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
Attention-based Experience Replay Framework for Continual Learning of Agnostic Time Serie…
arXiv cs.AI Research & Papers
Tractable Hierarchical Control of Autoregressive Language Models
arXiv cs.AI Research & Papers
The Devil is in the Spectrum: Mitigating Representation Collapse in LLMs via Topologicall…
arXiv cs.AI Research & Papers
JAXBench: Benchmarking Autonomous TPU Kernel Optimization
arXiv cs.AI Research & Papers
Scientific exploration, collaboration and labor division in the large language model era
arXiv cs.AI Research & Papers
ImplicitBBQ: Benchmarking Implicit Bias in Large Language Models through Characteristic B…
arXiv cs.AI Research & Papers
EZASP - Facilitating the Usage of ASP
arXiv cs.AI Research & Papers
TwistedMerge: Certified Higher-Order Diagnostics and Abstention for Model Merging
arXiv cs.AI Research & Papers
SR-TTT Does Not Learn Retrieval: A Correction and Mechanistic Post-Mortem of Surprisal-Aw…
arXiv cs.AI Research & Papers
Autonomous Topology Mutation: Safe Runtime Restructuring for Multi-Agent LLM Systems with…
arXiv cs.AI Research & Papers
Codec-Gauge: Learning Compression-Friendly Gauges for Transformer KV Caches
arXiv cs.AI Research & Papers
Isolating LLM Alignment from Regex: Zero Coverage and Metric-Dependent Divergence Under A…
arXiv cs.AI Research & Papers
From Errors to Rules: Iterative Prompt Optimization for Text Classification
arXiv cs.AI Research & Papers
AISE-Bench: A Full-Cycle Curated Benchmark for Information Seeking on Academic Knowledge …
arXiv cs.AI Research & Papers
ExecuGraph: A Multi-Agent, Execution-Grounded Framework for Reliable Backend Code Synthes…
arXiv cs.AI Research & Papers
FlowEdit: Information-Theoretic Control of LLM Reasoning Flows for Ill-posed Problems Inv…
arXiv cs.AI Research & Papers
One More Turn, Less Regret: A Regret-Based Multi-Turn Benchmark for LLMs' Clarification P…
arXiv cs.AI Research & Papers
MKEvolve: A Modular Multi-Agent Framework for Kernel Code Generation
arXiv cs.AI Research & Papers
LeanFlow: A Case Study in Workflow-Driven Lean Autoformalization
arXiv cs.AI Research & Papers
Hardware-Software Co-Design for Float16 On-Device Training on RISC-V Single-Core
arXiv cs.AI Research & Papers
Telco-GAIA: Bilingual Benchmark for Agents in Telecom Domain
arXiv cs.AI Research & Papers
SiGMA: Sign-Guided Merging and Adaptation for Multimodal Continual Instruction Tuning
arXiv cs.AI Research & Papers
CANN Bench: Benchmarking Agent Generated Kernels against Real NPU and Algorithmic Limits
arXiv cs.AI Research & Papers
Representation Robustness Under Executable Reasoning Constraints in Large Language Models…
arXiv cs.AI Research & Papers
ReliableTableQA:How Much Supervision Does Reliability Annotation Need?
arXiv cs.AI Research & Papers
Attention Degradation, Function Token Anchoring, and the Limits of Attention-Based Interv…
arXiv cs.AI Research & Papers
ConfidenceBench: Evaluating Confidence Calibration in Large Language Models
arXiv cs.AI Research & Papers
DynamicMCPBench: A Trace-Grounded, Effect-Scored Benchmark for LLM Agents over Live MCP S…
arXiv cs.AI Research & Papers
OPOD: On-Policy Omni Distillation
arXiv cs.AI Research & Papers
SalesLoop: Reinforcement Learning from Performance Feedback for Sales Lead Ranking