FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally

florinshen/flashsplat 12 Sep 2024

Extensive experiments demonstrate the efficiency and robustness of our method in segmenting various scenes, and its superior performance in downstream tasks such as object removal and inpainting.

91
0.69 stars / hour

iText2KG: Incremental Knowledge Graphs Construction Using Large Language Models

AuvaLab/itext2kg 5 Sep 2024

Our method demonstrates superior performance compared to baseline methods across three scenarios: converting scientific papers to graphs, websites to graphs, and CVs to graphs.

Few-Shot Learning Information Retrieval +5

372
0.64 stars / hour

NeuFlow v2: High-Efficiency Optical Flow Estimation on Edge Devices

ibaiGorordo/ONNX-NeuFlowV2-Optical-Flow 19 Aug 2024

In this paper, we propose a highly efficient optical flow method that balances high accuracy with reduced computational demands.

Optical Flow Estimation

26
0.60 stars / hour

MemoRAG: Moving towards Next-Gen RAG Via Memory-Inspired Knowledge Discovery

qhjqhj00/memorag 9 Sep 2024

Retrieval-Augmented Generation (RAG) leverages retrieval tools to access external databases, thereby enhancing the generation quality of large language models (LLMs) through optimized context.

Memorization Question Answering +2

396
0.55 stars / hour

OneGen: Efficient One-Pass Unified Generation and Retrieval for LLMs

zjunlp/onegen 8 Sep 2024

This paper introduces a novel and efficient One-pass Generation and retrieval framework (OneGen), designed to improve LLMs' performance on tasks that require both generation and retrieval.

Entity Linking RAG +1

107
0.53 stars / hour

AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

qwenlm/qwen2-vl 1 Jun 2023

We propose Activation-aware Weight Quantization (AWQ), a hardware-friendly approach for LLM low-bit weight-only quantization.

Autonomous Driving Cloud Computing +4

2,024
0.53 stars / hour

Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular Videos

coltonstearns/dynamic-gaussian-marbles 26 Jun 2024

We evaluate on the Nvidia Dynamic Scenes dataset and the DyCheck iPhone dataset, and show that Gaussian Marbles significantly outperforms other Gaussian baselines in quality, and is on-par with non-Gaussian representations, all while maintaining the efficiency, compositionality, editability, and tracking benefits of Gaussians.

Novel View Synthesis Point Tracking

80
0.52 stars / hour

Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking

ezelikman/quiet-star 14 Mar 2024

Crucially, these improvements require no fine-tuning on these tasks.

GSM8K Language Modelling +1

502
0.51 stars / hour

RealisDance: Equip controllable character animation with realistic hands

damo-cv/realisdance 10 Sep 2024

2) The hands generated using the DWPose sequence are blurry and unrealistic.

97
0.51 stars / hour

gsplat: An Open-Source Library for Gaussian Splatting

nerfstudio-project/gsplat 10 Sep 2024

gsplat is an open-source library designed for training and developing Gaussian Splatting methods.

1,896
0.51 stars / hour