Español

Explorar

Noticias de IA

37834 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
Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients
arXiv cs.AI Research & Papers
Evidence-Grounded Constraint Checking in Construction Documents
arXiv cs.AI Research & Papers
Mission-Level Runtime Assurance for LLM-Assisted ISR Swarms over a Verification-Aware Fab…
arXiv cs.AI Research & Papers
MMShopBench: A Real-Log Benchmark for Multimodal, Multi-Turn Shopping Agents
arXiv cs.AI Research & Papers
Learning Lookahead Lemmas for Neural Network Verification
arXiv cs.AI Research & Papers
What Makes a Sale? Simulating End-to-End Seller--Buyer Retail Dynamics with LLM Agents
arXiv cs.AI Research & Papers
SREGym: A Live Benchmark for AI SRE Agents with High-Fidelity Failure Scenarios
arXiv cs.AI Research & Papers
Dual-Dimensional Consistency: Balancing Budget and Quality in Adaptive Inference-Time Sca…
arXiv cs.AI Research & Papers
DualityCert: Verifier-Gated Language-Model Repair of Broken Duality Claims in Quantum Fie…
arXiv cs.AI Research & Papers
Can Large Language Models Derive New Knowledge? A Dynamic Benchmark for Biological Knowle…
arXiv cs.AI Research & Papers
Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in L…
arXiv cs.AI Research & Papers
Wrong Code, Right Structure: Learning Netlist Representations from Imperfect LLM-Generate…
arXiv cs.AI Research & Papers
Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Genera…
arXiv cs.AI Research & Papers
StaQ: a Finite Memory Approach to Discrete Action Policy Mirror Descent
arXiv cs.AI Research & Papers
Agentic Harness for Real-World Compilers
arXiv cs.AI Research & Papers
Latent Actions from Factorized Transition Effects under Agent Ambiguity
arXiv cs.AI Research & Papers
The Capability Convergence Hypothesis: Capability from Access Structure, Not Scale
arXiv cs.AI Research & Papers
DynaResize: Runtime GPU Reallocation for Disaggregated LLM Post-Training
arXiv cs.AI Research & Papers
On the Expressive Power of Sparse Geometric MPNNs
arXiv cs.AI Research & Papers
Revisiting Multi-Permutation Equivariance through the Lens of Irreducible Representations
arXiv cs.AI Research & Papers
Dual-Force: Enhanced Offline Diversity Maximization under Imitation Constraints
arXiv cs.AI Research & Papers
Reproducing Human Individual Motor Signatures: A Data-Driven Approach for Repetitive Moti…
arXiv cs.AI Research & Papers
ActionParty: Multi-Subject Action Binding in Generative Video Games
arXiv cs.AI Research & Papers
Generative AI in Action: Field Experimental Evidence from Alibaba's Customer Service Oper…
arXiv cs.AI Research & Papers
Maximum Entropy Behavior Exploration for Sim2Real Zero-Shot Reinforcement Learning
arXiv cs.AI Research & Papers
Why It Hurts: Identifying the Drivers of Negative Thoughts in Emotional Support Conversat…
arXiv cs.AI Research & Papers
ConnectED: A Curriculum-Aligned AI System for Vietnamese Instructional Lesson Planning an…
arXiv cs.AI Research & Papers
RareSense: Rarity-Aware Similarity Search for Anomaly Retrieval in Transactional Data
arXiv cs.AI Research & Papers
TextCloak: Thwarting Unauthorized LLM Exploitation via RL-Driven Unlearnable Text
arXiv cs.AI Research & Papers
EarlyDx: An Admission-Anchored Benchmark for Open-Ended Generation of Evidence-Supported …