Español

Explorar

Noticias de IA

22318 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
Sticky Routing: Training MoE Models for Memory-Efficient Inference
arXiv cs.AI Research & Papers
Signed Symmetric Quantization for Few-Bit Integers
arXiv cs.AI Research & Papers
REAL: REtrieval-reAsoning and Logic-constructed Attention Behaviors for Long-Context KV C…
arXiv cs.AI Research & Papers
A Descriptive and Normative Theory of Human Beliefs in RLHF
arXiv cs.AI Research & Papers
Scalable Visual Pretraining for Language Intelligence
arXiv cs.AI Research & Papers
Semantic Pareto-DQN: A Multi-Objective Reinforcement Learning Framework for Financial Ano…
arXiv cs.AI Research & Papers
Lean-QIT: Towards a Formal Infrastructure for Quantum Information Theory
arXiv cs.AI Research & Papers
Task-Specific Multimodal Question Answering Agents via Confidence Calibration and Increme…
arXiv cs.AI Research & Papers
PAC-ACT: Post-training Actor-Critic for Action Chunking Transformers
arXiv cs.AI Research & Papers
Heterogeneous Information-Bottleneck Coordination Graphs for Multi-Agent Reinforcement Le…
arXiv cs.AI Research & Papers
A Self-Evolving Agentic Framework for Metasurface Inverse Design
arXiv cs.AI Research & Papers
TCLA: Training-Free Class-wise Logit Adaptation for Medical Vision-Language Models
arXiv cs.AI Research & Papers
Seeing is Free, Speaking is Not: Uncovering the True Energy Bottleneck in Edge VLM Infere…
arXiv cs.AI Research & Papers
Conceptual Networks for Cross-Linguistic Idiomatic Expressions:A Feature-Based Graph Appr…
arXiv cs.AI Research & Papers
LongMedBench: Benchmarking Medical Agents for Long-Horizon Clinical Decision-Making
arXiv cs.AI Research & Papers
OpenProver: Agentic and Interactive Theorem Proving with Lean 4
arXiv cs.AI Research & Papers
Toward Auditable AI Scientists: A Hypothesis Evolution Protocol for LLM Agents
arXiv cs.AI Research & Papers
CtrlVTON: Controllable Virtual Try-On via Visual-Instance-Prompt Segmentation
arXiv cs.AI Research & Papers
KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time…
arXiv cs.AI Research & Papers
MedRealMM: A Real-World Multimodal Benchmark for Chinese Online Medical Consultation
arXiv cs.AI Research & Papers
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks …
arXiv cs.AI Research & Papers
Interval Certifications for Multilayered Perceptrons via Lattice Traversal
arXiv cs.AI Research & Papers
When Routes Run Out: Adversarial Co-Learning and Explainable Robustness in Quantum Repeat…
arXiv cs.AI Research & Papers
Fully Trainable Deep Differentiable Logic Gate Networks and Lookup Table Networks
arXiv cs.AI Research & Papers
Ceci n'est pas une pipe: AI systems as semantic abstractions
arXiv cs.AI Research & Papers
SVF-CR: Synchronized Visual-Facial Cross-Refinement for Multimodal Ambivalence and Hesita…
arXiv cs.AI Research & Papers
Shared Selective Persistent Memory for Agentic LLM Systems
arXiv cs.AI Research & Papers
Knowledge Graphs and Explainable AI as Complementary Resources for Urban Mining
arXiv cs.AI Research & Papers
Agora: Enhancing LLM Agent Reasoning Via Auction-Based Task Allocation
arXiv cs.AI Research & Papers
CogniConsole: Externalizing Inference-Time Control as a Formal Abstraction for Reliable L…