AI Stack 探索 AI 技术前沿，分享深度思考与实践
条目
2657
延迟
—
最新内容
当前时间
安全连接 OPERATIONAL

03 / ARTICLE LEDGER

关联文章

按发布时间倒序

  1. Do Metrics for Counterfactual Explanations Align with User Perception? 2026-03-17 · ARXIV
  2. Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning 2026-03-17 · ARXIV
  3. AC-Foley: Reference-Audio-Guided Video-to-Audio Synthesis with Acoustic Transfer 2026-03-17 · ARXIV
  4. Spiking Layer-Adaptive Magnitude-based Pruning 2026-03-17 · ARXIV
  5. SFedHIFI: Fire Rate-Based Heterogeneous Information Fusion for Spiking Federated Learning 2026-03-17 · ARXIV
  6. RS-WorldModel: a Unified Model for Remote Sensing Understanding and Future Sense Forecasting 2026-03-17 · ARXIV
  7. LLM as Graph Kernel: Rethinking Message Passing on Text-Rich Graphs 2026-03-17 · ARXIV
  8. Lightweight User-Personalization Method for Closed Split Computing 2026-03-17 · ARXIV
  9. Learning Question-Aware Keyframe Selection with Synthetic Supervision for Video Question Answering 2026-03-17 · ARXIV
  10. FairMed-XGB: A Bayesian-Optimised Multi-Metric Framework with Explainability for Demographic Equity in Critical Healthcare Data 2026-03-17 · ARXIV
  11. Visual-ERM: Reward Modeling for Visual Equivalence 2026-03-16 · ARXIV
  12. Semantic Invariance in Agentic AI 2026-03-16 · ARXIV
  13. Representation Learning for Spatiotemporal Physical Systems 2026-03-16 · ARXIV
  14. PhysMoDPO: Physically-Plausible Humanoid Motion with Preference Optimization 2026-03-16 · ARXIV
  15. Neuron-Aware Data Selection In Instruction Tuning For Large Language Models 2026-03-16 · ARXIV
  16. MXNorm: Reusing MXFP block scales for efficient tensor normalisation 2026-03-16 · ARXIV
  17. LLM Constitutional Multi-Agent Governance 2026-03-16 · ARXIV
  18. Learnability and Privacy Vulnerability are Entangled in a Few Critical Weights 2026-03-16 · ARXIV
  19. From Experiments to Expertise: Scientific Knowledge Consolidation for AI-Driven Computational Research 2026-03-16 · ARXIV
  20. The Latent Color Subspace: Emergent Order in High-Dimensional Chaos 2026-03-13 · ARXIV
  21. STAMP: Selective Task-Aware Mechanism for Text Privacy 2026-03-13 · ARXIV
  22. Spatial-TTT: Streaming Visual-based Spatial Intelligence with Test-Time Training 2026-03-13 · ARXIV
  23. Separable neural architectures as a primitive for unified predictive and generative intelligence 2026-03-13 · ARXIV
  24. SciMDR: Benchmarking and Advancing Scientific Multimodal Document Reasoning 2026-03-13 · ARXIV
  25. Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language Models 2026-03-13 · ARXIV
  26. Incremental Neural Network Verification via Learned Conflicts 2026-03-13 · ARXIV
  27. Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training 2026-03-13 · ARXIV
  28. EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models 2026-03-13 · ARXIV
  29. BiGain: Unified Token Compression for Joint Generation and Classification 2026-03-13 · ARXIV
  30. V2M-Zero: Zero-Pair Time-Aligned Video-to-Music Generation 2026-03-12 · ARXIV
  31. RCTs & Human Uplift Studies: Methodological Challenges and Practical Solutions for Frontier AI Evaluation 2026-03-12 · ARXIV
  32. Leech Lattice Vector Quantization for Efficient LLM Compression 2026-03-12 · ARXIV
  33. Does AI See like Art Historians? Interpreting How Vision Language Models Recognize Artistic Style 2026-03-12 · ARXIV
  34. COMIC: Agentic Sketch Comedy Generation 2026-03-12 · ARXIV
  35. Beyond the Illusion of Consensus: From Surface Heuristics to Knowledge-Grounded Evaluation in LLM-as-a-Judge 2026-03-12 · ARXIV
  36. A Systematic Study of Pseudo-Relevance Feedback with LLMs 2026-03-12 · ARXIV
  37. Understanding the Use of a Large Language Model-Powered Guide to Make Virtual Reality Accessible for Blind and Low Vision People 2026-03-11 · ARXIV
  38. Towards a Neural Debugger for Python 2026-03-11 · ARXIV
  39. Think Before You Lie: How Reasoning Improves Honesty 2026-03-11 · ARXIV
  40. On the Width Scaling of Neural Optimizers Under Matrix Operator Norms I: Row/Column Normalization and Hyperparameter Transfer 2026-03-11 · ARXIV
  41. From Semantics to Pixels: Coarse-to-Fine Masked Autoencoders for Hierarchical Visual Understanding 2026-03-11 · ARXIV
  42. From Data Statistics to Feature Geometry: How Correlations Shape Superposition 2026-03-11 · ARXIV
  43. CREATE: Testing LLMs for Associative Creativity 2026-03-11 · ARXIV
  44. BEACON: Language-Conditioned Navigation Affordance Prediction under Occlusion 2026-03-11 · ARXIV
  45. Structural Causal Bottleneck Models 2026-03-10 · ARXIV
  46. Split Federated Learning Architectures for High-Accuracy and Low-Delay Model Training 2026-03-10 · ARXIV
  47. Scale Space Diffusion 2026-03-10 · ARXIV
  48. Momentum SVGD-EM for Accelerated Maximum Marginal Likelihood Estimation 2026-03-10 · ARXIV
  49. Evaluating Financial Intelligence in Large Language Models: Benchmarking SuperInvesting AI with LLM Engines 2026-03-10 · ARXIV
  50. Benchmarking Language Modeling for Lossless Compression of Full-Fidelity Audio 2026-03-10 · ARXIV