Search Results for author:
Found 16 papers, 14 papers with code
LongVILA: Scaling Long-Context Visual Language Models for Long Videos
We introduce the long-context Multi-Modal Sequence Parallelism (MM-SP) system that efficiently parallelizes long video training and inference, enabling 2M context length training on 256 GPUs without any gradient checkpointing.
LLoCO: Learning Long Contexts Offline
We introduce LLoCO, a technique that combines context compression, retrieval, and parameter-efficient finetuning using LoRA.
RouterBench: A Benchmark for Multi-LLM Routing System
To bridge this gap, we present RouterBench, a novel evaluation framework designed to systematically assess the efficacy of LLM routing systems, along with a comprehensive dataset comprising over 405k inference outcomes from representative LLMs to support the development of routing strategies.
Magic-Me: Identity-Specific Video Customized Diffusion
To achieve this, we propose three novel components that are essential for high-quality identity preservation and stable video generation: 1) a noise initialization method with 3D Gaussian Noise Prior for better inter-frame stability; 2) an ID module based on extended Textual Inversion trained with the cropped identity to disentangle the ID information from the background 3) Face VCD and Tiled VCD modules to reinforce faces and upscale the video to higher resolution while preserving the identity's features.
A Dataset and Benchmark for Copyright Infringement Unlearning from Text-to-Image Diffusion Models
Notably, models like stable diffusion, which excel in text-to-image synthesis, heighten the risk of copyright infringement and unauthorized distribution. Machine unlearning, which seeks to eradicate the influence of specific data or concepts from machine learning models, emerges as a promising solution by eliminating the \enquote{copyright memories} ingrained in diffusion models.
TorchSparse++: Efficient Training and Inference Framework for Sparse Convolution on GPUs
On top of this, we design the Sparse Autotuner, which extends the design space of existing sparse convolution libraries and searches for the best dataflow configurations for training and inference workloads.
CVPR 2023 Text Guided Video Editing Competition
In this paper we present a retrospective on the competition and describe the winning method.
SqueezeLLM: Dense-and-Sparse Quantization
When applied to the LLaMA models, our 3-bit quantization significantly reduces the perplexity gap from the FP16 baseline by up to 2. 1x as compared to the state-of-the-art methods with the same memory requirement.
Q-Diffusion: Quantizing Diffusion Models
We propose a novel PTQ method specifically tailored towards the unique multi-timestep pipeline and model architecture of the diffusion models, which compresses the noise estimation network to accelerate the generation process.
Data Isotopes for Data Provenance in DNNs
With only query access to a trained model and no knowledge of the model training process, or control of the data labels, a user can apply statistical hypothesis testing to detect if a model has learned the spurious features associated with their isotopes by training on the user's data.
The ArtBench Dataset: Benchmarking Generative Models with Artworks
We introduce ArtBench-10, the first class-balanced, high-quality, cleanly annotated, and standardized dataset for benchmarking artwork generation.
TorchSparse: Efficient Point Cloud Inference Engine
TorchSparse directly optimizes the two bottlenecks of sparse convolution: irregular computation and data movement.
GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networks
Graph neural networks (GNNs) have been increasingly deployed in various applications that involve learning on non-Euclidean data.
Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods
Many widely used datasets for graph machine learning tasks have generally been homophilous, where nodes with similar labels connect to each other.
Ranked #2 on
Node Classification
on wiki
Graph Learning
Node Classification on Non-Homophilic (Heterophilic) Graphs
GARNET: A Spectral Approach to Robust and Scalable Graph Neural Networks
In this paper, we propose GARNET, a scalable spectral method to boost the adversarial robustness of GNN models for both homophilic and heterophilic graphs.
New Benchmarks for Learning on Non-Homophilous Graphs
Much data with graph structures satisfy the principle of homophily, meaning that connected nodes tend to be similar with respect to a specific attribute.
Ranked #4 on
Node Classification
on Yelp-Fraud
