24/07/07

[junhwi]

https://www.microsoft.com/en-us/research/blog/graphrag-new-tool-for-complex-data-discovery-now-on-github/

Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems https://arxiv.org/abs/2407.01370

[shylee2021]

RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMs https://arxiv.org/abs/2407.02552

Instruction Pre-Training: Language Models are Supervised Multitask Learners https://arxiv.org/abs/2406.14491 https://huggingface.co/instruction-pretrain/instruction-synthesizer

Adam-mini: Use Fewer Learning Rates To Gain More https://arxiv.org/abs/2406.16793

---

MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases (ICML 2024) https://arxiv.org/abs/2402.14905

BERGEN: A Benchmarking Library for Retrieval-Augmented Generation https://arxiv.org/pdf/2407.01102

[seyong92]

WavTool https://wavtool.com/

Pozalabs Releases its Official Statement on Sony Music Group’s AI Training Data Concerns https://markets.businessinsider.com/news/stocks/pozalabs-releases-its-official-statement-on-sony-music-group-s-ai-training-data-concerns-1033493827

PicoAudio: Enabling Precise Timestamp and Frequency Controllability of Audio Events in Text-to-audio Generation https://arxiv.org/abs/2407.02869 https://picoaudio.github.io/

SYNDI8 https://www.youtube.com/watch?v=8otvC6I9wVA