Search Results for author:
Found 57 papers, 33 papers with code
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.
HAWQ-V2: Hessian Aware trace-Weighted Quantization of Neural Networks
However, the search space for a mixed-precision quantization is exponential in the number of layers.
HAWQ: Hessian AWare Quantization of Neural Networks with Mixed-Precision
Another challenge is a similar factorial complexity for determining block-wise fine-tuning order when quantizing the model to a target precision.
HAWQV3: Dyadic Neural Network Quantization
Current low-precision quantization algorithms often have the hidden cost of conversion back and forth from floating point to quantized integer values.
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.
Iterative Global Similarity Points : A robust coarse-to-fine integration solution for pairwise 3D point cloud registration
Then, we formulate the correspondence matching task as an energy function, which models the global similarity of keypoints on the hybrid spaces of BSC feature and Euclidean geometry.
ZeroQ: A Novel Zero Shot Quantization Framework
Importantly, ZeroQ has a very low computational overhead, and it can finish the entire quantization process in less than 30s (0. 5\% of one epoch training time of ResNet50 on ImageNet).
Ranked #1 on
Data Free Quantization
on CIFAR10
(CIFAR-10 W8A8 Top-1 Accuracy metric)
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.
FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators
Matching cross-modality features between images and point clouds is a fundamental problem for image-to-point cloud registration.
Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting
Previous multiview registration methods rely on exhaustive pairwise registration to construct a densely-connected pose graph and apply Iteratively Reweighted Least Square (IRLS) on the pose graph to compute the scan poses.
LLM Inference Unveiled: Survey and Roofline Model Insights
Our survey stands out from traditional literature reviews by not only summarizing the current state of research but also by introducing a framework based on roofline model for systematic analysis of LLM inference techniques.
PB-LLM: Partially Binarized Large Language Models
This paper explores network binarization, a radical form of quantization, compressing model weights to a single bit, specifically for Large Language Models (LLMs) compression.
You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors
In this paper, we propose a novel local descriptor-based framework, called You Only Hypothesize Once (YOHO), for the registration of two unaligned point clouds.
Ranked #5 on
Point Cloud Registration
on ETH (trained on 3DMatch)
(Recall (30cm, 5 degrees) metric)
Mobile-Seed: Joint Semantic Segmentation and Boundary Detection for Mobile Robots
Our framework features a two-stream encoder, an active fusion decoder (AFD) and a dual-task regularization approach.
SparseDC: Depth Completion from sparse and non-uniform inputs
The key contributions of SparseDC are two-fold.
CVPR 2023 Text Guided Video Editing Competition
In this paper we present a retrospective on the competition and describe the winning method.
3D Shape Reconstruction from 2D Images with Disentangled Attribute Flow
Reconstructing 3D shape from a single 2D image is a challenging task, which needs to estimate the detailed 3D structures based on the semantic attributes from 2D image.
AdaFit: Rethinking Learning-based Normal Estimation on Point Clouds
Existing works use a network to learn point-wise weights for weighted least squares surface fitting to estimate the normals, which has difficulty in finding accurate normals in complex regions or containing noisy points.
Ranked #5 on
Surface Normals Estimation
on PCPNet
P2-Net: Joint Description and Detection of Local Features for Pixel and Point Matching
Accurately describing and detecting 2D and 3D keypoints is crucial to establishing correspondences across images and point clouds.
Hessian-Aware Pruning and Optimal Neural Implant
To address this problem, we introduce a new Hessian Aware Pruning (HAP) method coupled with a Neural Implant approach that uses second-order sensitivity as a metric for structured pruning.
DeepAAT: Deep Automated Aerial Triangulation for Fast UAV-based Mapping
The experimental results demonstrate DeepAAT's substantial improvements over conventional AAT methods, highlighting its potential in the efficiency and accuracy of UAV-based 3D reconstruction tasks.
MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaboration
Large Language Models (LLMs) have marked a significant advancement in the field of natural language processing, demonstrating exceptional capabilities in reasoning, tool usage, and memory.
PC$^2$-PU: Patch Correlation and Point Correlation for Effective Point Cloud Upsampling
Point cloud upsampling is to densify a sparse point set acquired from 3D sensors, providing a denser representation for the underlying surface.
Algorithm-hardware Co-design for Deformable Convolution
In this work, we first investigate the overhead of the deformable convolution on embedded FPGA SoCs, and then show the accuracy-latency tradeoffs for a set of algorithm modifications including full versus depthwise, fixed-shape, and limited-range.
CoDeNet: Efficient Deployment of Input-Adaptive Object Detection on Embedded FPGAs
Deploying deep learning models on embedded systems has been challenging due to limited computing resources.
Cross-Domain Sentiment Classification with Contrastive Learning and Mutual Information Maximization
Due to scarcity of labels on the target domain, we introduce mutual information maximization (MIM) apart from CL to exploit the features that best support the final prediction.
Cross-Domain Sentiment Classification with In-Domain Contrastive Learning
In this paper, we propose a contrastive learning framework for cross-domain sentiment classification.
Discovering Predictable Latent Factors for Time Series Forecasting
Many real-world data mining tasks, however, lack sufficient variables for relation reasoning, and therefore these methods may not properly handle such forecasting problems.
An Item is Worth a Prompt: Versatile Image Editing with Disentangled Control
Building on the success of text-to-image diffusion models (DPMs), image editing is an important application to enable human interaction with AI-generated content.
Domain-Adaptive Text Classification with Structured Knowledge from Unlabeled Data
Then during training, DASK injects pivot-related knowledge graph information into source domain texts.
Integrating View Conditions for Image Synthesis
In the field of image processing, applying intricate semantic modifications within existing images remains an enduring challenge.
Input Aggregated Network for Face Video Representation
To sufficiently discover the useful information contained in face videos, we present a novel network architecture called input aggregated network which is able to learn fixed-length representations for variable-length face videos.
Joint Point Cloud and Image Based Localization For Efficient Inspection in Mixed Reality
While external pose estimation and fiducial marker based localization would require setup, maintenance, and manual calibration; marker-free self-localization can be achieved using the onboard depth sensor and camera.
Robotics
Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT
In particular, we propose a new group-wise quantization scheme, and we use a Hessian based mix-precision method to compress the model further.
Ranked #13 on
Semantic Textual Similarity
on STS Benchmark
Data-Anonymous Encoding for Text-to-SQL Generation
On text-to-SQL generation, the input utterance usually contains lots of tokens that are related to column names or cells in the table, called \textit{table-related tokens}.
Learnable Motion Coherence for Correspondence Pruning
We propose a novel formulation of fitting coherent motions with a smooth function on a graph of correspondences and show that this formulation allows a closed-form solution by graph Laplacian.
A Survey of Quantization Methods for Efficient Neural Network Inference
Thus, it is not surprising that quantization has emerged recently as an important and very active sub-area of research in the efficient implementation of computations associated with Neural Networks.
HAO: Hardware-aware neural Architecture Optimization for Efficient Inference
Automatic algorithm-hardware co-design for DNN has shown great success in improving the performance of DNNs on FPGAs.
Hardware Aware Neural Architecture Search
Image Classification
+2
Applications and Techniques for Fast Machine Learning in Science
In this community review report, we discuss applications and techniques for fast machine learning (ML) in science -- the concept of integrating power ML methods into the real-time experimental data processing loop to accelerate scientific discovery.
KTNet: Knowledge Transfer for Unpaired 3D Shape Completion
The student network takes the incomplete one as input and restores the corresponding complete shape.
Optimization-Based Ramping Reserve Allocation of BESS for AGC Enhancement
This paper presents a novel scheme termed Optimization-based Ramping Reserve Allocation (ORRA) for addressing an ongoing challenge in Automatic Generation Control (AGC) enhancement, i. e., the optimal coordination of multiple Battery Energy Storage Systems (BESSs).
UnrealNAS: Can We Search Neural Architectures with Unreal Data?
Neural architecture search (NAS) has shown great success in the automatic design of deep neural networks (DNNs).
Semi-signed prioritized neural fitting for surface reconstruction from unoriented point clouds
To guide the network quickly fit the coarse shape, we propose to utilize the signed supervision in regions that are obviously outside the object and can be easily determined, resulting in our semi-signed supervision.
Analysis of Quantization on MLP-based Vision Models
Quantization is wildly taken as a model compression technique, which obtains efficient models by converting floating-point weights and activations in the neural network into lower-bit integers.
NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers
Building on the theoretical insight, NoisyQuant achieves the first success on actively altering the heavy-tailed activation distribution with additive noisy bias to fit a given quantizer.
CSQ: Growing Mixed-Precision Quantization Scheme with Bi-level Continuous Sparsification
CSQ stabilizes the bit-level mixed-precision training process with a bi-level gradual continuous sparsification on both the bit values of the quantized weights and the bit selection in determining the quantization precision of each layer.
Data-Driven Load-Current Sharing Control for Multi-Stack Fuel Cell System with Circulating Current Mitigation
The Multi-stack Fuel Cell System (MFCS), which is an assembly of FC stacks, can be a remedy for obstacles in high-power applications.
End-to-end codesign of Hessian-aware quantized neural networks for FPGAs and ASICs
We develop an end-to-end workflow for the training and implementation of co-designed neural networks (NNs) for efficient field-programmable gate array (FPGA) and application-specific integrated circuit (ASIC) hardware.
QD-BEV : Quantization-aware View-guided Distillation for Multi-view 3D Object Detection
Multi-view 3D detection based on BEV (bird-eye-view) has recently achieved significant improvements.
CoFiI2P: Coarse-to-Fine Correspondences for Image-to-Point Cloud Registration
Specifically, In the coarse matching phase, a novel I2P transformer module is employed to capture both homogeneous and heterogeneous global information from the image and point cloud data.
QFT: Quantized Full-parameter Tuning of LLMs with Affordable Resources
Large Language Models (LLMs) have showcased remarkable impacts across a wide spectrum of natural language processing tasks.
Research on Key Technologies of Infrastructure Digitalization based on Multimodal Spatial Data
In the process of constructing a road network with point cloud information, we summarize several major features of the point cloud collected by laser scanners and analyze the potential problems of constructing the network, such as misjudging the feature points as ground points and grid voids.
EPIM: Efficient Processing-In-Memory Accelerators based on Epitome
On the hardware side, we modify the datapath of current PIM accelerators to accommodate epitomes and implement a feature map reuse technique to reduce computation cost.
Split-Ensemble: Efficient OOD-aware Ensemble via Task and Model Splitting
In particular, we build a tree-like Split-Ensemble architecture by performing iterative splitting and pruning from a shared backbone model, where each branch serves as a submodel corresponding to a subtask.
Efficient Deweather Mixture-of-Experts with Uncertainty-aware Feature-wise Linear Modulation
In this work, we propose an efficient MoE architecture with weight sharing across the experts.
VEnvision3D: A Synthetic Perception Dataset for 3D Multi-Task Model Research
Therefore, such a unique attribute can assist in exploring the potential for the multi-task model and even the foundation model without separate training methods.
A Dataset and Benchmark for Copyright Protection from Text-to-Image Diffusion Models
Copyright is a legal right that grants creators the exclusive authority to reproduce, distribute, and profit from their creative works.
