pengxiang (Pengxiang Li)

upvoted a paper 3 days ago

Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers

Paper • 2409.04109 • Published 14 days ago • 37

upvoted a paper 19 days ago

Diffusion Models Are Real-Time Game Engines

Paper • 2408.14837 • Published 24 days ago • 119

upvoted 3 papers about 1 month ago

upvoted a paper about 2 months ago

MoMa: Efficient Early-Fusion Pre-training with Mixture of Modality-Aware Experts

Paper • 2407.21770 • Published Jul 31 • 20

upvoted an article about 2 months ago

Article

Mixture of Depth is Vibe

By

•

Apr 22

• 43

upvoted 4 papers about 2 months ago

SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models

Paper • 2407.15841 • Published Jul 22 • 38

E5-V: Universal Embeddings with Multimodal Large Language Models

Paper • 2407.12580 • Published Jul 17 • 38

Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion

Paper • 2407.13759 • Published Jul 18 • 17

EVLM: An Efficient Vision-Language Model for Visual Understanding

Paper • 2407.14177 • Published Jul 19 • 42

upvoted a paper 3 months ago

Step-aware Preference Optimization: Aligning Preference with Denoising Performance at Each Step

Paper • 2406.04314 • Published Jun 6 • 26

upvoted 7 papers 4 months ago

OwLore: Outlier-weighed Layerwise Sampled Low-Rank Projection for Memory-Efficient LLM Fine-tuning

Paper • 2405.18380 • Published May 28 • 1

Chameleon: Mixed-Modal Early-Fusion Foundation Models

Paper • 2405.09818 • Published May 16 • 125

LoRA Learns Less and Forgets Less

Paper • 2405.09673 • Published May 15 • 86

Personalized Residuals for Concept-Driven Text-to-Image Generation

Paper • 2405.12978 • Published May 21 • 9

Multi-Head Mixture-of-Experts

Paper • 2404.15045 • Published Apr 23 • 58

WildChat: 1M ChatGPT Interaction Logs in the Wild

Paper • 2405.01470 • Published May 2 • 59

StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation

Paper • 2405.01434 • Published May 2 • 51

upvoted 2 papers 5 months ago

Layer Skip: Enabling Early Exit Inference and Self-Speculative Decoding

Paper • 2404.16710 • Published Apr 25 • 57

Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video

Paper • 2404.09833 • Published Apr 15 • 29

upvoted an article 5 months ago

Article

Llama 2 is here - get it on Hugging Face

Jul 18, 2023

• 19

upvoted a paper 6 months ago

The Unreasonable Ineffectiveness of the Deeper Layers

Paper • 2403.17887 • Published Mar 26 • 77

upvoted a paper 8 months ago

Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion

Paper • 2402.03162 • Published Feb 5 • 17

upvoted a paper 10 months ago

GAIA: a benchmark for General AI Assistants

Paper • 2311.12983 • Published Nov 21, 2023 • 182

upvoted a paper 11 months ago

An Early Evaluation of GPT-4V(ision)

Paper • 2310.16534 • Published Oct 25, 2023 • 21

upvoted 2 papers about 1 year ago

DETR Doesn't Need Multi-Scale or Locality Design

Paper • 2308.01904 • Published Aug 3, 2023 • 7

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models

Paper • 2305.13655 • Published May 23, 2023 • 7

upvoted a paper over 1 year ago

GeneCIS: A Benchmark for General Conditional Image Similarity

Paper • 2306.07969 • Published Jun 13, 2023 • 4

Pengxiang Li

AI & ML interests

Organizations

pengxiang's activity