| 1. | | Why Workflows Fail: The Indeterministic Business Problem (dragonscale.ai) |
| 2 points by milliondreams 40 days ago | past | 1 comment |
|
| 2. | | Show HN: CodePrism – an AI-generated code analysis engine as MCP (rustic-ai.github.io) |
| 1 point by milliondreams 5 months ago | past | 1 comment |
|
| 3. | | VILA: On Pre-Training for Visual Language Models (arxiv.org) |
| 2 points by milliondreams on May 5, 2024 | past |
|
| 4. | | Flame: Factuality-Aware Alignment for Large Language Models (arxiv.org) |
| 3 points by milliondreams on May 4, 2024 | past |
|
| 5. | | LoRA Land: 310 Fine-Tuned LLMs That Rival GPT-4, a Technical Report (arxiv.org) |
| 3 points by milliondreams on May 3, 2024 | past |
|
| 6. | | Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing (arxiv.org) |
| 2 points by milliondreams on April 24, 2024 | past |
|
| 7. | | Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing (arxiv.org) |
| 3 points by milliondreams on April 19, 2024 | past |
|
| 8. | | ResearchAgent: Iterative Research Idea Generation Using LLMs (arxiv.org) |
| 124 points by milliondreams on April 16, 2024 | past | 63 comments |
|
| 9. | | CodecLM: Aligning Language Models with Tailored Synthetic Data (arxiv.org) |
| 2 points by milliondreams on April 14, 2024 | past |
|
| 10. | | Viking – a family of models for the Nordic languages (silo.ai) |
| 1 point by milliondreams on April 10, 2024 | past |
|
| 11. | | Mixtral-8x22B on HuggingFace (huggingface.co) |
| 33 points by milliondreams on April 10, 2024 | past | 3 comments |
|
| 12. | | Implementation of Google's Griffin Architecture – RNN LLM (github.com/google-deepmind) |
| 218 points by milliondreams on April 10, 2024 | past | 38 comments |
|
| 13. | | Griffin: RNN for Efficient Language Models (arxiv.org) |
| 2 points by milliondreams on April 10, 2024 | past |
|
| 14. | | Categorical Deep Learning: An Algebraic Theory of Architectures (arxiv.org) |
| 3 points by milliondreams on April 10, 2024 | past |
|
| 15. | | Training LLMs over Neurally Compressed Text (arxiv.org) |
| 1 point by milliondreams on April 9, 2024 | past |
|
| 16. | | TinyTimeMixer: Open-source time series LLM by IBM (huggingface.co) |
| 2 points by milliondreams on April 9, 2024 | past |
|
| 17. | | White House Announces Open Science Recognition Challenge Winners (whitehouse.gov) |
| 3 points by milliondreams on April 7, 2024 | past | 1 comment |
|
| 18. | | Mixture-of-Depths: Dynamically allocating compute in transformers (arxiv.org) |
| 281 points by milliondreams on April 7, 2024 | past | 83 comments |
|
| 19. | | Arizona State University – Can Large Language Models Reason and Plan? (arxiv.org) |
| 2 points by milliondreams on April 7, 2024 | past |
|
| 20. | | Can LLMs Every Reason? (arxiv.org) |
| 1 point by milliondreams on April 6, 2024 | past | 1 comment |
|
| 21. | | Berkeley Function-Calling Leaderboard (cs.berkeley.edu) |
| 2 points by milliondreams on April 6, 2024 | past | 1 comment |
|
| 22. | | Language models as compilers: Simulating pseudocode execution (arxiv.org) |
| 170 points by milliondreams on April 4, 2024 | past | 52 comments |
|
| 23. | | GLM: Genome Language Model – Deep learning to predict gene function (nature.com) |
| 3 points by milliondreams on April 4, 2024 | past |
|
| 24. | | Evolution of RAG (arxiv.org) |
| 1 point by milliondreams on April 2, 2024 | past |
|
| 25. | | Lumos: Learning Agents with Unified Data, Modular Design, and Open-Source LLMs (allenai.github.io) |
| 102 points by milliondreams on April 2, 2024 | past | 10 comments |
|
| 26. | | Mistral 7B v0.2 (huggingface.co) |
| 2 points by milliondreams on April 1, 2024 | past | 1 comment |
|
| 27. | | Ask HN: What do you all think of Modular's Mojo |
| 5 points by milliondreams on April 1, 2024 | past | 1 comment |
|
| 28. | | InternLM2 (arxiv.org) |
| 136 points by milliondreams on March 31, 2024 | past | 24 comments |
|
| 29. | | Adaptive RAG – dynamic retrieval methods adjustment (arxiv.org) |
| 126 points by milliondreams on March 31, 2024 | past | 39 comments |
|
| 30. | | Mini-Gemini: Mining the Potential of Multi-Modality Vision Language Models (arxiv.org) |
| 83 points by milliondreams on March 31, 2024 | past | 7 comments |
|
|
| More |
