Xingcheng Zhang

Orcid: 0009-0006-8525-0608

According to our database1, Xingcheng Zhang authored at least 47 papers between 2017 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Di-PS: System-Algorithm Co-Design for Asynchronous and Heterogeneous Cross-cluster LLM Training at Scale.
Proceedings of the 23rd USENIX Symposium on Networked Systems Design and Implementation, 2026

2025
RL in the Wild: Characterizing RLVR Training in LLM Deployment.
CoRR, September, 2025

Koala: Efficient Pipeline Training through Automated Schedule Searching on Domain-Specific Language.
ACM Trans. Archit. Code Optim., June, 2025

H2:Towards Efficient Large-Scale LLM Training on Hyper-Heterogeneous Cluster over 1,000 Chips.
CoRR, May, 2025

InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models.
CoRR, April, 2025

GS-Cache: A GS-Cache Inference Framework for Large-scale Gaussian Splatting Models.
CoRR, February, 2025

Towards Efficient Pre-training: Exploring FP4 Precision in Large Language Models.
CoRR, February, 2025

Research on the influence of installation error of capacitive angle sensor on angle error.
IEICE Electron. Express, 2025

TC-GS: A Faster Gaussian Splatting Module Utilizing Tensor Cores.
Proceedings of the SIGGRAPH Asia 2025 Conference Papers, 2025

MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

Tropical: Enhancing SLO Attainment in Disaggregated LLM Serving via SLO-Aware Multiplexing.
Proceedings of the 62nd ACM/IEEE Design Automation Conference, 2025

A Cross-model Fusion-aware Framework for Optimizing (gather-matmul-scatter)s Workload.
Proceedings of the 62nd ACM/IEEE Design Automation Conference, 2025

FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution Rendering.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

2024
DELTA: Memory-Efficient Training via Dynamic Fine-Grained Recomputation and Swapping.
ACM Trans. Archit. Code Optim., December, 2024

Proteus: Simulating the Performance of Distributed DNN Training.
IEEE Trans. Parallel Distributed Syst., October, 2024

PSE-Net: Channel pruning for Convolutional Neural Networks with parallel-subnets estimator.
Neural Networks, 2024

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions.
CoRR, 2024

Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling.
CoRR, 2024

Fisheye-GS: Lightweight and Extensible Gaussian Splatting Module for Fisheye Cameras.
CoRR, 2024

FlashGS: Efficient 3D Gaussian Splatting for Large-scale and High-resolution Rendering.
CoRR, 2024

Efficient Training of Large Language Models on Distributed Infrastructures: A Survey.
CoRR, 2024

OriGen:Enhancing RTL Code Generation with Code-to-Code Augmentation and Self-Reflection.
CoRR, 2024

InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output.
CoRR, 2024

Achieving Energetic Superiority Through System-Level Quantum Circuit Simulation.
CoRR, 2024

SampleAttention: Near-Lossless Acceleration of Long Context LLM Inference with Adaptive Structured Sparse Attention.
CoRR, 2024

SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models.
CoRR, 2024

MuxServe: Flexible Multiplexing for Efficient Multiple LLM Serving.
CoRR, 2024

Adaptive Blockwise Task-interleaved Pipeline Parallelism.
CoRR, 2024

InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model.
CoRR, 2024

Surpassing Sycamore: Achieving Energetic Superiority Through System-Level Circuit Simulation.
Proceedings of the International Conference for High Performance Computing, 2024

InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD.
Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

MuxServe: Flexible Spatial-Temporal Multiplexing for Multiple LLM Serving.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

OriGen: Enhancing RTL Code Generation with Code-to-Code Augmentation and Self-Reflection.
Proceedings of the 43rd IEEE/ACM International Conference on Computer-Aided Design, 2024

PackMamba: Efficient Processing of Variable-Length Sequences in Mamba Training.
Proceedings of the Computer Vision - ECCV 2024 Workshops, 2024

A Holistic Functionalization Approach to Optimizing Imperative Tensor Programs in Deep Learning.
Proceedings of the 61st ACM/IEEE Design Automation Conference, 2024

Centauri: Enabling Efficient Scheduling for Communication-Computation Overlap in Large Model Training via Communication Partitioning.
Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, 2024

2023
InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition.
CoRR, 2023

Poly-PC: A Polyhedral Network for Multiple Point Cloud Tasks at Once.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

MDL-NAS: A Joint Multi-domain Learning Framework for Vision Transformer.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
DELTA: Dynamically Optimizing GPU Memory beyond Tensor Recomputation.
CoRR, 2022

LongTail-Bench: A Benchmark Suite for Domain-Specific Operators in Deep Learning.
Proceedings of the IEEE International Symposium on Workload Characterization, 2022

EasyView: Enabling and Scheduling Tensor Views in Deep Learning Compilers.
Proceedings of the 51st International Conference on Parallel Processing, 2022

2021
An Ultralow-Ripple Polarization Voltage Generator based on High-Voltage Bandgap Reference for MEMS Gyroscopes.
Proceedings of the 16th IEEE International Conference on Nano/Micro Engineered and Molecular Systems, 2021

2020
Elan: Towards Generic and Efficient Elastic Training for Deep Learning.
Proceedings of the 40th IEEE International Conference on Distributed Computing Systems, 2020

2018
Optimizing Video Object Detection via a Scale-Time Lattice.
Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

Accelerated Training for Massive Classification via Dynamic Class Selection.
Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018

2017
PolyNet: A Pursuit of Structural Diversity in Very Deep Networks.
Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017


  Loading...