AI Stack 探索 AI 技术前沿，分享深度思考与实践
条目
2659
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. Agentic Critical Training 2026-03-10 · ARXIV
  2. A Multi-Objective Optimization Approach for Sustainable AI-Driven Entrepreneurship in Resilient Economies 2026-03-10 · ARXIV
  3. Impermanent: A Live Benchmark for Temporal Generalization in Time Series Forecasting 2026-03-10 · ARXIV
  4. TildeOpen LLM: Leveraging Curriculum Learning to Achieve Equitable Language Representation 2026-03-10 · ARXIV
  5. The Conundrum of Trustworthy Research on Attacking Personally Identifiable Information Removal Techniques 2026-03-10 · ARXIV
  6. SERQ: Saliency-Aware Low-Rank Error Reconstruction for LLM Quantization 2026-03-10 · ARXIV
  7. Revisiting Gradient Staleness: Evaluating Distance Metrics for Asynchronous Federated Learning Aggregation 2026-03-10 · ARXIV
  8. MM-TS: Multi-Modal Temperature and Margin Schedules for Contrastive Learning with Long-Tail Data 2026-03-10 · ARXIV
  9. Distributional Regression with Tabular Foundation Models: Evaluating Probabilistic Predictions via Proper Scoring Rules 2026-03-10 · ARXIV
  10. SCOPE: Scene-Contextualized Incremental Few-Shot 3D Segmentation 2026-03-09 · ARXIV
  11. Hierarchical Industrial Demand Forecasting with Temporal and Uncertainty Explanations 2026-03-09 · ARXIV
  12. Causal Interpretation of Neural Network Computations with Contribution Decomposition 2026-03-09 · ARXIV
  13. Boosting deep Reinforcement Learning using pretraining with Logical Options 2026-03-09 · ARXIV
  14. BEVLM: Distilling Semantic Knowledge from LLMs into Bird's-Eye View Representations 2026-03-09 · ARXIV
  15. A recipe for scalable attention-based MLIPs: unlocking long-range accuracy with all-to-all node attention 2026-03-09 · ARXIV
  16. Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation 2026-03-06 · ARXIV
  17. Thermodynamic Response Functions in Singular Bayesian Models 2026-03-06 · ARXIV
  18. The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks 2026-03-06 · ARXIV
  19. RoboPocket: Improve Robot Policies Instantly with Your Phone 2026-03-06 · ARXIV
  20. Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought 2026-03-06 · ARXIV
  21. POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation 2026-03-06 · ARXIV
  22. Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval 2026-03-06 · ARXIV
  23. Cheap Thrills: Effective Amortized Optimization Using Inexpensive Labels 2026-03-06 · ARXIV
  24. Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation 2026-03-06 · ARXIV
  25. TaxonRL: Reinforcement Learning with Intermediate Rewards for Interpretable Fine-Grained Visual Reasoning 2026-03-05 · ARXIV
  26. SimpliHuMoN: Simplifying Human Motion Prediction 2026-03-05 · ARXIV
  27. Robustness of Agentic AI Systems via Adversarially-Aligned Jacobian Regularization 2026-03-05 · ARXIV
  28. AgentIR: Reasoning-Aware Retrival for Deep Research Agents 2026-03-05 · ARXIV
  29. A Dual-Helix Governance Approach Towards Reliable Agentic AI for WebGIS Development 2026-03-05 · ARXIV
  30. $τ$-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge 2026-03-05 · ARXIV
  31. ZipMap: Linear-Time Stateful 3D Reconstruction with Test-Time Training 2026-03-05 · ARXIV
  32. Tuning Just Enough: Lightweight Backdoor Attacks on Multi-Encoder Diffusion Models 2026-03-05 · ARXIV
  33. Monitoring Emergent Reward Hacking During Generation via Internal Activations 2026-03-05 · ARXIV
  34. Hindsight Quality Prediction Experiments in Multi-Candidate Human-Post-Edited Machine Translation 2026-03-05 · ARXIV
  35. FedCova: Robust Federated Covariance Learning Against Noisy Labels 2026-03-05 · ARXIV
  36. Speculative Speculative Decoding 2026-03-04 · ARXIV
  37. Valet: A Standardized Testbed of Traditional Imperfect-Information Card Games 2026-03-04 · ARXIV
  38. LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory 2026-03-04 · ARXIV
  39. Inherited Goal Drift: Contextual Pressure Can Undermine Agentic Goals 2026-03-04 · ARXIV
  40. CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance 2026-03-04 · ARXIV
  41. Tether: Autonomous Functional Play with Correspondence-Driven Trajectory Warping 2026-03-04 · ARXIV
  42. Why Adam Can Beat SGD: Second-Moment Normalization Yields Sharper Tails 2026-03-04 · ARXIV
  43. Odin: Multi-Signal Graph Intelligence for Autonomous Discovery in Knowledge Graphs 2026-03-04 · ARXIV
  44. Multi-Scale Adaptive Neighborhood Awareness Transformer For Graph Fraud Detection 2026-03-04 · ARXIV
  45. MoECLIP: Patch-Specialized Experts for Zero-shot Anomaly Detection 2026-03-04 · ARXIV
  46. Interpreting Speaker Characteristics in the Dimensions of Self-Supervised Speech Features 2026-03-04 · ARXIV
  47. From Complex Dynamics to DynFormer: Rethinking Transformers for PDEs 2026-03-04 · ARXIV
  48. Evaluating Performance Drift from Model Switching in Multi-Turn LLM Systems 2026-03-04 · ARXIV
  49. Compact Prompting in Instruction-tuned LLMs for Joint Argumentative Component Detection 2026-03-04 · ARXIV
  50. Beyond Task Completion: Revealing Corrupt Success in LLM Agents through Procedure-Aware Evaluation 2026-03-04 · ARXIV