Search Results for author:
Found 53 papers, 14 papers with code
Efficient Unified Caching for Accelerating Heterogeneous AI Workloads
Modern AI clusters, which host diverse workloads like data pre-processing, training and inference, often store the large-volume data in cloud storage and employ caching frameworks to facilitate remote data access.
Advancing LLM Safe Alignment with Safety Representation Ranking
The rapid advancement of large language models (LLMs) has demonstrated milestone success in a variety of tasks, yet their potential for generating harmful content has raised significant safety concerns.
VGNC: Reducing the Overfitting of Sparse-view 3DGS via Validation-guided Gaussian Number Control
Recently, many methods based on the 3D Gaussian Splatting (3DGS) framework have been proposed to address sparse-view 3D reconstruction.
Improving the Serving Performance of Multi-LoRA Large Language Models via Efficient LoRA and KV Cache Management
FASTLIBRA comprises a dependency-aware cache manager and a performance-driven cache swapper.
A Language Vision Model Approach for Automated Tumor Contouring in Radiation Oncology
Conclusions: OCC represents a significant advance in oncology care, particularly through the use of the latest LVMs to improve contouring results by (1) streamlining oncology treatment workflows by optimizing tumor delineation, reducing manual processes; (2) offering a scalable and intuitive framework to reduce false positives in radiotherapy planning using LVMs; (3) introducing novel medical language vision prompt techniques to minimize LVMs hallucinations with ablation study, and (4) conducting a comparative analysis of LVMs, highlighting their potential in addressing medical language vision challenges.
Comet: Fine-grained Computation-communication Overlapping for Mixture-of-Experts
The inter-device communication of a MoE layer can occupy 47% time of the entire model execution with popular models and frameworks.
From Principles to Applications: A Comprehensive Survey of Discrete Tokenizers in Generation, Comprehension, Recommendation, and Information Retrieval
Discrete tokenizers have emerged as indispensable components in modern machine learning systems, particularly within the context of autoregressive modeling and large language models (LLMs).
Relative Distance Guided Dynamic Partition Learning for Scale-Invariant UAV-View Geo-Localization
Specifically, we propose a distance guided dynamic partition learning strategy~(DGDPL), consisting of a square partition strategy and a distance-guided adjustment strategy.
Text-Video Multi-Grained Integration for Video Moment Montage
The proliferation of online short video platforms has driven a surge in user demand for short video editing.
SweetTokenizer: Semantic-Aware Spatial-Temporal Tokenizer for Compact Visual Discretization
SweetTokenizer achieves comparable video reconstruction fidelity with only \textbf{25\%} of the tokens used in previous state-of-the-art video tokenizers, and boost video generation results by \textbf{32. 9\%} w. r. t gFVD.
Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads
We introduce Orthus, an autoregressive (AR) transformer that excels in generating images given textual prompts, answering questions based on visual inputs, and even crafting lengthy image-text interleaved contents.
Enhancing Instruction-Following Capability of Visual-Language Models by Reducing Image Redundancy
In this paper, we propose Visual-Modality Token Compression (VMTC) and Cross-Modality Attention Inhibition (CMAI) strategies to alleviate this gap between MLLMs and LLMs by inhibiting the influence of irrelevant visual tokens during content generation, increasing the instruction-following ability of the MLLMs while retaining their multimodal understanding capacity.
LiTformer: Efficient Modeling and Analysis of High-Speed Link Transmitters Using Non-Autoregressive Transformer
High-speed serial links are fundamental to energy-efficient and high-performance computing systems such as artificial intelligence, 5G mobile and automotive, enabling low-latency and high-bandwidth communication.
A QoE-Aware Split Inference Accelerating Algorithm for NOMA-based Edge Intelligence
Thus, the model split inference is proposed to improve the performance of edge intelligence, in which the AI model is divided into different sub models and the resource-intensive sub model is offloaded to edge server wirelessly for reducing resource requirements and inference latency.
Whole Heart Perfusion with High-Multiband Simultaneous Multislice Imaging via Linear Phase Modulated Extended Field of View (SMILE)
(5-point Likert Scale) Conclusion: The theoretical derivation and experimental results validate the SMILE's improved performance at high acceleration and MB as compared to the existing 2D CAIPI SMS acquisition and reconstruction techniques for first-pass myocardial perfusion imaging.
D&M: Enriching E-commerce Videos with Sound Effects by Key Moment Detection and SFX Matching
Previous studies about adding SFX to videos perform video to SFX matching at a holistic level, lacking the ability of adding SFX to a specific moment.
ASR-enhanced Multimodal Representation Learning for Cross-Domain Product Retrieval
While Automatic Speech Recognition (ASR) text derived from the short or live-stream videos is readily accessible, how to de-noise the excessively noisy text for multimodal representation learning is mostly untouched.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Spatiotemporal Graph Guided Multi-modal Network for Livestreaming Product Retrieval
The LPR task encompasses three primary dilemmas in real-world scenarios: 1) the recognition of intended products from distractor products present in the background; 2) the video-image heterogeneity that the appearance of products showcased in live streams often deviates substantially from standardized product images in stores; 3) there are numerous confusing products with subtle visual nuances in the shop.
Training-free Subject-Enhanced Attention Guidance for Compositional Text-to-image Generation
Furthermore, we propose a novel metric GroundingScore to evaluate subject alignment thoroughly.
LEARN: Knowledge Adaptation from Large Language Model to Recommendation for Practical Industrial Application
Contemporary recommendation systems predominantly rely on ID embedding to capture latent associations among users and items.
A Codesign of Scheduling and Parallelization for Large Model Training in Heterogeneous Clusters
The exponentially enlarged scheduling space and ever-changing optimal parallelism plan from adaptive parallelism together result in the contradiction between low-overhead and accurate performance data acquisition for efficient cluster scheduling.
Hierarchical Frequency-based Upsampling and Refining for Compressed Video Quality Enhancement
The goal of video quality enhancement is to reduce compression artifacts and reconstruct a visually-pleasant result.
Knowledge Condensation and Reasoning for Knowledge-based VQA
We condense the retrieved knowledge passages from two perspectives.
SDPL: Shifting-Dense Partition Learning for UAV-View Geo-Localization
We propose a dense partition strategy (DPS), dividing the image into multiple parts to explore contextual information while explicitly maintaining the global structure.
EXACT-Net:EHR-guided lung tumor auto-segmentation for non-small cell lung cancer radiotherapy
Lung cancer is a devastating disease with the highest mortality rate among cancer types.
Towards Efficient and Effective Text-to-Video Retrieval with Coarse-to-Fine Visual Representation Learning
To address this issue, we adopt multi-granularity visual feature learning, ensuring the model's comprehensiveness in capturing visual content features spanning from abstract to detailed levels during the training phase.
Ranked #7 on
Video Retrieval
on MSR-VTT-1kA
Mobility and Cost Aware Inference Accelerating Algorithm for Edge Intelligence
The model segmentation without user mobility has been investigated deeply by previous works.
STAG: Enabling Low Latency and Low Staleness of GNN-based Services with Dynamic Graphs
With the collaborative serving mechanism, only part of node representations are updated during the update phase, and the final representations are calculated in the inference phase.
Cross-Domain Product Representation Learning for Rich-Content E-Commerce
It is the first dataset to cover product pages, short videos, and live streams simultaneously, providing the basis for establishing a unified product representation across different media domains.
Cross-view Semantic Alignment for Livestreaming Product Recognition
Moreover, a cRoss-vIew semantiC alignmEnt (RICE) model is proposed to learn discriminative instance features from the image and video views of the products.
Non-line-of-sight reconstruction via structure sparsity regularization
Subsequently, the reconstruction is achieved by optimizing a directional albedo model with SS regularization using fast iterative shrinkage-thresholding algorithm.
MARS: Exploiting Multi-Level Parallelism for DNN Workloads on Adaptive Multi-Accelerator Systems
Along with the fast evolution of deep neural networks, the hardware system is also developing rapidly.
AdaptGear: Accelerating GNN Training via Adaptive Subgraph-Level Kernels on GPUs
Graph neural networks (GNNs) are powerful tools for exploring and learning from graph structures and features.
DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization
Image color harmonization algorithm aims to automatically match the color distribution of foreground and background images captured in different conditions.
Ranked #9 on
Image Harmonization
on iHarmony4
SALO: An Efficient Spatial Accelerator Enabling Hybrid Sparse Attention Mechanisms for Long Sequences
However, the quadratic complexity of self-attention w. r. t the sequence length incurs heavy computational and memory burdens, especially for tasks with long sequences.
Multilayer Perceptron Based Stress Evolution Analysis under DC Current Stressing for Multi-segment Wires
Electromigration (EM) is one of the major concerns in the reliability analysis of very large scale integration (VLSI) systems due to the continuous technology scaling.
A Space-Time Neural Network for Analysis of Stress Evolution under DC Current Stressing
The electromigration (EM)-induced reliability issues in very large scale integration (VLSI) circuits have attracted increased attention due to the continuous technology scaling.
Boosting Image Outpainting with Semantic Layout Prediction
Secondly, another GAN model is trained to synthesize real images based on the extended semantic layouts.
Dubhe: Towards Data Unbiasedness with Homomorphic Encryption in Federated Learning Client Selection
Federated learning (FL) is a distributed machine learning paradigm that allows clients to collaboratively train a model over their own local data.
FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware Transformation
Prior arts often discretize the network weights by carefully tuning hyper-parameters of quantization (e. g. non-uniform stepsize and layer-wise bitwidths), which are complicated and sub-optimal because the full-precision and low-precision models have a large discrepancy.
Federated Learning on Non-IID Data Silos: An Experimental Study
We find that non-IID does bring significant challenges in learning accuracy of FL algorithms, and none of the existing state-of-the-art FL algorithms outperforms others in all cases.
Edge Computing Assisted Autonomous Flight for UAV: Synergies between Vision and Communications
By proposing a framework of Edge Computing Assisted Autonomous Flight (ECAAF), we illustrate that vision and communications can interact with and assist each other with the aid of edge computing and offloading, and further speed up the UAV mission completion.
Edge-computing
Trajectory Planning
Networking and Internet Architecture
Robotics
Systems and Control
Systems and Control
How Far Does BERT Look At: Distance-based Clustering and Analysis of BERT's Attention
Recent research on the multi-head attention mechanism, especially that in pre-trained models such as BERT, has shown us heuristics and clues in analyzing various aspects of the mechanism.
How Far Does BERT Look At:Distance-based Clustering and Analysis of BERT$'$s Attention
Recent research on the multi-head attention mechanism, especially that in pre-trained models such as BERT, has shown us heuristics and clues in analyzing various aspects of the mechanism.
Balancing Efficiency and Flexibility for DNN Acceleration via Temporal GPU-Systolic Array Integration
We propose Simultaneous Multi-mode Architecture (SMA), a novel architecture design and execution model that offers general-purpose programmability on DNN accelerators in order to accelerate end-to-end applications.
Progressive Feature Polishing Network for Salient Object Detection
Feature matters for salient object detection.
Adversarial Defense Through Network Profiling Based Path Extraction
Recently, researchers have started decomposing deep neural network models according to their semantics or functions.
Prostate Segmentation from 3D MRI Using a Two-Stage Model and Variable-Input Based Uncertainty Measure
Using PROMISE-12 data, we demonstrated the robustness of the two-stage model and showed high correlation of the proposed variable-input based uncertainty measures with GT-based performance.
Effective Path: Know the Unknowns of Neural Network
Despite their enormous success, there is still no solid understanding of deep neural network’s working mechanism.
Semantic Human Matting
SHM is the first algorithm that learns to jointly fit both semantic information and high quality details with deep networks.
Ranked #5 on
Image Matting
on AIM-500
DLFuzz: Differential Fuzzing Testing of Deep Learning Systems
Deep learning (DL) systems are increasingly applied to safety-critical domains such as autonomous driving cars.
Software Engineering
Deep joint rain and haze removal from single images
On the other hand, the accumulation of rain streaks from long distance makes the rain image look like haze veil.
MSR-net:Low-light Image Enhancement Using Deep Convolutional Network
In this paper, a low-light image enhancement model based on convolutional neural network and Retinex theory is proposed.
