- Memoir: Lifelong Model Editing with Minimal Overwrite Informed Retention for LLM
by dataminer on 6/14/25, 4:29 AM, with comments
- The Earliest Language Model
by dataminer on 4/21/25, 12:16 PM, with comments
- Ai2 Paper Finder
by dataminer on 3/27/25, 6:25 PM, with comments
- Transformers Without Normalization
by dataminer on 3/14/25, 7:01 PM, with comments
- GeForce RTX 5090 fails to topple RTX 4090 in GPU compute benchmark
by dataminer on 2/8/25, 7:16 PM, with comments
- FireDucks Compiler Accelerated DataFrame Library for Python
by dataminer on 2/8/25, 4:19 PM, with comments
- DeepSeek-R1, Q8 Quant (Max Quality). 768GB of DDR5, 2x AMD EPYC CPU, No GPU
by dataminer on 1/28/25, 9:24 PM, with comments
- Huawei has a new chip to rival Nvidia's AI GPUs – Ascend 910C
by dataminer on 1/26/25, 7:06 PM, with comments
- What the First All-EV Car Market Looks Like
by dataminer on 11/29/24, 3:55 PM, with comments
- Scientist treated her own cancer with viruses she grew in the lab
by dataminer on 11/9/24, 2:23 PM, with comments
- Zamba2-7B
by dataminer on 10/14/24, 10:45 PM, with comments
- Mike Little
by dataminer on 10/14/24, 8:33 PM, with comments
- Day Trader Says He Made $306M on Tesla, Then Lost It All
by dataminer on 10/5/24, 7:31 AM, with comments
- OpenAI Discusses Giving Altman 7% Stake in For-Profit Shift
by dataminer on 9/26/24, 1:26 AM, with comments
- Macklem Warns AI May Push Prices Higher Through Demand Boost
by dataminer on 9/20/24, 5:13 PM, with comments
- DifuzCam: Replacing Camera Lens with a Mask and a Diffusion Model
by dataminer on 8/17/24, 4:50 PM, with comments
- Robots and Specialized Software Open New Solar Farm Development Opportunities
by dataminer on 6/18/24, 12:41 PM, with comments
- The Geometry of Categorical and Hierarchical Concepts in Large Language Models
by dataminer on 6/6/24, 2:03 AM, with comments
- Python 3.12 Preview: Subinterpreters
by dataminer on 6/2/24, 4:07 PM, with comments
- Have live audio/video conversations with ChatGPT
by dataminer on 5/13/24, 6:31 PM, with comments
- Adding NVMe SSDs to Enable and Accelerate 100B Model Fine-Tuning on a Single GPU
by dataminer on 3/13/24, 1:44 PM, with comments
- Humanoid Locomotion as Next Token Prediction
by dataminer on 3/3/24, 1:19 PM, with comments
- How do Spotify Codes work?
by dataminer on 2/6/24, 8:47 PM, with comments
- Variational autoencoder for design of synthetic viral vector serotypes
by dataminer on 1/24/24, 11:10 PM, with comments
- How AI is decoding the animal kingdom
by dataminer on 1/19/24, 1:51 PM, with comments
- Unified diffs make GPT-4 Turbo less lazy
by dataminer on 1/10/24, 11:55 PM, with comments
- LLM Augmented LLMs: Expanding Capabilities Through Composition
by dataminer on 1/6/24, 6:18 PM, with comments
- 2084: MarcRandbot: Speech Synthesis with Mamba
by dataminer on 1/5/24, 4:21 AM, with comments
- Losing weight without any stress
by dataminer on 12/30/23, 3:18 PM, with comments
- Degrowth can work here’s how science can help
by dataminer on 12/30/23, 4:40 AM, with comments
- High-Speed Large Language Model Serving on PCs with Consumer-Grade GPUs
by dataminer on 12/20/23, 1:46 PM, with comments
- Gated Linear Attention Transformers with Hardware-Efficient Training
by dataminer on 12/12/23, 2:20 PM, with comments
- Every Bitcoin payment 'uses a swimming pool of water'
by dataminer on 11/29/23, 5:44 PM, with comments
- Trends in Deep Learning Hardware: Bill Dally (Nvidia) [video]
by dataminer on 11/28/23, 9:48 PM, with comments
- Self-Refine: Iterative Refinement with Self-Feedback
by dataminer on 11/24/23, 1:15 AM, with comments
- Machine Learning Engineering Guides and Tools
by dataminer on 10/14/23, 12:32 PM, with comments
- In London, the Long Wait for a Super Sewer Is Almost Over
by dataminer on 9/25/23, 3:58 PM, with comments
- Auto-Regressive Next-Token Predictors Are Universal Learners
by dataminer on 9/23/23, 12:31 AM, with comments
- Parameter-Free Molecular Classification and Regression with Gzip
by dataminer on 7/28/23, 9:34 PM, with comments
- Eli Lilly experimental obesity drug helped patients lose upto 24% of weight
by dataminer on 6/27/23, 4:01 AM, with comments
- The testing framework dedicated to ML models, from tabular to LLMs
by dataminer on 6/23/23, 3:47 AM, with comments
- The Rate of Return on Everything, 1870–2015 [pdf]
by dataminer on 6/15/23, 11:24 PM, with comments
- Hybrid Electric Powered Multi-Lobed Airship for Sustainable Aviation
by dataminer on 5/28/23, 1:35 PM, with comments
- Ellison's Cave
by dataminer on 5/21/23, 6:41 PM, with comments
- Virus-Like “Jumping” DNA Regulates Human Neurons
by dataminer on 5/17/23, 4:21 AM, with comments
- The 1% of the population accountable for 63 % of all violent crime convictions (2013)
by dataminer on 5/15/23, 1:59 AM, with comments
- The Little Book of Deep Learning [pdf]
by dataminer on 5/1/23, 12:18 AM, with comments