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
Xe-Forge: Multi-Stage LLM-Powered Kernel Optimization for Intel GPU
arXiv cs.AI Security & Safety
Turning Bias into Bugs: Bandit-Guided Style Manipulation Attacks on LLM Judges
arXiv cs.AI Research & Papers
Planning Neural Dynamics with Lie Group Embedding through Supervised Projective Manifold …
arXiv cs.AI Research & Papers
Model Merging on Loss Landscape: A Geometry Perspective
arXiv cs.AI Research & Papers
ReMoE: Boosting Expert Reuse through Router Fine-Tuning in Memory-Constrained MoE LLM Inf…
arXiv cs.AI Research & Papers
GAC: Noise-Aware Adaptive Mixing for Hybrid SFT-RL Post-Training
arXiv cs.AI Research & Papers
Workflow Closure Is Not Scientific Closure in Auto-Research Systems
arXiv cs.AI Research & Papers
Composition Collapse: Stable Factual Knowledge Does Not Imply Compositional Reasoning
arXiv cs.AI Research & Papers
When Does Adaptive Guidance Help? Belief-Aware Privileged Distillation for Autonomous Dri…
arXiv cs.AI Research & Papers
Quantized Keys Steal Attention: Bias Correction for KV-Cache Compression in Video Diffusi…
arXiv cs.AI Research & Papers
Semigroup Consistency as a Diagnostic for Learned Physics Simulators
arXiv cs.AI Security & Safety
Furina: Fragmented Uncertainty-Driven Refusal Instability Attack
arXiv cs.AI Research & Papers
Less is More: Early Stopping Rollout for On-Policy Distillation
arXiv cs.AI Research & Papers
Credit-assigned Policy Gradient for Early Stage Retrieval in Two-stage Ranking
arXiv cs.AI Research & Papers
The Rescue Effect: Spatio-Semantic Early Exit Bypasses Quantization Collapse in CLIP
arXiv cs.AI Research & Papers
Recursive Flow Matching
arXiv cs.AI Research & Papers
RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations
arXiv cs.AI Research & Papers
Tool-Schema Compression Enables Agentic RAG Under Constrained Context Budgets
arXiv cs.AI Research & Papers
Targeted Remasking: Replacing Token Editing with Token-to-Mask Refinement in Discrete Dif…
arXiv cs.AI Research & Papers
Enhancing Autonomous Online Intrusion Detection for IoT with Balanced Learning, Reliable …
arXiv cs.AI Research & Papers
Alignment Tuning for Large Language Models: A Data-Centric Lens on Alignment Data Pipelin…
arXiv cs.AI Research & Papers
Cross-scale Aligned Supervision for Training GANs
arXiv cs.AI Research & Papers
Verus-SpecGym: An Agentic Environment for Evaluating Specification Autoformalization
arXiv cs.AI Research & Papers
InfoQuant: Shaping Activation Distributions for Low-Bit LLM Quantization
arXiv cs.AI Models & Releases
The MiniMax-M2 Series: Mini Activations Unleashing Max Real-World Intelligence
arXiv cs.AI Research & Papers
How Reliable are LLMs for Reasoning on the Re-ranking task?
arXiv cs.AI Research & Papers
PitchBench: Measuring Pitch Hearing in Audio-Language Models
arXiv cs.AI Research & Papers
Prospective evaluation of multimodal respiratory failure prediction: Do chest X-rays impr…
arXiv cs.AI Research & Papers
AutoDFT: A Closed-Loop Multi-Agent Framework for Autonomous DFT Calculations
arXiv cs.AI Research & Papers
Certified Causal Attribution for Real-Time Attack Forensics in 6G Network Slicing