most citedInvestigating the Impact of Quantization on Adversarial Robustness

1 citations · 1 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV2024

GAQAT: gradient-adaptive quantization-aware training for domain generalization

Jiacheng Jiang, Yuan Meng, Chen Tang +4

Research on loss surface geometry, such as Sharpness-Aware Minimization (SAM), shows that flatter minima improve generalization. Recent studies further reveal that flatter minima c…

gr-qc2024

Quasinormal modes of regular black holes with sub-Planckian curvature and Minkowskian core

Chen Tang, Yi Ling, Qing-Quan Jiang +1

We investigate the perturbation of the scalar field as well as the electromagnetic field over a sort of regular black holes which are characterized by the sub-Planckian curvature a…

cs.CV2024

PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference

Ye Li, Chen Tang, Yuan Meng +5

We introduce PRANCE, a Vision Transformer compression framework that jointly optimizes the activated channels and reduces tokens, based on the characteristics of inputs. Specifical…

cs.CV2024

STAR: Skeleton-aware Text-based 4D Avatar Generation with In-Network Motion Retargeting

Zenghao Chai, Chen Tang, Yongkang Wong +1

The creation of 4D avatars (i.e., animated 3D avatars) from text description typically uses text-to-image (T2I) diffusion models to synthesize 3D avatars in the canonical space and…

cs.CV2024

TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models

Haojun Sun, Chen Tang, Zhi Wang +4

Diffusion models have emerged as preeminent contenders in the realm of generative models. Distinguished by their distinctive sequential generative processes, characterized by hundr…

cs.LG20241 cited

Investigating the Impact of Quantization on Adversarial Robustness

Qun Li, Yuan Meng, Chen Tang +2

Quantization is a promising technique for reducing the bit-width of deep models to improve their runtime performance and storage efficiency, and thus becomes a fundamental step for…