Sublime
An inspiration engine for ideas
Had a ton of fun this weekend building a demo project: PapersGPT. It enables you to feed any scientific papers into GPT to give it deep customized knowledge. Moreover, it’s a proof-of-concept UX of the end goal of connecting arbitrary data. Demo: https://t.co/aMm7Tn5oCo... See more
Jesse Zhangx.como3-mini researcher
Give it a topic, use o3-mini for report planning w/ human feedback, then parallelize all research/writing when plan is accepted. All open source (code below)
Lance Martinx.com
Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback
abs: https://t.co/jq5xphYaoJ
... See more
Simple chunking strategies outperform sophisticated semantic chunking methods for RAG, as per this paper,
Original Problem 🤔:
RAG systems commonly use semantic chunking to split documents into coherent segments, aiming to improve retrieval performance. However, there's no systematic evidenc... See more
NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior
Wenjing Bian, Zirui Wang, Kejie Li, Jia-Wang Bian, Victor Adrian Prisacariu
tl;dr: monodepth per image -> pointclouds-> merge & optimize NERF -> PROFIT.
https://t.co/uf9Dxn5R8r... See more
