Trending Research
MiraGe: Editable 2D Images using Gaussian Splatting
waczjoan/mirage
•
•
Our approach improves the rendering quality and allows realistic image modifications, including human-inspired perception of photos in the 3D world.
VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment
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.
OmAgent: A Multi-modal Agent Framework for Complex Video Understanding with Task Divide-and-Conquer
Recent advancements in Large Language Models (LLMs) have expanded their capabilities to multimodal contexts, including comprehensive video understanding.
Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?
xichen-fy/fira
•
•
In this way, we can preserve the low-rank constraint in the optimizer while achieving full-rank training for better performance.
A Multi-Level Superoptimizer for Tensor Programs
We introduce Mirage, the first multi-level superoptimizer for tensor programs.
3DGS-DET: Empower 3D Gaussian Splatting with Boundary Guidance and Box-Focused Sampling for 3D Object Detection
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.
CAX: Cellular Automata Accelerated in JAX
Cellular automata have become a cornerstone for investigating emergence and self-organization across diverse scientific disciplines, spanning neuroscience, artificial life, and theoretical physics.
Breaking reCAPTCHAv2
aplesner/Breaking-reCAPTCHAv2
•
•
Our work examines the efficacy of employing advanced machine learning methods to solve captchas from Google's reCAPTCHAv2 system.
Dynamic Diffusion Transformer
In addition, we design a Spatial-wise Dynamic Token (SDT) strategy to avoid redundant computation at unnecessary spatial locations.
AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation
MCG-NJU/AWT
•
•
Pre-trained vision-language models (VLMs) have shown impressive results in various visual classification tasks.
