Search Results for author:
Found 49 papers, 20 papers with code
Prism: Mining Task-aware Domains in Non-i.i.d. IMU Data for Flexible User Perception
To achieve uncontrolled online prediction on mobile devices, referred to as the flexible user perception (FUP) problem, is attractive but hard.
A Survey on Inference Optimization Techniques for Mixture of Experts Models
This comprehensive survey systematically analyzes the current landscape of inference optimization techniques for MoE models across the entire system stack.
ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression
To achieve efficient and accurate recallable KV cache compression, we introduce ClusterKV, which recalls tokens at the granularity of semantic clusters.
Nimbus: Secure and Efficient Two-Party Inference for Transformers
For the linear layer, we propose a new 2PC paradigm along with an encoding approach to securely compute matrix multiplications based on an outer-product insight, which achieves $2. 9\times \sim 12. 5\times$ performance improvements compared to the state-of-the-art (SOTA) protocol.
HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference
We present HOBBIT, a mixed precision expert offloading system to enable flexible and efficient MoE inference.
SparseTem: Boosting the Efficiency of CNN-Based Video Encoders by Exploiting Temporal Continuity
To address these issues, we propose a memory-efficient scheduling method to eliminate memory overhead and an online adjustment mechanism to minimize accuracy degradation.
Inf-MLLM: Efficient Streaming Inference of Multimodal Large Language Models on a Single GPU
In this paper, we introduce Inf-MLLM, an efficient inference framework for MLLMs, which enable streaming inference of MLLM on a single GPU with infinite context.
vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving
This study introduces the vTensor, an innovative tensor structure for LLM inference based on GPU virtual memory management (VMM).
AutoVCoder: A Systematic Framework for Automated Verilog Code Generation using LLMs
Recently, the use of large language models (LLMs) for software code generation, e. g., C/C++ and Python, has proven a great success.
SimGen: Simulator-conditioned Driving Scene Generation
In this work, we introduce a simulator-conditioned scene generation framework called SimGen that can learn to generate diverse driving scenes by mixing data from the simulator and the real world.
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.
Embodied Understanding of Driving Scenarios
Hereby, we introduce the Embodied Language Model (ELM), a comprehensive framework tailored for agents' understanding of driving scenes with large spatial and temporal spans.
Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension
Registration of point clouds collected from a pair of distant vehicles provides a comprehensive and accurate 3D view of the driving scenario, which is vital for driving safety related applications, yet existing literature suffers from the expensive pose label acquisition and the deficiency to generalize to new data distributions.
Hierarchical Source-to-Post-Route QoR Prediction in High-Level Synthesis with GNNs
High-level synthesis (HLS) notably speeds up the hardware design process by avoiding RTL programming.
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.
Accelerating Generic Graph Neural Networks via Architecture, Compiler, Partition Method Co-Design
However, designing GNN accelerators faces two fundamental challenges: the high bandwidth requirement of GNN models and the diversity of GNN models.
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.
Density-invariant Features for Distant Point Cloud Registration
Registration of distant outdoor LiDAR point clouds is crucial to extending the 3D vision of collaborative autonomous vehicles, and yet is challenging due to small overlapping area and a huge disparity between observed point densities.
Ranked #1 on
Point Cloud Registration
on nuScenes (Distant PCR)
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.
APR: Online Distant Point Cloud Registration Through Aggregated Point Cloud Reconstruction
Such features are then used for online distant point cloud registration.
Ranked #3 on
Point Cloud Registration
on nuScenes (Distant PCR)
MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformer
Mobile monocular 3D object detection (Mono3D) (e. g., on a vehicle, a drone, or a robot) is an important yet challenging task.
MoGDE: Boosting Mobile Monocular 3D Object Detection with Ground Depth Estimation
To this end, we utilize a pose detection network to estimate the pose of the camera and then construct a feature map portraying pixel-level ground depth according to the 3D-to-2D perspective geometry.
Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training
An activation function is an element-wise mathematical function and plays a crucial role in deep neural networks (DNN).
ANT: Exploiting Adaptive Numerical Data Type for Low-bit Deep Neural Network Quantization
In this work, we propose a fixed-length adaptive numerical data type called ANT to achieve low-bit quantization with tiny hardware overheads.
Efficient Adaptive Activation Rounding for Post-Training Quantization
To deal with the runtime overhead, we use a coarse-grained version of the border function.
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.
Transkimmer: Transformer Learns to Layer-wise Skim
To address the above limitations, we propose the Transkimmer architecture, which learns to identify hidden state tokens that are not required by each layer.
SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation
This paper proposes an on-the-fly DFQ framework with sub-second quantization time, called SQuant, which can quantize networks on inference-only devices with low computation and memory requirements.
Block-Skim: Efficient Question Answering for Transformer
We further prune the hidden states corresponding to the unnecessary positions early in lower layers, achieving significant inference-time speedup.
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.
TempNet: Online Semantic Segmentation on Large-Scale Point Cloud Series
In this paper, we propose a light-weight semantic segmentation framework for large-scale point cloud series, called TempNet, which can improve both the accuracy and the stability of existing semantic segmentation models by combining a novel frame aggregation scheme.
Block Skim Transformer for Efficient Question Answering
Following this idea, we proposed Block Skim Transformer (BST) to improve and accelerate the processing of transformer QA models.
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.
Architectural Implications of Graph Neural Networks
Graph neural networks (GNN) represent an emerging line of deep learning models that operate on graph structures.
Accelerating Sparse DNN Models without Hardware-Support via Tile-Wise Sparsity
Network pruning can reduce the high computation cost of deep neural network (DNN) models.
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.
Adversarial Defense Through Network Profiling Based Path Extraction
Recently, researchers have started decomposing deep neural network models according to their semantics or functions.
Position-Aware Convolutional Networks for Traffic Prediction
Our approach employs the inception backbone network to capture rich features of traffic distribution on the whole area.
Knowledge Graph Convolutional Networks for Recommender Systems
To alleviate sparsity and cold start problem of collaborative filtering based recommender systems, researchers and engineers usually collect attributes of users and items, and design delicate algorithms to exploit these additional information.
Ranked #1 on
Click-Through Rate Prediction
on Book-Crossing
Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation
Collaborative filtering often suffers from sparsity and cold start problems in real recommendation scenarios, therefore, researchers and engineers usually use side information to address the issues and improve the performance of recommender systems.
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.
RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems
To address the sparsity and cold start problem of collaborative filtering, researchers usually make use of side information, such as social networks or item attributes, to improve recommendation performance.
Ranked #2 on
Click-Through Rate Prediction
on Book-Crossing
Personalized Exposure Control Using Adaptive Metering and Reinforcement Learning
We propose a reinforcement learning approach for real-time exposure control of a mobile camera that is personalizable.
DKN: Deep Knowledge-Aware Network for News Recommendation
To solve the above problems, in this paper, we propose a deep knowledge-aware network (DKN) that incorporates knowledge graph representation into news recommendation.
Ranked #5 on
News Recommendation
on MIND
SHINE: Signed Heterogeneous Information Network Embedding for Sentiment Link Prediction
First, due to the lack of explicit sentiment links in mainstream social networks, we establish a labeled heterogeneous sentiment dataset which consists of users' sentiment relation, social relation and profile knowledge by entity-level sentiment extraction method.
Joint Topic-Semantic-aware Social Recommendation for Online Voting
JTS-MF model calculates similarity among users and votings by combining their TEWE representation and structural information of social networks, and preserves this topic-semantic-social similarity during matrix factorization.
GraphGAN: Graph Representation Learning with Generative Adversarial Nets
The goal of graph representation learning is to embed each vertex in a graph into a low-dimensional vector space.
Ranked #1 on
Node Classification
on Wikipedia
Unsupervised Extraction of Video Highlights Via Robust Recurrent Auto-encoders
With the growing popularity of short-form video sharing platforms such as \em{Instagram} and \em{Vine}, there has been an increasing need for techniques that automatically extract highlights from video.
