Español

Explorar

Noticias de IA

27413 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
UniRank: Unified Rank Allocation for Low-Rank LLM Compression
arXiv cs.AI Research & Papers
Keyless Attention: Value-Space Routing and Value-Only Caching for Efficient Transformers
arXiv cs.AI Research & Papers
Harness-MU: A Safe, Governed, and Effective Harness for Multi-User LLM Agents
arXiv cs.AI Research & Papers
Protein contacts are already in the attention: a single-forward-pass alternative to the C…
arXiv cs.AI Research & Papers
Streaming T5-based Text-to-Speech Synthesis with Limited Lookahead
arXiv cs.AI Research & Papers
A Verifiable Search Is Not a Learnable Chain-of-Thought
arXiv cs.AI Research & Papers
AI-Mediated Negotiation: Design Reflections and Lessons
arXiv cs.AI Research & Papers
Scaling Performance and Low-Resource Annotation with Many-Shot In-Context Learning for Na…
arXiv cs.AI Research & Papers
Rethinking the Adaptation of Vision Foundation Models for Efficient Cell Segmentation
arXiv cs.AI Research & Papers
Attention-Spectrum Regularization for Replay-Free Continual Multimodal LLMs
arXiv cs.AI Research & Papers
From Text Metrics to Model Internals: A Study of Whisper ASR Hallucination Detection
arXiv cs.AI Research & Papers
HALAS: A Human-Annotated Dataset of Hallucinations of Modern ASR Systems
arXiv cs.AI Research & Papers
Domain Adaptation Under Wireless Network Constraints: When Does It Become Green?
arXiv cs.AI Research & Papers
The Model as One Rater Among Several: Measuring Political Positions in Data-Sparse Region…
arXiv cs.AI Research & Papers
EvoRubrics: Dynamic Rubrics as Rewards via Adversarial Co-Evolution for LLM Reinforcement…
arXiv cs.AI Research & Papers
Group-Graph Policy Optimization for Long-Horizon Agentic Reinforcement Learning
arXiv cs.AI Research & Papers
Latent Confidence Alignment for LLM Self-Assessment
arXiv cs.AI Research & Papers
ScalePredictor: Instance-aware Scale Learning for Accurate Quantization of Vision Transfo…
arXiv cs.AI Research & Papers
From RAN Control to Agentic Intelligence: Architecture and Vision for Energy Efficient AI…
arXiv cs.AI Research & Papers
SPOTR: Spatio-temporal Pooling One-Token Reconstruction for Universal Physiological Signa…
arXiv cs.AI Research & Papers
Fine-Tuning Large Language Models for Quantum Reasoning
arXiv cs.AI Research & Papers
Understanding Parallel Samplers in Masked Diffusion via Random Walks on Graphs
arXiv cs.AI Research & Papers
Attacking the Trusted Imagination: Oracle-Level Integrity Attacks on Imagine-then-Act Wor…
arXiv cs.AI Research & Papers
Channel Location Constrains the Auditability of Subliminal Learning
arXiv cs.AI Research & Papers
Cluster-Specific Localized Drift Detection for Efficient Batch Model Adaptation under Con…
arXiv cs.AI Research & Papers
RARM: Confidence-Gated Progress Reward Modeling for RL in Manipulation
arXiv cs.AI Research & Papers
NL2Scratch: An Executable Benchmark and Evaluation for Block-Based Programming
arXiv cs.AI Research & Papers
New Smooth Loss functions for Robust Regression that Closely Approximate Absolute Error a…
arXiv cs.AI Research & Papers
CodeTeam: An LLM-Powered Multi-Agent Framework for Repository-Level Code Generation
arXiv cs.AI Research & Papers
KITE: Decoupling Kinematics and Interaction for Zero-Shot Cross-Embodiment Manipulation