Search Results for author:
Found 36 papers, 15 papers with code
A Survey on Efficient Inference for Large Language Models
This paper presents a comprehensive survey of the existing literature on efficient LLM inference.
Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better
For example, LCSC achieves better performance using 1 number of function evaluation (NFE) than the base model with 2 NFE on consistency distillation, and decreases the NFE of DM from 15 to 9 while maintaining the generation quality on CIFAR-10.
FlashEval: Towards Fast and Accurate Evaluation of Text-to-image Diffusion Generative Models
In recent years, there has been significant progress in the development of text-to-image generative models.
Evaluating Quantized Large Language Models
Post-training quantization (PTQ) has emerged as a promising technique to reduce the cost of large language models (LLMs).
LV-Eval: A Balanced Long-Context Benchmark with 5 Length Levels Up to 256K
In contrast, the average context lengths of mainstream benchmarks are insufficient (5k-21k), and they suffer from potential knowledge leakage and inaccurate metrics, resulting in biased evaluation.
FlightLLM: Efficient Large Language Model Inference with a Complete Mapping Flow on FPGAs
However, existing GPU and transformer-based accelerators cannot efficiently process compressed LLMs, due to the following unresolved challenges: low computational efficiency, underutilized memory bandwidth, and large compilation overheads.
A Unified Sampling Framework for Solver Searching of Diffusion Probabilistic Models
In this paper, we propose a unified sampling framework (USF) to study the optional strategies for solver.
THInImg: Cross-modal Steganography for Presenting Talking Heads in Images
Cross-modal Steganography is the practice of concealing secret signals in publicly available cover signals (distinct from the modality of the secret signals) unobtrusively.
Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation
This work aims at decreasing the end-to-end generation latency of large language models (LLMs).
Ada3D : Exploiting the Spatial Redundancy with Adaptive Inference for Efficient 3D Object Detection
One reason for this high resource consumption is the presence of a large number of redundant background points in Lidar point clouds, resulting in spatial redundancy in both 3D voxel and dense BEV map representations.
OMS-DPM: Optimizing the Model Schedule for Diffusion Probabilistic Models
Diffusion probabilistic models (DPMs) are a new class of generative models that have achieved state-of-the-art generation quality in various domains.
Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels
To address this, we introduce Jaccard Metric Losses (JMLs), which are identical to the soft Jaccard loss in standard settings with hard labels but are fully compatible with soft labels.
Dynamic Ensemble of Low-fidelity Experts: Mitigating NAS "Cold-Start"
In the first step, we train different sub-predictors on different types of available low-fidelity information to extract beneficial knowledge as low-fidelity experts.
CLOSE: Curriculum Learning On the Sharing Extent Towards Better One-shot NAS
Specifically, we train the supernet with a large sharing extent (an easier curriculum) at the beginning and gradually decrease the sharing extent of the supernet (a harder curriculum).
Fault-Tolerant Deep Learning: A Hierarchical Perspective
With the rapid advancements of deep learning in the past decade, it can be foreseen that deep learning will be continuously deployed in more and more safety-critical applications such as autonomous driving and robotics.
CodedVTR: Codebook-based Sparse Voxel Transformer with Geometric Guidance
We propose CodedVTR (Codebook-based Voxel TRansformer), which improves data efficiency and generalization ability for 3D sparse voxel transformers.
Multi-Agent Vulnerability Discovery for Autonomous Driving with Hazard Arbitration Reward
These scenarios indeed correspond to the vulnerabilities of the under-test driving policies, thus are meaningful for their further improvements.
BoolNet: Streamlining Binary Neural Networks Using Binary Feature Maps
Recent works on Binary Neural Networks (BNNs) have made promising progress in narrowing the accuracy gap of BNNs to their 32-bit counterparts, often based on specialized model designs using additional 32-bit components.
BoolNet: Minimizing The Energy Consumption of Binary Neural Networks
Recent works on Binary Neural Networks (BNNs) have made promising progress in narrowing the accuracy gap of BNNs to their 32-bit counterparts.
Ensemble-in-One: Learning Ensemble within Random Gated Networks for Enhanced Adversarial Robustness
It provides high scalability because the paths within an EIO network exponentially increase with the network depth.
FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learning
In this work, we propose FedCor -- an FL framework built on a correlation-based client selection strategy, to boost the convergence rate of FL.
Machine Learning for Electronic Design Automation: A Survey
With the down-scaling of CMOS technology, the design complexity of very large-scale integrated (VLSI) is increasing.
Explore the Potential of CNN Low Bit Training
Through this dynamic precision framework, we can reduce the bit-width of convolution, which is the most computational cost, while keeping the training process close to the full precision floating-point training.
Discovering Robust Convolutional Architecture at Targeted Capacity: A Multi-Shot Approach
In this paper, considering scenarios with capacity budget, we aim to discover adversarially robust architecture at targeted capacities.
aw_nas: A Modularized and Extensible NAS framework
Neural Architecture Search (NAS) has received extensive attention due to its capability to discover neural network architectures in an automated manner.
BARS: Joint Search of Cell Topology and Layout for Accurate and Efficient Binary ARchitectures
We also design the micro-level search space to strengthen the information flow for BNN.
A Surgery of the Neural Architecture Evaluators
A major challenge in NAS is to conduct a fast and accurate evaluation of neural architectures.
Evaluating Efficient Performance Estimators of Neural Architectures
Conducting efficient performance estimations of neural architectures is a major challenge in neural architecture search (NAS).
Physical Adversarial Attack on Vehicle Detector in the Carla Simulator
In this paper, we tackle the issue of physical adversarial examples for object detectors in the wild.
Exploring the Potential of Low-bit Training of Convolutional Neural Networks
For training a variety of models on CIFAR-10, using 1-bit mantissa and 2-bit exponent is adequate to keep the accuracy loss within $1\%$.
DSA: More Efficient Budgeted Pruning via Differentiable Sparsity Allocation
In budgeted pruning, how to distribute the resources across layers (i. e., sparsity allocation) is the key problem.
A Generic Graph-based Neural Architecture Encoding Scheme for Predictor-based NAS
Experimental results on various search spaces confirm GATES's effectiveness in improving the performance predictor.
FTT-NAS: Discovering Fault-Tolerant Convolutional Neural Architecture
By inspecting the discovered architectures, we find that the operation primitives, the weight quantization range, the capacity of the model, and the connection pattern have influences on the fault resilience capability of NN models.
Nonparametric Topic Modeling with Neural Inference
Moreover, we also propose HiTM-VAE, where the document-specific topic distributions are generated in a hierarchical manner.
Hu-Fu: Hardware and Software Collaborative Attack Framework against Neural Networks
So, in this paper, we propose a hardware-software collaborative attack framework to inject hidden neural network Trojans, which works as a back-door without requiring manipulating input images and is flexible for different scenarios.
A Bayesian Nonparametric Topic Model with Variational Auto-Encoders
On the other hand, different with the other BNP topic models, the inference of iTM-VAE is modeled by neural networks, which has rich representation capacity and can be computed in a simple feed-forward manner.
