Español

Explorar

Noticias de IA

29349 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
DMF: A Deterministic Memory Framework for Conversational AI Agents
arXiv cs.AI Research & Papers
Rethinking the Role of Tensor Decompositions in Post-Training LLM Compression
arXiv cs.AI Security & Safety
Inference Cost Attacks for Retrieval-Augmented Large Language Models
arXiv cs.AI Opinion & Editorial
Position: Prioritize Identifying Structure, Not Complex Models, for Scientific Discovery
arXiv cs.AI Research & Papers
KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem
arXiv cs.AI Security & Safety
MultiTurnPSB: Evaluating Multi-Turn Jailbreak Attacks an dClassifier-Based Defenses for M…
arXiv cs.AI Research & Papers
OpenAgenet/OAN: Technical Architecture for Trust-Governed Agent Identity and Discovery
arXiv cs.AI Research & Papers
Oscillatory State-Space Models as Inductive Biases for Physics-Informed Neural PDE Solvers
arXiv cs.AI Research & Papers
CARVE: Certified Affordable Repair of Vetoed Maneuvers via Envelopes for Interactive Driv…
arXiv cs.AI Security & Safety
D-Judge: Disrupting Multi-Turn Jailbreaks using Semantics-Preserving Output Rewriting
arXiv cs.AI Research & Papers
DeskCraft: Benchmarking Desktop Agents on Professional Workflows and Human-in-the-Loop Co…
arXiv cs.AI Research & Papers
Hedge-Bench: Benchmarking Agents on Hard, Realistic Tasks Pertaining to Financial Reasoni…
arXiv cs.AI Research & Papers
Sparse-View Lung Nodule Volumetry from Digitally Reconstructed Radiographs via AReT: Anat…
arXiv cs.AI Research & Papers
TimeOmni-VL: Unified Models for Time Series Understanding and Generation
arXiv cs.AI Research & Papers
Whom to Query for What: Adaptive Group Elicitation via Multi-Turn LLM Interactions
arXiv cs.AI Security & Safety
AI Model Extraction Attacks: Bypassing Single-Client Assumptions in Defenses
arXiv cs.AI Research & Papers
Local Guidance, Global Impact: Gaussian-Reshaped Trust Region Unlocks Behavior Transitions
arXiv cs.AI Research & Papers
SegTune: Structured and Fine-Grained Control for Song Generation
arXiv cs.AI Research & Papers
WRIT: Write-Read Intensive Trajectory Synthesis for Multi-Turn User-Facing Agents
arXiv cs.AI Research & Papers
The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Size
arXiv cs.AI Research & Papers
Whose Name Comes Up? II: Benchmarking and Intervention-Based Auditing of LLM-Based Schola…
arXiv cs.AI Research & Papers
Think-Before-Speak: From Internal Evaluation to Public Expression in Multi-Agent Social S…
arXiv cs.AI Security & Safety
Phantom Transfer: Data Poisoning can Survive Data-Level Defences
arXiv cs.AI Research & Papers
AI Rater Discrimination Depends on Scoring Protocol in Complex Clinical Decision-Making
arXiv cs.AI Research & Papers
$\mathbb{R}^{2k}$ is Theoretically Large Enough for Embedding-based Top-$k$ Retrieval
arXiv cs.AI Research & Papers
Distill-then-Replace: Efficient Task-Specific Hybrid Attention Model Construction
arXiv cs.AI Research & Papers
SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale
arXiv cs.AI Research & Papers
A Training-Free Mixture-of-Agents Framework for Multi-Document Summarization using LLMs a…
arXiv cs.AI Research & Papers
Bridging Auxiliary Constraints to Resolve Instruction Following in Large Reasoning Models
arXiv cs.AI Research & Papers
Target Updates May Stabilize Linear Q-Learning: Periodic and Soft Dynamics