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. Subgroups of $U(d)$ Induce Natural RNN and Transformer Architectures 2026-02-23 · ARXIV
  2. SPQ: An Ensemble Technique for Large Language Model Compression 2026-02-23 · ARXIV
  3. RVR: Retrieve-Verify-Retrieve for Comprehensive Question Answering 2026-02-23 · ARXIV
  4. Benchmarking Graph Neural Networks in Solving Hard Constraint Satisfaction Problems 2026-02-23 · ARXIV
  5. Assigning Confidence: K-partition Ensembles 2026-02-23 · ARXIV
  6. A.R.I.S.: Automated Recycling Identification System for E-Waste Classification Using Deep Learning 2026-02-21 · ARXIV
  7. What Language is This? Ask Your Tokenizer 2026-02-20 · ARXIV
  8. Sink-Aware Pruning for Diffusion Language Models 2026-02-20 · ARXIV
  9. Pushing the Frontier of Black-Box LVLM Attacks via Fine-Grained Detail Targeting 2026-02-20 · ARXIV
  10. Multi-Round Human-AI Collaboration with User-Specified Requirements 2026-02-20 · ARXIV
  11. Mine and Refine: Optimizing Graded Relevance in E-commerce Search Retrieval 2026-02-20 · ARXIV
  12. MARS: Margin-Aware Reward-Modeling with Self-Refinement 2026-02-20 · ARXIV
  13. FAMOSE: A ReAct Approach to Automated Feature Discovery 2026-02-20 · ARXIV
  14. Differences in Typological Alignment in Language Models' Treatment of Differential Argument Marking 2026-02-20 · ARXIV
  15. Reinforced Fast Weights with Next-Sequence Prediction 2026-02-19 · ARXIV
  16. Protecting the Undeleted in Machine Unlearning 2026-02-19 · ARXIV
  17. Policy Compiler for Secure Agentic Systems 2026-02-19 · ARXIV
  18. Measuring Mid-2025 LLM-Assistance on Novice Performance in Biology 2026-02-19 · ARXIV
  19. Knowledge-Embedded Latent Projection for Robust Representation Learning 2026-02-19 · ARXIV
  20. Causality is Key for Interpretability Claims to Generalise 2026-02-19 · ARXIV
  21. Calibrate-Then-Act: Cost-Aware Exploration in LLM Agents 2026-02-19 · ARXIV
  22. Are Object-Centric Representations Better At Compositional Generalization? 2026-02-19 · ARXIV
  23. Task-Agnostic Continual Learning for Chest Radiograph Classification 2026-02-18 · ARXIV
  24. Stabilizing Test-Time Adaptation of High-Dimensional Simulation Surrogates via D-Optimal Statistics 2026-02-18 · ARXIV
  25. Solving Parameter-Robust Avoid Problems with Unknown Feasibility using Reinforcement Learning 2026-02-18 · ARXIV
  26. Operationalising the Superficial Alignment Hypothesis via Task Complexity 2026-02-18 · ARXIV
  27. Dex4D: Task-Agnostic Point Track Policy for Sim-to-Real Dexterous Manipulation 2026-02-18 · ARXIV
  28. Developing AI Agents with Simulated Data: Why, what, and how? 2026-02-18 · ARXIV
  29. CrispEdit: Low-Curvature Projections for Scalable Non-Destructive LLM Editing 2026-02-18 · ARXIV
  30. Avey-B 2026-02-18 · ARXIV
  31. Text Style Transfer with Parameter-efficient LLM Finetuning and Round-trip Translation 2026-02-17 · ARXIV
  32. Symmetry in language statistics shapes the geometry of model representations 2026-02-17 · ARXIV
  33. Scaling Beyond Masked Diffusion Language Models 2026-02-17 · ARXIV
  34. Rethinking Diffusion Models with Symmetries through Canonicalization with Applications to Molecular Graph Generation 2026-02-17 · ARXIV
  35. Long Context, Less Focus: A Scaling Gap in LLMs Revealed through Privacy and Personalization 2026-02-17 · ARXIV
  36. Hunt Globally: Deep Research AI Agents for Drug Asset Scouting in Investing, Business Development, and Search & Evaluation 2026-02-17 · ARXIV
  37. Efficient Sampling with Discrete Diffusion Models: Sharp and Adaptive Guarantees 2026-02-17 · ARXIV
  38. Cold-Start Personalization via Training-Free Priors from Structured World Models 2026-02-17 · ARXIV
  39. BPP: Long-Context Robot Imitation Learning by Focusing on Key History Frames 2026-02-17 · ARXIV
  40. When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift 2026-02-17 · ARXIV
  41. UniWeTok: An Unified Binary Tokenizer with Codebook Size $\mathit{2^{128｝｝$ for Unified Multimodal Large Language Model 2026-02-17 · ARXIV
  42. Process-Supervised Multi-Agent Reinforcement Learning for Reliable Clinical Reasoning 2026-02-17 · ARXIV
  43. Knowing When Not to Answer: Abstention-Aware Scientific Reasoning 2026-02-17 · ARXIV
  44. Index Light, Reason Deep: Deferred Visual Ingestion for Visual-Dense Document Question Answering 2026-02-17 · ARXIV
  45. GPT-5 vs Other LLMs in Long Short-Context Performance 2026-02-17 · ARXIV
  46. Deep Dense Exploration for LLM Reinforcement Learning via Pivot-Driven Resampling 2026-02-17 · ARXIV
  47. Semantic Chunking and the Entropy of Natural Language 2026-02-16 · ARXIV
  48. Realistic Face Reconstruction from Facial Embeddings via Diffusion Models 2026-02-16 · ARXIV
  49. In-Context Autonomous Network Incident Response: An End-to-End Large Language Model Agent Approach 2026-02-16 · ARXIV
  50. Improved Regret Guarantees for Online Mirror Descent using a Portfolio of Mirror Maps 2026-02-16 · ARXIV