Español

Explorar

Noticias de IA

21052 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
When Gradients Collide: Failure Modes of Multi-Objective Prompt Optimization for LLM Judg…
arXiv cs.AI Research & Papers
Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization
arXiv cs.AI Research & Papers
PASA: A Principled Embedding-Space Watermarking Approach for LLM-Generated Text under Sem…
arXiv cs.AI Research & Papers
SURGE: Surrogate Gradient Adaptation in Binary Neural Networks
arXiv cs.AI Research & Papers
StakeBench: Evaluating Language Understanding Grounded in Market Commitment
arXiv cs.AI Research & Papers
Memorize Theorems, Not Instances: Probing SFT Generalization through Mathematical Reasoni…
arXiv cs.AI Research & Papers
Flow-OPD: On-Policy Distillation for Flow Matching Models
arXiv cs.AI Research & Papers
PACZero: PAC-Private Fine-Tuning of Language Models via Sign Quantization
arXiv cs.AI Research & Papers
Conditional KRR: Injecting Unpenalized Features into Kernel Methods with Applications to …
arXiv cs.AI Research & Papers
Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior Adjustment
arXiv cs.AI Research & Papers
WorldGUI: An Interactive Benchmark for Desktop GUI Automation from Any Starting Point
arXiv cs.AI Research & Papers
Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval
arXiv cs.AI Research & Papers
From Muscle Bursts to Motor Intent: Self-Supervised Token Modeling for Heterogeneous EMG
arXiv cs.AI Research & Papers
Auditing Stealth Sycophancy in Mental-Health Dialogue: Structured Clinical-State Diagnost…
arXiv cs.AI Research & Papers
BFORE: Butterfly-Firefly Optimized Retinex Enhancement for Low-Light Image Quality Improv…
arXiv cs.AI Research & Papers
ClawTrace: Cost-Aware Tracing for LLM Agent Skill Distillation
arXiv cs.AI Research & Papers
Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace
arXiv cs.AI Research & Papers
ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Fo…
arXiv cs.AI Research & Papers
Talking Slide Avatars: Open-Source Multimodal Communication Approach for Teaching
arXiv cs.AI Research & Papers
ESIA: An Energy-Based Spatiotemporal Interaction-Aware Framework for Pedestrian Intention…
arXiv cs.AI Research & Papers
Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Gener…
arXiv cs.AI Research & Papers
VILAS: A VLA-Integrated Low-cost Architecture with Soft Grasping for Robotic Manipulation
arXiv cs.AI Research & Papers
Is VLA Reasoning Faithful? Probing Safety of Chain-of-Causation in Autonomous Driving Mod…
arXiv cs.AI Research & Papers
ECUAS$_n$: A family of metrics for principled evaluation of uncertainty-augmented systems
arXiv cs.AI Research & Papers
Federation over Text: Insight Sharing for Multi-Agent Reasoning
arXiv cs.AI Research & Papers
Depth Registers Unlock W4A4 on SwiGLU: A Reader/Generator Decomposition
arXiv cs.AI Research & Papers
Copy-as-Decode: Grammar-Constrained Parallel Prefill for LLM Editing
arXiv cs.AI Research & Papers
Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training
arXiv cs.AI Research & Papers
From Reasoning to Code: GRPO Optimization for Underrepresented Languages
arXiv cs.AI Research & Papers
Beyond Static Uncertainty: Modeling Temporal Uncertainty Dynamics for Probabilistic Time …