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

Yifan Zhao

3 indexed papers

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

Publications per year

3
26

Top categories

ML×2NLP×1Vision×1AI×1

Frequent co-authors

Yuchen Yang1×
Anisha Dasgupta1×
Sasa Misailovic1×
Xinkai Ma1×
Zhiqi Bai1×
Dingling Zhang1×

Research Timeline

2026
Envisioning Beyond the Few: Disentangled Semantics and Primitives for Few-Shot Atypical Layout-to-Image Generation

The paper proposes a disentangled representation framework to significantly improve few-shot layout-to-image generation by separating semantic identity from local visual details, thereby mitigating representation fragmentation.

TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation

The paper introduces TVIR, a new benchmark and multi-agent framework for deep research, to evaluate and improve the generation of factually reliable, text-visual interleaved reports.

PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization

The paper proposes PagedWeight, a method for managing Mixture-of-Experts (MoE) language model serving in KV-cache-intensive scenarios, achieving FP16-equivalent accuracy with up to 72.0% GPU memory savings and 1.94$ imes$ throughput improvement.

Highlighted terms show continued research focus across papers

Papers

cs.LGEmpiricalRecentJul 17, 2026

PagedWeight: Efficient MoE LLM Serving with Dynamic Quality-Aware Weight Quantization

Yuchen Yang, Yifan Zhao, Anisha Dasgupta, Sasa Misailovic

The paper proposes PagedWeight, a method for managing Mixture-of-Experts (MoE) language model serving in KV-cache-intensive scenarios, achieving FP16-equivalent accuracy with up to 72.0% GPU memory sa…

View →
cs.CLRecentJun 1, 2026

TVIR: Building Deep Research Agents Towards Text--Visual Interleaved Report Generation

Xinkai Ma, Zhiqi Bai, Dingling Zhang, Pei Liu +20 more

The paper introduces TVIR, a new benchmark and multi-agent framework for deep research, to evaluate and improve the generation of factually reliable, text-visual interleaved reports.

View →
cs.CVcs.AIcs.LGRecentMay 29, 2026

Envisioning Beyond the Few: Disentangled Semantics and Primitives for Few-Shot Atypical Layout-to-Image Generation

Nan Bao, Yifan Zhao, Wenzhuang Wang, Jia Li

The paper proposes a disentangled representation framework to significantly improve few-shot layout-to-image generation by separating semantic identity from local visual details, thereby mitigating re…

View →