Search Results for author:
Found 19 papers, 10 papers with code
The Super Weight in Large Language Models
For weight quantization, we similarly find that by preserving the super weight and clipping other weight outliers, round-to-nearest quantization can scale to much larger block sizes than previously considered.
Apple Intelligence Foundation Language Models
We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large server-based language model designed for Private Cloud Compute.
Talaria: Interactively Optimizing Machine Learning Models for Efficient Inference
On-device machine learning (ML) moves computation from the cloud to personal devices, protecting user privacy and enabling intelligent user experiences.
StableDreamer: Taming Noisy Score Distillation Sampling for Text-to-3D
Our analysis identifies the core of these challenges as the interaction among noise levels in the 2D diffusion process, the architecture of the diffusion network, and the 3D model representation.
UPSCALE: Unconstrained Channel Pruning
However, for multi-branch segments of a model, channel removal can introduce inference-time memory copies.
HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion
HyperDiffusion operates directly on MLP weights and generates new neural implicit fields encoded by synthesized MLP parameters.
PointConvFormer: Revenge of the Point-based Convolution
Hence, we preserved the invariances from point convolution, whereas attention helps to select relevant points in the neighborhood for convolution.
FvOR: Robust Joint Shape and Pose Optimization for Few-view Object Reconstruction
In this paper, we present FvOR, a learning-based object reconstruction method that predicts accurate 3D models given a few images with noisy input poses.
Texturify: Generating Textures on 3D Shape Surfaces
Texture cues on 3D objects are key to compelling visual representations, with the possibility to create high visual fidelity with inherent spatial consistency across different views.
Fast and Explicit Neural View Synthesis
We study the problem of novel view synthesis from sparse source observations of a scene comprised of 3D objects.
MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions
Deep learning has made significant impacts on multi-view stereo systems.
RetrievalFuse: Neural 3D Scene Reconstruction with a Database
3D reconstruction of large scenes is a challenging problem due to the high-complexity nature of the solution space, in particular for generative neural networks.
Equivariant Neural Rendering
We propose a framework for learning neural scene representations directly from images, without 3D supervision.
Manhattan Room Layout Reconstruction from a Single 360 image: A Comparative Study of State-of-the-art Methods
Recent approaches for predicting layouts from 360 panoramas produce excellent results.
LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image
We propose an algorithm to predict room layout from a single image that generalizes across panoramas and perspective images, cuboid layouts and more general layouts (e. g. L-shape room).
RIDI: Robust IMU Double Integration
This paper proposes a novel data-driven approach for inertial navigation, which learns to estimate trajectories of natural human motions just from an inertial measurement unit (IMU) in every smartphone.
Panoramic Structure from Motion via Geometric Relationship Detection
This paper addresses the problem of Structure from Motion (SfM) for indoor panoramic image streams, extremely challenging even for the state-of-the-art due to the lack of textures and minimal parallax.
IM2CAD
Given a single photo of a room and a large database of furniture CAD models, our goal is to reconstruct a scene that is as similar as possible to the scene depicted in the photograph, and composed of objects drawn from the database.
Occluding Contours for Multi-View Stereo
The proposed approach outperforms state of the art MVS techniques for challenging Internet datasets, yielding dramatic quality improvements both around object contours and in surface detail.
