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

