Español

Explorar

Noticias de IA

22318 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
Spectral Rewiring for Exploration, Purification, and Model Merging
arXiv cs.AI Research & Papers
Don't Wait to Reply: Towards Responsive yet Thoughtful Dialogue through Proactive Thinking
arXiv cs.AI Research & Papers
S-EMBER: A Large-Scale Benchmark for Streaming Egocentric Memory Retrieval
arXiv cs.AI Research & Papers
Not All Refusals Are Equal: How Safety Alignment Fails Cybersecurity at Scale
arXiv cs.AI Research & Papers
SMOCS: A Streaming Framework for Simplified Deployment, Monitoring, and Optimization of M…
arXiv cs.AI Research & Papers
Safe Inference-Time Alignment via Lagrangian Reward Augmentation
arXiv cs.AI Research & Papers
Test-Time Adaptation for EEG Foundation Models: A Systematic Study under Real-World Distr…
arXiv cs.AI Research & Papers
Seduced by the Narrative: Assessing Rule Adherence in Semi-Open Textual Sandboxes
arXiv cs.AI Research & Papers
Teaming Up with AI: Coordination and Cooperation
arXiv cs.AI Research & Papers
Parallelized Autoregressive Decoding for Omni-Modal Dense Video Captioning
arXiv cs.AI Research & Papers
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling
arXiv cs.AI Research & Papers
CONFLUX: A Latent Diusion Model for 3D Chest-CT Synthesis with RL Post-Training
arXiv cs.AI Research & Papers
Back to Basics: Improving Molecular Understanding in LLMs via SMILES-Graph Translation
arXiv cs.AI Research & Papers
HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Dif…
arXiv cs.AI Research & Papers
Is Agentic Code Review Helpful? Mining Developers' Feedback to CodeRabbit Reviews in the …
arXiv cs.AI Research & Papers
From Judgments to Issues: Structured Extraction of Legal Reasoning with Citation-Hallucin…
arXiv cs.AI Research & Papers
FedAvg for HAR: Exploring the Tradeoff Between Personalized and Generalization Accuracy
arXiv cs.AI Research & Papers
Differential Amplifier-Inspired AmpAttention for Multi-View Robotic Manipulation
arXiv cs.AI Research & Papers
PPE-Bench: A Benchmark for Evaluating MLLM Unlearning under Private-Public Entanglement
arXiv cs.AI Research & Papers
Learning Taxonomic Trees with Hierarchical Representation Regularization for Large Multim…
arXiv cs.AI Research & Papers
Bootstrap Flow-Map Tree Sampling Enables Online Feedback Driven Search
arXiv cs.AI Research & Papers
Full Glyph Images Beat Token Embeddings: A Controlled Study for Transformers
arXiv cs.AI Research & Papers
Separating Representation from Reconstruction Enables Scalable Text Encoders
arXiv cs.AI Research & Papers
Finite Reliability Representations: Noise-Calibrated Belief-Space Covers for Reliable Dec…
arXiv cs.AI Research & Papers
A Unified Algebraic Framework for Classification Performance Evaluation
arXiv cs.AI Research & Papers
OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers
arXiv cs.AI Research & Papers
The "I Don't Know" Filter: Enhancing Agentic Reliability in Function Calling
arXiv cs.AI Research & Papers
Telescope: Improving Zero Shot Detection of LLM Generated Content By Measuring Token Repe…
arXiv cs.AI Research & Papers
BoRP: Bootstrapped Regression Probing for Scalable and Human-Aligned LLM Evaluation
arXiv cs.AI Research & Papers
MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources