQ Biases in German and Multilingual Language Models
arXiv cs.AI Research & Papers
LCoT-GV: Graph Attention Networks for Verifying Long Reasoning Chains in Large Language M…
arXiv cs.AI Research & Papers
Parallel Time-Band Mixing with Learned Observation-Adding for Robust ASR Front-Ends
arXiv cs.AI Research & Papers
ObjectSplat: Improving Mesh Fidelity and Interactivity for 3D Scenes via Object-Level Mes…
arXiv cs.AI Research & Papers
TSExplorer: An interactive data annotation and exploration tool for time-series data
arXiv cs.AI Research & Papers
Pretrained, Curriculum-Tuned, and Ensembled: A Tracer-Aware Interactive Segmentation Pipe…
arXiv cs.AI Research & Papers
MusGU+: Toward a Musician-Centered Evaluation Framework and Discovery Tool for Generative…
arXiv cs.AI Research & Papers
Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling
arXiv cs.AI Research & Papers
Disappearing Ink: Obfuscation Breaks N-gram Code Watermarks in Theory and Practice
arXiv cs.AI Research & Papers
CPR for LLMs: Critical-Point Routing against Catastrophic Forgetting in Domain Adaptation
arXiv cs.AI Research & Papers
ReGraP-LLaVA: Reasoning enabled Graph-based Personalized Large Language and Vision Assist…
arXiv cs.AI Research & Papers
A Mental Model Based Framework of Trust