charlescai2016 (Charles Cai)

upvoted a paper about 1 month ago

Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers

Paper • 2408.06195 • Published Aug 12 • 53

upvoted an article about 1 month ago

Article

Memory-efficient Diffusion Transformers with Quanto and Diffusers

Jul 30

• 50

upvoted 2 papers about 1 month ago

GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS

Paper • 2408.01584 • Published Aug 2 • 7

Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Paper • 2408.02657 • Published Aug 5 • 32

upvoted a paper about 2 months ago

Adding Conditional Control to Text-to-Image Diffusion Models

Paper • 2302.05543 • Published Feb 10, 2023 • 34

upvoted an article about 2 months ago

Article

TGI Multi-LoRA: Deploy Once, Serve 30 Models

Jul 18

• 42

upvoted an article 2 months ago

Article

Fine-tune Llama 3 with ORPO

By

•

Apr 22

• 218

upvoted a collection 2 months ago

FP8 LLMs for vLLM

Collection

Accurate FP8 quantized models by Neural Magic, ready for use with vLLM! • 37 items • Updated 20 days ago • 50

upvoted 2 papers 2 months ago

Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems

Paper • 2407.01370 • Published Jul 1 • 84

Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP

Paper • 2407.00402 • Published Jun 29 • 22

upvoted a collection 3 months ago

Graph-enhanced RAG

Collection

using knowledge graphs in RAG for grounding LLM results • 21 items • Updated 17 days ago • 7

upvoted 3 papers 3 months ago

upvoted a paper 4 months ago

Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts

Paper • 2405.11273 • Published May 18 • 17

upvoted an article 4 months ago

Article

Making LLMs lighter with AutoGPTQ and transformers

Aug 23, 2023

• 25

upvoted an article 5 months ago

Article

Powerful ASR + diarization + speculative decoding with Hugging Face Inference Endpoints

May 1

• 60

upvoted a paper 6 months ago

Chronos: Learning the Language of Time Series

Paper • 2403.07815 • Published Mar 12 • 45

upvoted 2 papers 7 months ago

GPTVQ: The Blessing of Dimensionality for LLM Quantization

Paper • 2402.15319 • Published Feb 23 • 19

FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models

Paper • 2402.10986 • Published Feb 16 • 76

upvoted a paper 9 months ago

LLM360: Towards Fully Transparent Open-Source LLMs

Paper • 2312.06550 • Published Dec 11, 2023 • 56

upvoted a paper 11 months ago

CustomNet: Zero-shot Object Customization with Variable-Viewpoints in Text-to-Image Diffusion Models

Paper • 2310.19784 • Published Oct 30, 2023 • 9

upvoted a paper 12 months ago

LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent

Paper • 2309.12311 • Published Sep 21, 2023 • 17

Charles Cai

AI & ML interests

Organizations

charlescai2016's activity

Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers

Memory-efficient Diffusion Transformers with Quanto and Diffusers

GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS

Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Adding Conditional Control to Text-to-Image Diffusion Models

TGI Multi-LoRA: Deploy Once, Serve 30 Models

Fine-tune Llama 3 with ORPO

FP8 LLMs for vLLM

Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems

Is It Really Long Context if All You Need Is Retrieval? Towards Genuinely Difficult Long Context NLP

Graph-enhanced RAG

Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges

4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models

Teaching Large Language Models to Reason with Reinforcement Learning

Uni-MoE: Scaling Unified Multimodal LLMs with Mixture of Experts

Making LLMs lighter with AutoGPTQ and transformers

Powerful ASR + diarization + speculative decoding with Hugging Face Inference Endpoints

Chronos: Learning the Language of Time Series

GPTVQ: The Blessing of Dimensionality for LLM Quantization

FinTral: A Family of GPT-4 Level Multimodal Financial Large Language Models

LLM360: Towards Fully Transparent Open-Source LLMs

CustomNet: Zero-shot Object Customization with Variable-Viewpoints in Text-to-Image Diffusion Models

LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent