Español

Explorar

Noticias de IA

27413 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
Real vs. Semi-Simulated: Rethinking Evaluation for Treatment Effect Estimation
arXiv cs.AI Research & Papers
E = T*H/(O+B): A Dimensionless Control Parameter for Mixture-of-Experts Ecology
arXiv cs.AI Research & Papers
Quality-Conditioned Agreement in Automated Short Answer Scoring: Mid-Range Degradation an…
arXiv cs.AI Research & Papers
MoBayes: A Modular Bayesian Framework for Separating Reasoning from Language in Conversat…
arXiv cs.AI Research & Papers
EditCaption: Human-Refined SFT and HAE-DPO for Image Editing Instruction Synthesis
arXiv cs.AI Research & Papers
Inference Time Context Sparsity: Illusion or Opportunity?
arXiv cs.AI Research & Papers
Theoretical Analysis of Sparse Optimization with Reparameterization, Weight Decay, and Ad…
arXiv cs.AI Research & Papers
Identifying and Mitigating Systemic Measurement Bias in Production LLM Inference Benchmar…
arXiv cs.AI Research & Papers
How Well Do Models Follow Their Constitutions?
arXiv cs.AI Research & Papers
HiGraph: A Large-Scale Hierarchical Graph Dataset for Malware Analysis
arXiv cs.AI Research & Papers
Prism: Spectral-Aware Block-Sparse Attention
arXiv cs.AI Research & Papers
Scalable Explainability-as-a-Service (XaaS) for Edge AI Systems
arXiv cs.AI Research & Papers
SPA-Cache: Singular Proxies for Adaptive Caching in Diffusion Language Models
arXiv cs.AI Research & Papers
Dynamics Reveals Structure: Challenging the Linear Propagation Assumption
arXiv cs.AI Research & Papers
Characterizing Linear Alignment Across Language Models
arXiv cs.AI Research & Papers
Reliable AI Needs to Externalize Implicit Knowledge: A Human-AI Collaboration Perspective
arXiv cs.AI Research & Papers
Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of A…
arXiv cs.AI Research & Papers
From Prompt Optimization to Multi-Dimensional Credibility Evaluation: Enhancing Trustwort…
arXiv cs.AI Research & Papers
Learning to Trust: Bayesian Adaptation to Varying Suggester Reliability in Sequential Dec…
arXiv cs.AI Research & Papers
SPARK: Search Personalization via Agent-Driven Retrieval and Knowledge-sharing
arXiv cs.AI Research & Papers
PathWise: Planning through World Model for Automated Heuristic Design via Self-Evolving L…
arXiv cs.AI Research & Papers
LGMT: Logic-Grounded Metamorphic Testing for Evaluating the Reasoning Reliability of LLMs
arXiv cs.AI Research & Papers
E3AD: An Emotion-Aware Vision-Language-Action Model for Human-Centric End-to-End Autonomo…
arXiv cs.AI Research & Papers
Why We Need World Models for AGI: Where LLMs Fail and How World Models May Outperform
arXiv cs.AI Research & Papers
BackWeak: Backdooring Knowledge Distillation Simply with Weak Triggers and Fine-tuning
arXiv cs.AI Research & Papers
LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward …
arXiv cs.AI Research & Papers
Breaking the Chains of Probability: Neutrosophic Logic as a New Framework for Epistemic U…
arXiv cs.AI Research & Papers
SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills
arXiv cs.AI Research & Papers
ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference
arXiv cs.AI Research & Papers
Go witheFlow: Real-time Emotion Driven Audio Effects Modulation