conftrace_

token aggregation

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

vision-language model (2) content-aware attention (1) video encoding (1) pixel-level perception (1) multi-granularity semantics (1) multi-scale token aggregation (1) center-distance regularization (1) holistic strategy (1) multi-level token sparsification (1) proximal aggregation (1)

Papers

Granulon: Awakening Pixel-Level Visual Encoders with Adaptive Multi-Granularity Semantics for MLLM CVPR 2026 CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution CVPR 2025 Not All Tokens Matter All The Time: Dynamic Token Aggregation Towards Efficient Detection Transformers ICML 2025 TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding EMNLP 2023 Shunted Self-Attention via Multi-Scale Token Aggregation CVPR 2022