Cecilia De La Parra — accepted AI-conference papers

2026

HTTM: Head-wise Temporal Token Merging for Faster VGGT

Weitian Wang, Lukas Meiner, Rai Shubham, Cecilia De La Parra, Akash Kumar

CVPR 2026

The Visual Geometry Grounded Transformer (VGGT) marks a significant leap forward in 3D scene reconstruction, as it is the first model that directly infers all key 3D attributes (camera poses, depths, and dense geometry) jointly in one pass. However, this joint inference mechanism requires global att

Cited by 0 Source ↗Scholar ↗

2025

MixA-Q: Revisiting Activation Sparsity for Vision Transformers from a Mixed-Precision Quantization Perspective

Weitian Wang, Rai Shubham, Cecilia De La Parra, Akash Kumar

ICCV 2025poster

In this paper, we propose MixA-Q, a mixed-precision activation quantization framework that leverages intra-layer activation sparsity (a concept widely explored in activation pruning methods) for efficient inference of quantized window-based vision transformers. For a given uniform-bit quantization c…

Cited by 0 Source ↗PDF ↗Scholar ↗