4 papers
MoI-Bench: A Benchmark for Image Generation and Editing on Mobile Devices
Kailai Feng, Haoxiang Rao, Yuxiang Wei +5
Developing on-device image models requires considering practical user needs, task types and device resource constraints. However, existing benchmarks provide limited guidance on id…
PN-Mix: Pair-Norm Guided Mixed-Precision Key Cache Quantization for Efficient Long-Output LLM Inference
Gil Jae Song, Sungjoo Yoo
Long-output inference in large language models suffers from severe KV cache memory and bandwidth bottlenecks. While KV cache quantization alleviates this issue, low-bit quantizatio…
One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Control
Haoxiang Rao, Zhao Wang, Chenyang Si +4
Industrial anomaly detection (AD) is characterized by an abundance of normal images but a scarcity of anomalous ones. Although numerous few-shot anomaly synthesis methods have been…
An Effective End-to-End Solution for Multimodal Action Recognition
Songping Wang, Xiantao Hu, Yueming Lyu +1
Recently, multimodal tasks have strongly advanced the field of action recognition with their rich multimodal information. However, due to the scarcity of tri-modal data, research o…