Explorar

Noticias de IA

27413 elementos — filtrados, clasificados y sin duplicados

arXiv cs.AI Research & Papers
X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation
arXiv cs.AI Research & Papers
A Time-Based Readout for Vector-Matrix Multiplication in Fully Analog Memristive SNNs
arXiv cs.AI Research & Papers
Structural priors for data-efficient language learning
arXiv cs.AI Research & Papers
Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport
arXiv cs.AI Research & Papers
Physics-Informed Neural Networks to Infer the Perpendicular Energy Conductivity in the Sc…
arXiv cs.AI Research & Papers
TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown…
arXiv cs.AI Research & Papers
The Semantic Elevation Operator and the Closure of the Undecidable Class under Preservati…
arXiv cs.AI Research & Papers
Your Model Already Knows Don't Teach It, Learn to Ask It: Soft Prompting for Few-Shot Ada…
arXiv cs.AI Research & Papers
E-CONAN (Entailment, CONtradition And Neutral) Benchmarks: Arabic Textual Entailment and …
arXiv cs.AI Research & Papers
On the Impact of Anonymization on the Performance of Large Language Models
arXiv cs.AI Research & Papers
Improving Faint Object Detection for Space Situational Awareness with Variational Autoenc…
arXiv cs.AI Research & Papers
Generative Replay Mitigates Sample Starvation in Quantum Architecture Search
arXiv cs.AI Research & Papers
2AM: Grounding Agent-Side Memory as Guidance for Steerable Action Models in Long-Horizon …
arXiv cs.AI Research & Papers
(Whose defaults?) Is artificial intelligence reorienting archaeological methods?
arXiv cs.AI Research & Papers
Beyond Visual Quality: Evaluating Physical Consistency under Ego-Motion with EgoGenEval
arXiv cs.AI Research & Papers
X-RACE: XAI-assisted Recurrent neural network Attribution for Channel Estimation
arXiv cs.AI Research & Papers
From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for…
arXiv cs.AI Research & Papers
A Fragility Spectrum for Recursive Language-Model Training
arXiv cs.AI Research & Papers
Characterizing Bluesky Content Moderation Service: From Automation of Service to Landscap…
arXiv cs.AI Research & Papers
BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evalua…
arXiv cs.AI Research & Papers
Less can be More: What Aspects of Speech Drive End-of-Turn Detection
arXiv cs.AI Research & Papers
Beyond Benchmarks: Using VLMs to Reveal Systematic Classification Failures Under Real Wor…
arXiv cs.AI Research & Papers
New Evidence, Same Choice: Testing Physical Experiment Selection in Vision Language Models
arXiv cs.AI Research & Papers
A Mathematical Theory of Pragmatic Information
arXiv cs.AI Research & Papers
Topological Necessities: Mechanism-Invariant Strategic Subgoals for Cross-Embodiment Goal…
arXiv cs.AI Research & Papers
ReactHuman: A Physics-Grounded Benchmark for Human-Like Reactive Decision-Making in Embod…
arXiv cs.AI Research & Papers
Tapes Together Strong: The Co-evolution of Computation and Cooperation
arXiv cs.AI Research & Papers
Robust Multimodal Sentiment Analysis with Incomplete Modalities via Semantic-aware Comple…
arXiv cs.AI Research & Papers
When Synthetic Data Hurts: On Catastrophic Forgetting in Skill Retrieval for LLM Agents
arXiv cs.AI Research & Papers
What a Random Draw from the MCP Registry Contains, and What Tool-Use Benchmarks Contain I…