Español

Explorar

Noticias de IA

29347 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
A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners
arXiv cs.AI Research & Papers
Leave it to the Specialist: Repair Sparse LLMs with Sparse Fine-Tuning via Sparsity Evolu…
arXiv cs.AI Research & Papers
Distribution-Calibrated Inference Time Compute for Thinking LLM-as-a-Judge
arXiv cs.AI Research & Papers
Uncertainty-Aware Clarification in LLM Agents with Information Gain
arXiv cs.AI Research & Papers
ConTraIRL: Factorized Contrastive Abstractions for Transferable IRL
arXiv cs.AI Research & Papers
Geometry-Aware Tabular Diffusion
arXiv cs.AI Research & Papers
Aletheia: What Makes RLVR For Code Verifiers Tick?
arXiv cs.AI Research & Papers
EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement
arXiv cs.AI Research & Papers
Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis
arXiv cs.AI Research & Papers
Code-on-Graph: Iterative Programmatic Reasoning via Large Language Models on Knowledge Gr…
arXiv cs.AI Research & Papers
TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning
arXiv cs.AI Research & Papers
Towards Non-Monotonic Entailment in Propositional Defeasible Standpoint Logic
arXiv cs.AI Research & Papers
A Negative Result on Cross-Model Activation Transfer in a Pythia Multi-Hop Setting
arXiv cs.AI Research & Papers
MedCUA-Bench: A Screenshot-Only Benchmark for Clinical Computer-Use Agents
arXiv cs.AI Research & Papers
See Less, Specify More: Visual Evidence Budgets for Generalizable VLAs
arXiv cs.AI Research & Papers
Perceive Before Reasoning: A Pre-Reasoning Perception Framework for Efficient and Reliabl…
arXiv cs.AI Security & Safety
Narrow Secret Loyalty Dodges Black-Box Audits
arXiv cs.AI Research & Papers
OpenAgenet/OAN: Open Infrastructure for Trusted Agent Interconnection
arXiv cs.AI Security & Safety
DDOR: Delta Debugging for Explainable Overrefusal Testing and Repair
arXiv cs.AI Research & Papers
BaltiVoice: A Speech Corpus and Fine-tuned Whisper ASR System for the Balti Language
arXiv cs.AI Security & Safety
A Hybrid Approach For Malware Classification Using Secondary Features Fusion
arXiv cs.AI Research & Papers
BAHSD: Bridging the Long-tail Gap via Adaptive Distillation in Black-box Sequential Recom…
arXiv cs.AI Research & Papers
AI Rater Discrimination Depends on Scoring Protocol in Complex Clinical Decision-Making
arXiv cs.AI Research & Papers
WebRISE: Requirement-Induced State Evaluation for MLLM-Generated Web Artifacts
arXiv cs.AI Research & Papers
AI-Generated Traces for Novice Programmers: Learning Effects and Learner Differences in a…
arXiv cs.AI Research & Papers
RobotValues: Evaluating Household Robots When Human Values Conflict
arXiv cs.AI Research & Papers
FLIPS: Instance-Fingerprinting for LLMs via Pseudo-random Sequences
arXiv cs.AI Research & Papers
Physics-Guided Policy Optimization with Self-Distillation
arXiv cs.AI Research & Papers
Safety Measurements for Fine-tuned LLMs Should be Grounded in Capability
arXiv cs.AI Research & Papers
Evaluating Transformer and LSTM Frameworks for Prediction in Ungauged Basins