MiraGe: Editable 2D Images using Gaussian Splatting

waczjoan/mirage 2 Oct 2024

Our approach improves the rendering quality and allows realistic image modifications, including human-inspired perception of photos in the 3D world.

66
0.62 stars / hour

VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment

mcgill-nlp/vineppo 2 Oct 2024

In this work, we systematically evaluate the efficacy of value networks and reveal their significant shortcomings in reasoning-heavy LLM tasks, showing that they barely outperform a random baseline when comparing alternative steps.

GSM8K Math +1

56
0.49 stars / hour

OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-Conquer

om-ai-lab/OmAgent 24 Jun 2024

Recent advancements in Large Language Models (LLMs) have expanded their capabilities to multimodal contexts, including comprehensive video understanding.

AI Agent Video Understanding

779
0.48 stars / hour

Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?

xichen-fy/fira 2 Oct 2024

In this way, we can preserve the low-rank constraint in the optimizer while achieving full-rank training for better performance.

55
0.46 stars / hour

A Multi-Level Superoptimizer for Tensor Programs

mirage-project/mirage 9 May 2024

We introduce Mirage, the first multi-level superoptimizer for tensor programs.

Navigate

472
0.46 stars / hour

3DGS-DET: Empower 3D Gaussian Splatting with Boundary Guidance and Box-Focused Sampling for 3D Object Detection

yangcaoai/3dgs-det 2 Oct 2024

Neural Radiance Fields (NeRF) are widely used for novel-view synthesis and have been adapted for 3D Object Detection (3DOD), offering a promising approach to 3DOD through view-synthesis representation.

3D Object Detection Novel View Synthesis +1

73
0.43 stars / hour

CAX: Cellular Automata Accelerated in JAX

maxencefaldor/cax 3 Oct 2024

Cellular automata have become a cornerstone for investigating emergence and self-organization across diverse scientific disciplines, spanning neuroscience, artificial life, and theoretical physics.

ARC Artificial Life

51
0.42 stars / hour

Breaking reCAPTCHAv2

aplesner/Breaking-reCAPTCHAv2 13 Sep 2024

Our work examines the efficacy of employing advanced machine learning methods to solve captchas from Google's reCAPTCHAv2 system.

Image Segmentation Semantic Segmentation

205
0.38 stars / hour

Dynamic Diffusion Transformer

nus-hpc-ai-lab/dynamic-diffusion-transformer 4 Oct 2024

In addition, we design a Spatial-wise Dynamic Token (SDT) strategy to avoid redundant computation at unnecessary spatial locations.

Image Generation

23
0.38 stars / hour

AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation

MCG-NJU/AWT 5 Jul 2024

Pre-trained vision-language models (VLMs) have shown impressive results in various visual classification tasks.

Action Recognition Few-Shot Image Classification +3

53
0.36 stars / hour