4 citations · 4 across the 3 of their papers we have counts for
Showing 2026Show all
3 papers · 1 filter
cs.CV2026
Rotation Is Token-Blind: A Structural Criterion for Post-Training Quantization of Feed-Forward Geometry Transformers
Huanfei He, Bohao Zhang, Jiaxin Zhang +4
Feed-forward 3D models use Transformers to predict camera poses, depth, and structure in one pass, avoiding iterative multi-view optimization. Long sequences and deep attention inc…
cs.CV2026
TecoPrompt: Temporal-Conservative Prompt Learning for Vision-Language Models
Zeyi Shao, Haowen Hua, Jiaxin Zhang +3
Prompt learning adapts vision-language models, such as CLIP, by adjusting a small set of context tokens. However, under few-shot supervision, even moderate label noise can disrupt…
cs.RO2026
World-Model-Augmented Visual Locomotion for Humanoids on Foothold-Constrained Terrain
Yuxi Liu, Lijun Han, Ziming Wang +3
Foothold-constrained terrain limits feasible footholds to sparse, discontinuous, or narrow support regions, as in gaps, stepping stones, stairs, and balance beams. In such settings…