Felix Brockmeier
felixbrock
		AI & ML interests
None yet
		
		Organizations
OCR
			
			
	
	cv-eval
			
			
	
	llm-model
			
			
	
	- 
	
	
	One Wide Feedforward is All You NeedPaper • 2309.01826 • Published • 33
- 
	
	
	Gated recurrent neural networks discover attentionPaper • 2309.01775 • Published • 10
- 
	
	
	FLM-101B: An Open LLM and How to Train It with $100K BudgetPaper • 2309.03852 • Published • 44
- 
	
	
	Large Language Models as OptimizersPaper • 2309.03409 • Published • 77
cv-embedding
			
			
	
	llm-gen-ai-text
			
			
	
	llm-performance
			
			
	
	- 
	
	
	Efficient Memory Management for Large Language Model Serving with PagedAttentionPaper • 2309.06180 • Published • 25
- 
	
	
	Ambiguity-Aware In-Context Learning with Large Language ModelsPaper • 2309.07900 • Published • 5
- 
	
	
	Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt OptimizersPaper • 2309.08532 • Published • 53
- 
	
	
	LASER: LLM Agent with State-Space Exploration for Web NavigationPaper • 2309.08172 • Published • 13
llm-agent
			
			
	
	privacy/security
			
			
	
	llm-eval
			
			
	
	- 
	
	
	Prometheus: Inducing Fine-grained Evaluation Capability in Language ModelsPaper • 2310.08491 • Published • 55
- 
	
	
	Self-RAG: Learning to Retrieve, Generate, and Critique through Self-ReflectionPaper • 2310.11511 • Published • 78
- 
	
	
	Calibrating LLM-Based EvaluatorPaper • 2309.13308 • Published • 12
- 
	
	
	Fusion-Eval: Integrating Evaluators with LLMsPaper • 2311.09204 • Published • 6
cv-gen-ai-3D
			
			
	
	- 
	
	
	TeCH: Text-guided Reconstruction of Lifelike Clothed HumansPaper • 2308.08545 • Published • 34
- 
	
	
	AniPortraitGAN: Animatable 3D Portrait Generation from 2D Image CollectionsPaper • 2309.02186 • Published • 22
- 
	
	
	3D Gaussian Splatting for Real-Time Radiance Field RenderingPaper • 2308.04079 • Published • 191
- 
	
	
	ControlMat: A Controlled Generative Approach to Material CapturePaper • 2309.01700 • Published • 16
dataset
			
			
	
	cv-pre-eval
			
			
	
	RLHF/RLAIF
			
			
	
	- 
	
	
	Efficient RLHF: Reducing the Memory Usage of PPOPaper • 2309.00754 • Published • 15
- 
	
	
	Statistical Rejection Sampling Improves Preference OptimizationPaper • 2309.06657 • Published • 14
- 
	
	
	Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?Paper • 2309.07462 • Published • 5
- 
	
	
	Stabilizing RLHF through Advantage Model and Selective RehearsalPaper • 2309.10202 • Published • 11
llm-system
			
			
	
	text-to-image-model
			
			
	
	- 
	
	
	InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image GenerationPaper • 2309.06380 • Published • 32
- 
	
	
	PhotoVerse: Tuning-Free Image Customization with Text-to-Image Diffusion ModelsPaper • 2309.05793 • Published • 50
- 
	
	
	DreamStyler: Paint by Style Inversion with Text-to-Image Diffusion ModelsPaper • 2309.06933 • Published • 13
- 
	
	
	MagiCapture: High-Resolution Multi-Concept Portrait CustomizationPaper • 2309.06895 • Published • 27
llm-monitoring
			
			
	
	llm-doc-retrieval
			
			
	
	cv-performance
			
			
	
	selflearning
			
			
	
	llm-pretraining
			
			
	
	cv-gen-ai-3D
			
			
	
	- 
	
	
	TeCH: Text-guided Reconstruction of Lifelike Clothed HumansPaper • 2308.08545 • Published • 34
- 
	
	
	AniPortraitGAN: Animatable 3D Portrait Generation from 2D Image CollectionsPaper • 2309.02186 • Published • 22
- 
	
	
	3D Gaussian Splatting for Real-Time Radiance Field RenderingPaper • 2308.04079 • Published • 191
- 
	
	
	ControlMat: A Controlled Generative Approach to Material CapturePaper • 2309.01700 • Published • 16
OCR
			
			
	
	dataset
			
			
	
	cv-eval
			
			
	
	cv-pre-eval
			
			
	
	llm-model
			
			
	
	- 
	
	
	One Wide Feedforward is All You NeedPaper • 2309.01826 • Published • 33
- 
	
	
	Gated recurrent neural networks discover attentionPaper • 2309.01775 • Published • 10
- 
	
	
	FLM-101B: An Open LLM and How to Train It with $100K BudgetPaper • 2309.03852 • Published • 44
- 
	
	
	Large Language Models as OptimizersPaper • 2309.03409 • Published • 77
RLHF/RLAIF
			
			
	
	- 
	
	
	Efficient RLHF: Reducing the Memory Usage of PPOPaper • 2309.00754 • Published • 15
- 
	
	
	Statistical Rejection Sampling Improves Preference OptimizationPaper • 2309.06657 • Published • 14
- 
	
	
	Are Large Language Model-based Evaluators the Solution to Scaling Up Multilingual Evaluation?Paper • 2309.07462 • Published • 5
- 
	
	
	Stabilizing RLHF through Advantage Model and Selective RehearsalPaper • 2309.10202 • Published • 11
cv-embedding
			
			
	
	llm-system
			
			
	
	llm-gen-ai-text
			
			
	
	text-to-image-model
			
			
	
	- 
	
	
	InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image GenerationPaper • 2309.06380 • Published • 32
- 
	
	
	PhotoVerse: Tuning-Free Image Customization with Text-to-Image Diffusion ModelsPaper • 2309.05793 • Published • 50
- 
	
	
	DreamStyler: Paint by Style Inversion with Text-to-Image Diffusion ModelsPaper • 2309.06933 • Published • 13
- 
	
	
	MagiCapture: High-Resolution Multi-Concept Portrait CustomizationPaper • 2309.06895 • Published • 27
llm-performance
			
			
	
	- 
	
	
	Efficient Memory Management for Large Language Model Serving with PagedAttentionPaper • 2309.06180 • Published • 25
- 
	
	
	Ambiguity-Aware In-Context Learning with Large Language ModelsPaper • 2309.07900 • Published • 5
- 
	
	
	Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt OptimizersPaper • 2309.08532 • Published • 53
- 
	
	
	LASER: LLM Agent with State-Space Exploration for Web NavigationPaper • 2309.08172 • Published • 13
llm-monitoring
			
			
	
	llm-agent
			
			
	
	llm-doc-retrieval
			
			
	
	privacy/security
			
			
	
	cv-performance
			
			
	
	llm-eval
			
			
	
	- 
	
	
	Prometheus: Inducing Fine-grained Evaluation Capability in Language ModelsPaper • 2310.08491 • Published • 55
- 
	
	
	Self-RAG: Learning to Retrieve, Generate, and Critique through Self-ReflectionPaper • 2310.11511 • Published • 78
- 
	
	
	Calibrating LLM-Based EvaluatorPaper • 2309.13308 • Published • 12
- 
	
	
	Fusion-Eval: Integrating Evaluators with LLMsPaper • 2311.09204 • Published • 6
selflearning
			
			
	
	
