-
How to Synthesize Text Data without Model Collapse?
Paper • 2412.14689 • Published • 52 -
SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator
Paper • 2412.12094 • Published • 11 -
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
Paper • 2306.07691 • Published • 12 -
iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform
Paper • 2203.02395 • Published • 1
ELYOR
eli02
AI & ML interests
None yet
Organizations
None yet
RAG Systems
-
VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation
Paper • 2412.10704 • Published • 16 -
How to Synthesize Text Data without Model Collapse?
Paper • 2412.14689 • Published • 52 -
Atla Selene Mini: A General Purpose Evaluation Model
Paper • 2501.17195 • Published • 35
General
-
How to Synthesize Text Data without Model Collapse?
Paper • 2412.14689 • Published • 52 -
SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator
Paper • 2412.12094 • Published • 11 -
StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models
Paper • 2306.07691 • Published • 12 -
iSTFTNet: Fast and Lightweight Mel-Spectrogram Vocoder Incorporating Inverse Short-Time Fourier Transform
Paper • 2203.02395 • Published • 1
RAG Systems
-
VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation
Paper • 2412.10704 • Published • 16 -
How to Synthesize Text Data without Model Collapse?
Paper • 2412.14689 • Published • 52 -
Atla Selene Mini: A General Purpose Evaluation Model
Paper • 2501.17195 • Published • 35
models
0
None public yet
datasets
0
None public yet