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
Aligning Deep Implicit Preferences by Learning to Reason Defensively
arXiv cs.AI Research & Papers
BRAINCELL-AID: An Agentic AI Created Brain Cell Type Resource for Community Annotation
arXiv cs.AI Research & Papers
A Unified Geometric Space for Topological Alignment Between Transformer-Based Models and …
arXiv cs.AI Research & Papers
Reasoning or Fluency? Dissecting Probabilistic Confidence in Best-of-N Selection
arXiv cs.AI Research & Papers
Interfaze: The Future of AI is built on Task-Specific Small Models
arXiv cs.AI Research & Papers
Bilevel Autoresearch: Meta-Autoresearching Itself
arXiv cs.AI Research & Papers
KITE: Kernelized and Information Theoretic Exemplars for In-Context Learning
arXiv cs.AI Research & Papers
Belief-Aware VLM Model for Human-like Reasoning
arXiv cs.AI Research & Papers
Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning
arXiv cs.AI Research & Papers
Test-time reward-guided alignment of language models by importance sampling on pre-logit …
arXiv cs.AI Research & Papers
Transformer-Based Autonomous Driving Models and Deployment-Oriented Compression: A Survey
arXiv cs.AI Research & Papers
SSSD: Simply-Scalable Speculative Decoding
arXiv cs.AI Research & Papers
LaVIDE: Language-Prompted Satellite Change Detection via Map-Image Alignment
arXiv cs.AI Research & Papers
Speculative Thinking: Enhancing Small-Model Reasoning with Large Model Guidance at Infere…
arXiv cs.AI Research & Papers
100-LongBench: Are de facto Long-Context Benchmarks Literally Evaluating Long-Context Abi…
arXiv cs.AI Research & Papers
MesaNet: Sequence Modeling by Locally Optimal Test-Time Training
arXiv cs.AI Research & Papers
Can VLMs Predict Future States? Bootstrapping World Models from Inverse Dynamics
arXiv cs.AI Research & Papers
Time Series Forecasting as Reasoning: A Slow-Thinking Approach with Reinforced LLMs
arXiv cs.AI Research & Papers
VGGSounder: Audio-Visual Evaluations for Foundation Models
arXiv cs.AI Research & Papers
A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy…
arXiv cs.AI Research & Papers
BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economic…
arXiv cs.AI Research & Papers
Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thoug…
arXiv cs.AI Research & Papers
Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents
arXiv cs.AI Research & Papers
OckBench: Measuring the Efficiency of LLM Reasoning
arXiv cs.AI Research & Papers
Dynamic Content Moderation in Livestreams: Combining Supervised Classification with MLLM-…
arXiv cs.AI Research & Papers
Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs
arXiv cs.AI Research & Papers
You Only Train Once: Differentiable Subset Selection for Omics Data
arXiv cs.AI Research & Papers
Mid-Think: Training-Free Intermediate-Budget Reasoning via Token-Level Triggers
arXiv cs.AI Research & Papers
Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data
arXiv cs.AI Research & Papers
Curated Synthetic Data Doesn't Have to Collapse: A Theoretical Study of Generative Retrai…