Search Results for author:
Found 29 papers, 10 papers with code
Accelerating Large Language Models through Partially Linear Feed-Forward Network
We propose TARDIS, which enables optimization of LLMs with non-linear activations by partially approximating them with linear functions in frequently occurring input ranges.
KunServe: Elastic and Efficient Large Language Model Serving with Parameter-centric Memory Management
The stateful nature of large language model (LLM) servingcan easily throttle precious GPU memory under load burstor long-generation requests like chain-of-thought reasoning, causing latency spikes due to queuing incoming requests.
Unifying KV Cache Compression for Large Language Models with LeanKV
Large language models (LLMs) demonstrate exceptional performance but incur high serving costs due to substantial memory demands, with the key-value (KV) cache being a primary bottleneck.
Turbo Sparse: Achieving LLM SOTA Performance with Minimal Activated Parameters
By applying our neuron sparsification method to the Mistral and Mixtral models, only 2. 5 billion and 4. 3 billion parameters are activated per inference iteration, respectively, while achieving even more powerful model performance.
PowerInfer-2: Fast Large Language Model Inference on a Smartphone
The storage engine provides a fine-grained pipeline mechanism that coordinates cluster-level computation and I/O operations, enhanced by a segmented neuron cache to reduce I/O activities.
Characterizing the Dilemma of Performance and Index Size in Billion-Scale Vector Search and Breaking It with Second-Tier Memory
In this paper, we are the first to characterize the trade-off of performance and index size in existing SSD-based graph and cluster indexes: to improve throughput by 5. 7$\times$ and 1. 7$\times$, these indexes have to pay a 5. 8$\times$ storage amplification and 7. 7$\times$ with respect to the dataset size, respectively.
PNeSM: Arbitrary 3D Scene Stylization via Prompt-Based Neural Style Mapping
3D scene stylization refers to transform the appearance of a 3D scene to match a given style image, ensuring that images rendered from different viewpoints exhibit the same style as the given style image, while maintaining the 3D consistency of the stylized scene.
Attack Deterministic Conditional Image Generative Models for Diverse and Controllable Generation
Given that many deterministic conditional image generative models have been able to produce high-quality yet fixed results, we raise an intriguing question: is it possible for pre-trained deterministic conditional image generative models to generate diverse results without changing network structures or parameters?
PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPU
This paper introduces PowerInfer, a high-speed Large Language Model (LLM) inference engine on a personal computer (PC) equipped with a single consumer-grade GPU.
TSSAT: Two-Stage Statistics-Aware Transformation for Artistic Style Transfer
To address this issue, we imitate the drawing process of humans and propose a Two-Stage Statistics-Aware Transformation (TSSAT) module, which first builds the global style foundation by aligning the global statistics of content and style features and then further enriches local style details by swapping the local statistics (instead of local features) in a patch-wise manner, significantly improving the stylization effects.
An Overview of Resource Allocation in Integrated Sensing and Communication
Integrated sensing and communication (ISAC) is considered as a promising solution for improving spectrum efficiency and relieving wireless spectrum congestion.
Overview and Performance Analysis of Various Waveforms in High Mobility Scenarios
In the high-mobility scenarios of next-generation wireless communication systems (beyond 5G/6G), the performance of orthogonal frequency division multiplexing (OFDM) deteriorates drastically due to the loss of orthogonality between the subcarriers caused by large Doppler frequency shifts.
MicroAST: Towards Super-Fast Ultra-Resolution Arbitrary Style Transfer
The style encoder, coupled with a modulator, encodes the style image into learnable dual-modulation signals that modulate both intermediate features and convolutional filters of the decoder, thus injecting more sophisticated and flexible style signals to guide the stylizations.
Texture Reformer: Towards Fast and Universal Interactive Texture Transfer
In addition, we also introduce a novel learning-free view-specific texture reformation (VSTR) operation with a new semantic map guidance strategy to achieve more accurate semantic-guided and structure-preserved texture transfer.
Artistic Style Transfer with Internal-external Learning and Contrastive Learning
Although existing artistic style transfer methods have achieved significant improvement with deep neural networks, they still suffer from artifacts such as disharmonious colors and repetitive patterns.
Scalable Memory Protection in the PENGLAI Enclave
Upon these two primitives, our system can scale to thousands of concurrent enclaves with high resource utilization and eliminate the high-cost initialization of secure memory using fork-style enclave creation without weakening the security guarantees.
DualAST: Dual Style-Learning Networks for Artistic Style Transfer
Artistic style transfer is an image editing task that aims at repainting everyday photographs with learned artistic styles.
A family of simple non-weight modules over the twisted $N=2$ superconformal algebra
We construct a class of non-weight modules over the twisted $N=2$ superconformal algebra $\T$.
Representation Theory
VSync: Push-Button Verification and Optimization for Synchronization Primitives on Weak Memory Models (Technical Report)
Finally, in Sec.
Logic in Computer Science
DivSwapper: Towards Diversified Patch-based Arbitrary Style Transfer
Gram-based and patch-based approaches are two important research lines of style transfer.
Diverse Image Style Transfer via Invertible Cross-Space Mapping
Image style transfer aims to transfer the styles of artworks onto arbitrary photographs to create novel artistic images.
Characterizing serverless platforms with serverlessbench
This, however, also presents new challenges including how to efficiently design high-performance serverless platforms and how to efficiently program on the platforms.
Multimodal Image-to-Image Translation via Mutual Information Estimation and Maximization
Multimodal image-to-image translation (I2IT) aims to learn a conditional distribution that explores multiple possible images in the target domain given an input image in the source domain.
LDMGAN: Reducing Mode Collapse in GANs with Latent Distribution Matching
Generative Adversarial Networks (GANs) have shown impressive results in modeling distributions over complicated manifolds such as those of natural images.
Diversified Arbitrary Style Transfer via Deep Feature Perturbation
Image style transfer is an underdetermined problem, where a large number of solutions can satisfy the same constraint (the content and style).
Action Recognition in Untrimmed Videos with Composite Self-Attention Two-Stream Framework
This model can implement action recognition under zero-shot conditions, and has good recognition performance for untrimmed video data.
A Novel Task-Oriented Text Corpus in Silent Speech Recognition and its Natural Language Generation Construction Method
In the process of construction, we propose a task-oriented hybrid construction method based on natural language generation algorithm.
Learned Indexes for Dynamic Workloads
In this paper, we demonstrate that the missing consideration of access patterns and dynamic data distribution notably hinders the applicability of learned indexes.
Deep Learning At Scale and At Ease
The other is scalability, that is the deep learning system must be able to provision for a huge demand of computing resources for training large models with massive datasets.
