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

Yang Bo

5 indexed papers

Recent (6 mo)
5
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

Vision×3AI×3

Frequent co-authors

Peiwen Sun2×
Xudong Lu2×
Huadai Liu2×
Dongming Wu2×
Huankang Guan2×
Minghong Cai2×

Research Timeline

2026
CIVIC: End-to-End Sequence Compactness for Efficient Vision-Language Models

CIVIC is a path-consistent compact visual inference framework that achieves genuine hardware efficiency in Vision-Language Models by maintaining contiguous sequence representations across all inference stages, significantly reducing memory and latency.

CIVIC: End-to-End Sequence Compactness for Efficient Vision-Language Models

CIVIC is a path-consistent compact visual inference framework that achieves genuine hardware efficiency in Vision-Language Models by maintaining contiguous sequence representations across all inference stages, significantly reducing memory and latency.

X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding

The paper introduces X-Stream, a new benchmark for multi-stream video understanding, and finds that current state-of-the-art MLLMs perform poorly when required to process multiple concurrent video streams.

X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding

The paper introduces X-Stream, a new benchmark for multi-stream video understanding, and finds that current state-of-the-art MLLMs perform poorly when required to process multiple concurrent video streams.

DMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation

DMAD recasts distribution matching as classification and learns log-density ratios directly to improve few-step student training.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIEmpiricalRecentOct 1, 2026

DMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation

Zhengming Yu, Junkun Yuan, Haotian Yang, Gordon Guocheng Qian +7 more

DMAD recasts distribution matching as classification and learns log-density ratios directly to improve few-step student training.

View →
cs.CVRecentJun 1, 2026

X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding

Peiwen Sun, Xudong Lu, Huadai Liu, Yang Bo +8 more

The paper introduces X-Stream, a new benchmark for multi-stream video understanding, and finds that current state-of-the-art MLLMs perform poorly when required to process multiple concurrent video str…

View →
cs.CVRecentJun 1, 2026

X-Stream: Exploring MLLMs as Multiplexers for Multi-Stream Understanding

Peiwen Sun, Xudong Lu, Huadai Liu, Yang Bo +8 more

The paper introduces X-Stream, a new benchmark for multi-stream video understanding, and finds that current state-of-the-art MLLMs perform poorly when required to process multiple concurrent video str…

View →
cs.AIRecentMay 27, 2026

CIVIC: End-to-End Sequence Compactness for Efficient Vision-Language Models

Fengze Yang, Bo Yu, Xuewen Luo, Cathy Liu +1 more

CIVIC is a path-consistent compact visual inference framework that achieves genuine hardware efficiency in Vision-Language Models by maintaining contiguous sequence representations across all inferenc…

View →
cs.AIRecentMay 27, 2026

CIVIC: End-to-End Sequence Compactness for Efficient Vision-Language Models

Fengze Yang, Bo Yu, Xuewen Luo, Cathy Liu +1 more

CIVIC is a path-consistent compact visual inference framework that achieves genuine hardware efficiency in Vision-Language Models by maintaining contiguous sequence representations across all inferenc…

View →