| 1. | Code Health Guardian | 1,112 | |
|
| 2. | Going Back and Beyond: Emerging (Old) Threats in LLM Privacy and Poisoning | 367 | |
|
| 3. | Leveraging Per-Instance Privacy for Machine Unlearning | 147 | |
|
| 4. | POPri: Private Federated Learning using Preference-Optimized Synthetic Data | 197 | |
|
| 5. | Worst-Case Membership Inference of Language Models | 139 | |
|
| 6. | Disparate Privacy Risks from Medical AI - An Investigation into Patient-level Privacy Risk | 131 | |
|
| 7. | Private Adaptations of Large Language Models | 190 | |
|
| 8. | Stable Estimators for Fast Private Statistics | 95 | |
|
| 9. | Cascading Adversarial Bias from Injection to Distillation in Language Models | 96 | |
|
| 10. | The Limits and Possibilities of One Run Auditing | 102 | |
|
| 11. | Threat Models for Memorization: Privacy, Copyright, and Everything In-Between | 124 | |
|
| 12. | Differentially Private Synthetic Data without Training | 82 | |
|
| 13. | Persistent Pre-Training Poisoning of LLMs | 51 | |
|
| 14. | Privacy Ripple Effects from Adding or Removing Personal Information in Language Model Training | 94 | |
|
| 15. | Streaming Private Continual Counting via Binning | 98 | |
|
| 16. | Privacy Auditing of Large Language Models | 106 | |
|
| 17. | Optimistic Verifiable Training by Controlling Hardware Nondeterminism | 34 | |
|
| 18. | Continual Release Moment Estimation with Differential Privacy | 29 | |
|
| 19. | Differentially Private Prototypes for Imbalanced Transfer Learning | 92 | |
|
| 20. | Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data? | 33 | |
|
| 21. | Chasing the Constants and its Implications in Differential Privacy | 30 | |
|
| 22. | Cascading Adversarial Bias from Injection to Distillation in Language Models | 35 | |
|
| 23. | The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage | 64 | |
|
| 24. | Differentially Private Multiway and k-Cut | 46 | |
|
| 25. | How Much Do Language Models Memorize? | 80 | |
|
| 26. | Watermarking in Generative AI: Opportunities and Threats | 64 | |
|
| 27. | Beyond Trust: Proving Fairness and Privacy in Machine Learning | 32 | |
|
| 28. | Evaluating Data Misuse in LLMs: Introducing Adversarial Compression Rate as a Metric of Memorization | 32 | |
|
| 29. | Streaming Attention Approximation via Discrepancy Theory | 751 | |
|
| 30. | Is Learning Effective in Dynamic Strategic Interactions? Evidence from Stackelberg Games | 577 | |
|
| 31. | Algorithmic Contract Design | 757 | |
|
| 32. | Online Learning and Economics | 588 | |
|
| 33. | Go Meetup April 2025 - i18n Go Experiment | 818 | |
|
| 34. | Go Meetup April 2025 - Whats New in Go 1.24? | 624 | |
|
| 35. | Go Meetup April 2025 - Git Bisect and Go Size Analyzer | 271 | |
|
| 36. | Go Meetup April 2025 - Photobooth | 388 | |
|
| 37. | Go Meetup April 2025 - Go Protobuf | 918 | |
|
| 38. | Understanding LLMs Like Physicists: Observation, Hypothesis, Experimentation, and Prediction | 1,527 | |
|
| 39. | Theoretical Limitations of Multi layer Transformers | 1,305 | |
|
| 40. | Hash Functions: Bridging the Gap from Theory to Practice | 1,207 | |
|
| 41. | LLM Dataset Inference: Did you train on my dataset? | 1,545 | |
|
| 42. | Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty | 1,052 | |
|
| 43. | AI Snake Oil | 2,298 | |
|
| 44. | How I Wrote 10K Lines of Go in a Weekend | 2,561 | |
|
| 45. | Supply Chain Security with Go | 1,261 | |
|
| 46. | A Multi Dimensional Online Contention Resolution Scheme | 621 | |
|
| 47. | Robust Distortion-free Watermarks for Language Models | 1,284 | |
|
| 48. | Is it possible to make self-adjusting data structures concurrent? | 1,230 | |
|
| 49. | Privacy Preserving ML with Fully Homomorphic Encryption | 2,020 | |
|
| 50. | The Chinese Computer: A Global History of the Information Age | 1,212 | Guide |
|
| 51. | KAN: Kolmogorov-Arnold Networks | 11,896 | |
|
| 52. | Learning through Transient Matching in Congested Markets | 685 | |
|
| 53. | What Makes Software Work? | 2,518 | |
|
| 54. | Algorithms and Hardness for Attention and Kernel Density Estimation | 532 | |
|
| 55. | A Unified Analysis of Label Inference Attacks | 364 | |
|
| 56. | Copyright Regenerated: Harnessing GenAI to Measure Originality and Copyright Scope | 263 | |
|
| 57. | Oblivious RAM: From Theory to Large-scale Real-world Deployment | 386 | |
|
| 58. | The Data Minimization Principle in Machine Learning | 452 | |
|
| 59. | Can LLMs Keep a Secret? Testing Privacy Implications of Language Models | 335 | |
|
| 60. | Low Cost High Power Membership Inference Attacks | 282 | |
|
| 61. | Challenges in Augmenting Large Language Models with Private Data | 875 | |
|
| 62. | Design is Testability | 1,438 | |
|
| 63. | Charles Hoskinson | CEO of Input Output Global | web3 talks | Apr 4th 2024 | MC: Marlon Ruiz | 8,901 | |
|
| 64. | Limitations of Stochastic Selection with Pairwise Independent Priors | 452 | |
|
| 65. | NASA CARA - Air Traffic Control in Spaaaaaaaace | 789 | |
|
| 66. | How Your Brain Processes Code | 2,355 | |
|
| 67. | Fixed-point Error Bounds for Mean-payoff Markov Decision Processes | 481 | |
|
| 68. | One Tree to Rule Them All: Polylogarithmic Universal Steiner Trees | 1,047 | Vlog |
|
| 69. | Understanding Oversmoothing in Graph Neural Networks (GNNs): Insights from Two Theoretical Studies | 1,024 | |
|
| 70. | Socially Responsible Software Development (Teaching Software Design Systematically) | 1,185 | |
|
| 71. | Understanding and Mitigating Copying in Diffusion Models | 893 | |
|
| 72. | Efficient Training Image Extraction from Diffusion Models Ryan Webs | 890 | |
|
| 73. | High-Dimensional Prediction for Sequential Decision Making | 550 | |
|
| 74. | Representational Strengths and Limitations of Transformers | 1,687 | |
|
| 75. | Steven Goldfeder | CEO Offchain Labs / Arbitrum | web3 talks | Aug 24 2023 | MC: Marlon Ruiz | 1,076 | |
|
| 76. | Differentially Private Sampling from Distributions | 672 | |
|
| 77. | Revisiting Nearest Neighbors from a Sparse Signal Approximation View | 1,161 | |
|
| 78. | 2023 Blockly Developer Summit Day 2-5: Plug-ins Demonstration | 522 | |
|
| 79. | 2023 Blockly Developer Summit DAY 1-5: The Future of Computational Thinking | 354 | |
|
| 80. | 2023 Blockly Developer Summit DAY 1-14: BlocksCAD - Math + Coding + Design | 252 | |
|
| 81. | 2023 Blockly Developer Summit DAY 1-7: Cubi - Extending Blockly for Teachers | 260 | |
|
| 82. | 2023 Blockly Developer Summit DAY 1-12: Serialization and Visual Diff | 181 | |
|
| 83. | 2023 Blockly Developer Summit Day 2-2: Blockly Themes for Accessibility | 231 | |
|
| 84. | 2023 Blockly Developer Summit Day 2-3: Revisiting Performance in Blockly | 133 | |
|
| 85. | 2023 Blockly Developer Summit DAY 1-11: Performance | 254 | |
|
| 86. | 2023 Blockly Developer Summit Day 2-7: How to Convince Teachers to Teach Coding | 60 | |
|
| 87. | 2023 Blockly Developers Summit Day 1-1: Welcome | 365 | |
|
| 88. | 2023 Blockly Developer Summit Day 2-8: Active STEM with Unruly Splats | 79 | |
|
| 89. | 2023 Blockly Developer Summit DAY 1-9: Engineering Block-based Languages | 141 | |
|
| 90. | 2023 Blockly Developer Summit Day 2-11: Onboarding New Users | 75 | |
|
| 91. | 2023 Blockly Developer Summit Day 2-16: Curriculum Development Panel Discussion | 60 | Discussion |
|
| 92. | 2023 Blockly Developers Summit DAY 1-3: Generators | 465 | |
|
| 93. | 2023 Blockly Developer Summit Day 2-4: Parsing with Visitor Pattern | 174 | |
|
| 94. | 2023 Blockly Developer Summit Day 2-15: Thoughts on Bidirectional Text to Blocks to Text | 115 | |
|
| 95. | 2023 Blockly Developer Summit Day 2-14: Text to Blocks to Text with Layout | 59 | |
|
| 96. | 2023 Blockly Developer Summit Day 2-1: Unforking Blockly | 135 | |
|
| 97. | 2023 Blockly Developer Summit DAY 1-4: Generators - Past Present and Future | 87 | |
|
| 98. | 2023 Blockly Developer Summit Day 2-13: Unleashing Creativity - Blocks and Curricula for K-12 AI Ed | 70 | |
|
| 99. | 2023 Blockly Developer Summit DAY 1-13 Blockly meets Jupyter | 85 | |
|
| 100. | 2023 Blockly Developer Summit Day 2-6: Code.org - Sprite Lab | 69 | |
|
