Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Hao Zhong

Hao Zhong

3 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

3
26

Top categories

Vision×2Distributed×1ML×1

Frequent co-authors

Bin Lin2×
Yunlong Lin2×
Miles Yang2×
Zhao Zhong2×
Liefeng Bo2×
Zhihao Xu1×

Research Timeline

2026
GEAR: Guided End-to-End AutoRegression for Image Synthesis

This paper introduces GEAR, a method for training a vector-quantized tokenizer and an autoregressive generator jointly and end-to-end, resolving the issue of non-differentiable VQ indices.

Twins: Learn to Predict Unified Representations with Focal Loss

This paper proposes Twins, a unified continuous token space for multimodal models using ViT and VAE features, and addresses optimization imbalance with a focal regression objective.

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs

This paper proposes Gleam, a framework for efficient GPU sharing across local-area CUDA devices, reducing bandwidth overhead, improving API call latency, and ensuring context consistency.

Highlighted terms show continued research focus across papers

Papers

cs.DCcs.LGEmpiricalRecentJul 25, 2026

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs

Zhihao Xu, Hao Zhong, Zeting Zhou, Yuhang Xu +8 more

This paper proposes Gleam, a framework for efficient GPU sharing across local-area CUDA devices, reducing bandwidth overhead, improving API call latency, and ensuring context consistency.

View →
cs.CVEmpirical
Recent
Jul 24, 2026

Twins: Learn to Predict Unified Representations with Focal Loss

Kaixiong Gong, Xin Cai, Bin Lin, Hao Wang +8 more

This paper proposes Twins, a unified continuous token space for multimodal models using ViT and VAE features, and addresses optimization imbalance with a focal regression objective.

View →
cs.CVEmpiricalRecentJun 30, 2026

GEAR: Guided End-to-End AutoRegression for Image Synthesis

Bin Lin, Zheyuan Liu, Chenguo Lin, Sixiang Chen +7 more

This paper introduces GEAR, a method for training a vector-quantized tokenizer and an autoregressive generator jointly and end-to-end, resolving the issue of non-differentiable VQ indices.

View →