OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation Paper • 2412.02592 • Published 22 days ago • 20
A Generalized Bandsplit Neural Network for Cinematic Audio Source Separation Paper • 2309.02539 • Published Sep 5, 2023
A Stem-Agnostic Single-Decoder System for Music Source Separation Beyond Four Stems Paper • 2406.18747 • Published Jun 26
Efficient Retrieval of Temporal Event Sequences from Textual Descriptions Paper • 2410.14043 • Published Oct 17
Enhancing Conditional Image Generation with Explainable Latent Space Manipulation Paper • 2408.16232 • Published Aug 29 • 1
EconLogicQA: A Question-Answering Benchmark for Evaluating Large Language Models in Economic Sequential Reasoning Paper • 2405.07938 • Published May 13
GeorgiaTech/0.0005_llama_nodpo_3iters_bs128_531lr_oldtrl_iter_3 Text Generation • Updated May 13 • 19
GeorgiaTech/0.0005_zephyr_withdpo_5551_4iters_bs256_newtrl_iter_3 Text Generation • Updated May 12 • 19
GeorgiaTech/0.0005_llama_nodpo_3iters_bs128_531lr_oldtrl_iter_2 Text Generation • Updated May 12 • 101
GeorgiaTech/0.0005_llama_nodpo_3iters_bs128_531lr_oldtrl_iter_1 Text Generation • Updated May 12 • 124
PokéLLMon: A Human-Parity Agent for Pokémon Battles with Large Language Models Paper • 2402.01118 • Published Feb 2 • 29
Multimodal Attention Merging for Improved Speech Recognition and Audio Event Classification Paper • 2312.14378 • Published Dec 22, 2023