Español

Explorar

Noticias de IA

29623 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
Cooperation of Experts: Fusing Heterogeneous Information with Large Margin
arXiv cs.AI Security & Safety
Erased but Not Forgotten: How Backdoors Compromise Concept Erasure
arXiv cs.AI Research & Papers
Gradients with Respect to Semantics Preserving Embeddings Tell the Uncertainty of Large L…
arXiv cs.AI Research & Papers
Beyond Offline A/B Testing: Context-Aware Agent Simulation for Recommender System Evaluat…
arXiv cs.AI Research & Papers
AtomEval: Validity-Aware Atomic Evaluation of Adversarial Claim Rewriting in Fact Verific…
arXiv cs.AI Research & Papers
Heterogeneous Decentralized Diffusion Models
arXiv cs.AI Research & Papers
Topology-Preserving Neural Operator Learning via Hodge Decomposition
arXiv cs.AI Research & Papers
Soft-NBCE: Entropy-Weighted Chunk Fusion for Long-Context
arXiv cs.AI Research & Papers
ThinkSwitch: Context Distillation with LoRA and Weight Interpolation for Specific-Purpose…
arXiv cs.AI Research & Papers
APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate A…
arXiv cs.AI Research & Papers
{\lambda}Split: Self-Supervised Content-Aware Spectral Unmixing for Fluorescence Microsco…
arXiv cs.AI Research & Papers
Geometry-Aware Probabilistic Circuits via Voronoi Tessellations
arXiv cs.AI Research & Papers
DyLLM: Efficient Diffusion LLM Inference via Saliency-based Token Selection and Partial A…
arXiv cs.AI Research & Papers
Hybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding
arXiv cs.AI Research & Papers
FVSpec: Real-World Property-Based Tests as Lean Challenges
arXiv cs.AI Research & Papers
Silent Failures in Federated Personalization of Foundation Models
arXiv cs.AI Research & Papers
Understanding-Enhanced Model Collaboration for Long-Tailed Egocentric Mistake Detection
arXiv cs.AI Research & Papers
Balancing Knowledge Distillation for Imbalance Learning with Bilevel Optimization
arXiv cs.AI Research & Papers
RADAR: Redundancy-Aware Diffusion for Multi-Agent Communication Structure Generation
arXiv cs.AI Research & Papers
Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution
arXiv cs.AI Research & Papers
Process Reward Agents for Steering Knowledge-Intensive Reasoning
arXiv cs.AI Research & Papers
What's Missing in Screen-to-Action? Towards a UI-in-the-Loop Paradigm for Multimodal GUI …
arXiv cs.AI Research & Papers
AgentProcessBench: Diagnosing Step-Level Process Quality in Tool-Using Agents
arXiv cs.AI Research & Papers
PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering
arXiv cs.AI Research & Papers
Structure Enables Effective Self-Localization of Errors in LLMs
arXiv cs.AI Research & Papers
ReasonBENCH: Benchmarking the (In)Stability of LLM Reasoning
arXiv cs.AI Research & Papers
Multimodal Function Vectors for Visual Relations
arXiv cs.AI Research & Papers
InPhyRe Discovers: Large Multimodal Models Struggle in Inductive Physical Reasoning
arXiv cs.AI Research & Papers
Stop Wandering, Find the Keys: LLMs Discriminate Key States for Efficient Multi-Agent Exp…
arXiv cs.AI Research & Papers
Why Not Hyperparameter-Friendly Optimisation? A Monotonic Adaptive Norm Rescaling Approac…