wassname
  • Joined on 2026-02-05
Updated 2025-08-20 14:21:57 +08:00
A logical, reasonably standardized, but flexible project structure for doing and sharing data science work.
Updated 2025-06-11 10:33:14 +08:00
Robust recipes to align language models with human and AI preferences
Updated 2025-06-04 13:37:07 +08:00
SimPO: Simple Preference Optimization with a Reference-Free Reward
Updated 2025-06-02 13:26:08 +08:00
Integrating ChatGPT into your browser deeply, everything you need is here
Updated 2025-05-01 05:15:20 +08:00
Updated 2025-04-27 15:37:14 +08:00
implementing "recurrent attentive neural processes" to forecast power usage (w. LSTM baseline, MCDropout)
Updated 2025-03-22 05:57:13 +08:00
Attempting to replicate "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem" https://arxiv.org/abs/1706.10059 (and an openai gym environment)
Updated 2025-03-18 18:42:00 +08:00
A high-throughput and memory-efficient inference and serving engine for LLMs
Updated 2025-03-07 08:18:58 +08:00
A basic editor for xBrowserSync json backup files
Updated 2024-11-09 10:49:53 +08:00
Generalization Analogies: A Testbed for Generalizing AI Oversight to Hard-To-Measure Domains
Updated 2024-08-25 15:06:10 +08:00
Updated 2024-08-07 21:50:03 +08:00
Videos of deep learning optimizers moving on 3D problem-landscapes
Updated 2024-07-25 18:12:05 +08:00
Research dataset. We use prompts to get LLM's to lie. Using sys prompts and multi shot examples
Updated 2024-07-02 18:25:13 +08:00
Hackable frontend for LLM assisted searching with citations
Updated 2024-06-29 20:18:49 +08:00