about
Stories from October 12, 2023 (UTC)
Go back a day, month, or year. Go forward a day.
1. Why Do We Need Weight Decay in Modern Deep Learning? (arxiv.org)
3 points by sebg on Oct 12, 2023 | hide | past | pdf | discuss
2. SWE-Bench: Can Language Models Resolve Real-World GitHub Issues? (arxiv.org)
2 points by t0e on Oct 12, 2023 | hide | past | pdf | discuss
3. Llark: An LLM which understands music (arxiv.org)
2 points by xavriley on Oct 12, 2023 | hide | past | pdf | 1 comment
4. High-Fidelity Head Avatar via Facial Model Conditioned Neural Radiance Field (arxiv.org)
2 points by PaulHoule on Oct 12, 2023 | hide | past | pdf | discuss
5. The Geometry of Truth: Emergent Linear Structure in How LLMs Represent Truth (arxiv.org)
1 point by famouswaffles on Oct 12, 2023 | hide | past | pdf | 1 comment