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
CIPHER: Benchmarking Cross-record Inference over Privacy-Hardened Evidence Records
arXiv cs.AI Research & Papers
LANTERN: Language Model Assessment on Noisy and Transformed Tasks for Understanding Error…
arXiv cs.AI Research & Papers
Fewer yet critical: Reducing Redundant Token Dependencies for Transformer-based Time Seri…
arXiv cs.AI Research & Papers
DeCAL: Towards Physically-Grounded Dexterous Vision-Language-Action Models via Contact-Aw…
arXiv cs.AI Research & Papers
LOBERT: Generative AI Foundation Model for Limit Order Book Messages
arXiv cs.AI Research & Papers
CriticGen: Generation-Aware Evaluation as Actionable Feedback
arXiv cs.AI Research & Papers
VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification
arXiv cs.AI Research & Papers
When Does Memory Help? A Cost-Aware Evaluation of Long-Term Memory in Tool-Using LLM Agen…
arXiv cs.AI Research & Papers
Damage-Aware Bandit Pruning for Vision and Language Transformers
arXiv cs.AI Research & Papers
Compiling VGDL into Causal Models
arXiv cs.AI Research & Papers
PGP-Clinical-TimeKAN: Prior-Guided Joint Probabilistic Forecasting of Clinical Trajectori…
arXiv cs.AI Research & Papers
Reading Decoder Trajectories: Training-Free Counterfactual Query-Trajectory Reliability f…
arXiv cs.AI Research & Papers
The Normalization of Deviance in AI Development
arXiv cs.AI Research & Papers
STAR-Pro: Stage-Wise Token Adaptive Reduction with Progressive Refinement for Efficient L…
arXiv cs.AI Research & Papers
Discovering Natural Transformation Vulnerabilities in Black-Box Vision Models
arXiv cs.AI Research & Papers
Hi-FLoop: Hierarchical State-Feedback Loops for Multi-Timescale World Modeling
arXiv cs.AI Research & Papers
Earth System World Model for What-If Simulations: A Case Study for Terrestrial Ecosystems
arXiv cs.AI Research & Papers
The Geometry of Refusal: Why Post-Hoc Safety Is Fragile and Pretraining-Time Safety Persi…
arXiv cs.AI Research & Papers
SQLMorph: Query Mutation and Fine-Grained Metrics for Text-to-SQL Evaluation
arXiv cs.AI Research & Papers
Attention-Weighted Value Projection for KV-Cache Compression
arXiv cs.AI Research & Papers
Neither Adversarial Training Nor Purification: Emergent Adversarial Robustness from Oscil…
arXiv cs.AI Research & Papers
Memory in Deep Time-Series Models
arXiv cs.AI Research & Papers
Hyperparameter Scaling Laws Across MoE Sparsity
arXiv cs.AI Research & Papers
Silent Revision: Measuring Undisclosed Change in the Safety Frameworks of Frontier AI Dev…
arXiv cs.AI Research & Papers
RAPID: Reliability-Aware Pair Importance Distillation
arXiv cs.AI Research & Papers
Parallelism Strategy Chaining for Fast Training Convergence
arXiv cs.AI Research & Papers
Omni Interaction Agent Technical Report
arXiv cs.AI Research & Papers
From the Fluency Fallacy to the Micro-to-Macro Validity Gap: Opportunities and Pitfalls o…
arXiv cs.AI Research & Papers
Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence…
arXiv cs.AI Research & Papers
TriCCOT: Tri-part Convolutional Conformal Transformer for Onboard Space Object Detection