ML Newsnew | past | best | rss | submit about
Stories from March 17, 2026 (UTC)
Go back a day, month, or year. Go forward a day.
1. Why AI systems don't learn – On autonomous learning from cognitive science (arxiv.org)
205 points by aanet 200 days ago | hide | past | pdf | 116 comments
2. Flash-KMeans: Fast and Memory-Efficient Exact K-Means (arxiv.org)
185 points by matt_d 201 days ago | hide | past | pdf | 14 comments
3. Kimi introduces Attention Residuals: 1.25x compute performance at <2% overhead (arxiv.org)
9 points by nekofneko 201 days ago | hide | past | pdf | discuss
4. Automating Forecasting Question Generation and Resolution for AI Evaluation (arxiv.org)
3 points by nbosse 201 days ago | hide | past | pdf | discuss
5. True 4-Bit Quantized CNN Training on CPU – 92.34% on Cifar-10 (arxiv.org)
3 points by shivnathtathe 201 days ago | hide | past | pdf | 3 comments
6. Benchmarking Distilled Language Models for Performance and Efficiency (arxiv.org)
2 points by PaulHoule 201 days ago | hide | past | pdf | discuss
7. Generative Video Compression with One-Dimensional Latent Representation (arxiv.org)
2 points by selimonder 201 days ago | hide | past | pdf | discuss
8. Pimp My LLM: Leveraging Variability Modeling to Tune Inference Hyperparameters (arxiv.org)
1 point by PaulHoule 201 days ago | hide | past | pdf | 1 comment
9. Real-World Industrial-Scale Verification: LLM-Driven Theorem Proving on SeL4 (arxiv.org)
1 point by PaulHoule 201 days ago | hide | past | pdf | discuss
10. We Ran the Largest AI Pokemon Tournament Ever. Now It's an Open Benchmark (arxiv.org)
1 point by milkkarten 201 days ago | hide | past | pdf | discuss
About | RSS | RSS (all) | HN arXiv