X-MeshGraphNet: Scalable Multi-Scale Graph Neural Networks for Physics Simulation
By Javier Vásquez
Posted on: November 27, 2024
Graph Neural Networks (GNNs) have gained significant traction for simulating complex physical systems, with models like MeshGraphNet demonstrating strong performance on unstructured simulation meshes. However, these models face several limitations, including scalability issues, requirement for meshi...
DROID-Splat: Combining end-to-end SLAM with 3D Gaussian Splatting
By Javier Vásquez
Posted on: November 27, 2024
Recent progress in scene synthesis makes standalone SLAM systems purely based on optimizing hyperprimitives with a Rendering objective possible \cite{monogs}. However, the tracking performance still lacks behind traditional \cite{orbslam} and end-to-end SLAM systems \cite{droid}. An optimal trade-of...
DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding
By Javier Vásquez
Posted on: November 25, 2024
In this paper, we introduce DINO-X, which is a unified object-centric vision model developed by IDEA Research with the best open-world object detection performance to date. DINO-X employs the same Transformer-based encoder-decoder architecture as Grounding DINO 1.5 to pursue an object-level represen...
MMGenBench: Evaluating the Limits of LMMs from the Text-to-Image Generation Perspective
By Naomi Wilson
Posted on: November 25, 2024
Large Multimodal Models (LMMs) have demonstrated remarkable capabilities. While existing benchmarks for evaluating LMMs mainly focus on image comprehension, few works evaluate them from the image generation perspective. To address this issue, we propose a straightforward automated evaluation pipelin...
Multimodal Autoregressive Pre-training of Large Vision Encoders
By Naomi Wilson
Posted on: November 22, 2024
We introduce a novel method for pre-training of large-scale vision encoders. Building on recent advancements in autoregressive pre-training of vision models, we extend this framework to a multimodal setting, i.e., images and text. In this paper, we present AIMV2, a family of generalist vision encode...
OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMs
By Kate Martin
Posted on: November 22, 2024
Scientific progress depends on researchers' ability to synthesize the growing body of literature. Can large language models (LMs) assist scientists in this task? We introduce OpenScholar, a specialized retrieval-augmented LM that answers scientific queries by identifying relevant passages from 45 mi...
SemiKong: Curating, Training, and Evaluating A Semiconductor Industry-Specific Large Language Model
By Javier Vásquez
Posted on: November 22, 2024
Large Language Models (LLMs) have demonstrated the potential to address some issues within the semiconductor industry. However, they are often general-purpose models that lack the specialized knowledge needed to tackle the unique challenges of this sector, such as the intricate physics and chemistry...
Stereo Anything: Unifying Stereo Matching with Large-Scale Mixed Data
By Kate Martin
Posted on: November 22, 2024
Stereo matching has been a pivotal component in 3D vision, aiming to find corresponding points between pairs of stereo images to recover depth information. In this work, we introduce StereoAnything, a highly practical solution for robust stereo matching. Rather than focusing on a specialized model, ...
