Español

Explorar

Noticias de IA

37834 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
ICA: Information-Aware Credit Assignment for Visually Grounded Long-Horizon Information-S…
arXiv cs.AI Research & Papers
Efficient LLM Collaboration via Planning
arXiv cs.AI Research & Papers
The Handoff Tax: Continuing Non-Native Trajectories in LLM Agents
arXiv cs.AI Research & Papers
Memory Is Not Always Needed: Characterizing Conditional Memory in Scientific Reasoning
arXiv cs.AI Research & Papers
FARCA: Fact-Aligned Reliability-Aware Credit Assignment for Reinforcement Learning with F…
arXiv cs.AI Research & Papers
Beyond Accuracy: A Dual-Judge Evaluation Protocol for Vision-Language Models in Legally G…
arXiv cs.AI Research & Papers
Tlow: Flow-based Item Tokenizer for Recommendation
arXiv cs.AI Research & Papers
Meta$^n$: Recursive Self-Improvement through Emergent Depth
arXiv cs.AI Research & Papers
Right Diagnoses, Decorative Reasoning:A Perturbation Audit of Medical Chain-of-Thought
arXiv cs.AI Research & Papers
More Rejective, Not More Discriminative: The Unit of Verification in Pre-Execution LLM Ov…
arXiv cs.AI Research & Papers
Evidence Blindness in Direct Corpus Interaction: Persistent Navigation with AtlasNav
arXiv cs.AI Research & Papers
LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding
arXiv cs.AI Research & Papers
The Limits of Automatic Evaluation of Creativity in Large Language Models
arXiv cs.AI Research & Papers
Quantifying System-Level Harms from AI Adoption in Complex Sociotechnical Systems
arXiv cs.AI Research & Papers
ADVERSA: Measuring Multi-Turn Guardrail Degradation and Judge Reliability in Large Langua…
arXiv cs.AI Research & Papers
Outlier-Robust Diffusion Solvers for Inverse Problems
arXiv cs.AI Research & Papers
Diverse by Reasoning: Harnessing the Wisdom of LLM Crowds for Future Prediction
arXiv cs.AI Research & Papers
Mahalanobis-Based Multi-Head Attention for Complex State Propagation
arXiv cs.AI Research & Papers
A Judge Should Know What Changed:Construct Validity for LLM-as-a-Judge Evaluation
arXiv cs.AI Research & Papers
FraudBench: Protocol-Sensitive Benchmarking of Adversarial Robustness for Financial Risk …
arXiv cs.AI Research & Papers
PhysMLLMs: Spatial Priors for Unified Referring Segmentation and Grounded Reasoning of Im…
arXiv cs.AI Research & Papers
EXAM$^2$: $\underline{Ex}tending$ $\underline{A}udio$ $Understanding$ $in$ $\underline{M}…
arXiv cs.AI Research & Papers
RACE: Scalable Statistical Estimation of Functional Consistency in LLM Neurons
arXiv cs.AI Research & Papers
Causal Modelling of Support Interventions for Student Competency Assessment
arXiv cs.AI Research & Papers
When "Must" Becomes "Maybe": Constraint Weakening in LLM Agent Workflows
arXiv cs.AI Research & Papers
Syn2RealTrack: Bridging the Gap Between Synthetic and Real-World Datasets for Online Mult…
arXiv cs.AI Research & Papers
Lifted Model Construction under Approximate Commutativity
arXiv cs.AI Research & Papers
PlaceSeek: Human-Centered Geospatial Retrieval of Urban Outdoor Places via Semantic Groun…
arXiv cs.AI Research & Papers
LumiXAI: A Modular Full-Stack Framework for Feature Attribution
arXiv cs.AI Research & Papers
SENSESHIFT: Continuous Sentiment-Controlled Text Generation via Encoder-based Mask Infill…