F^3A is a training-free visual token pruning router that treats pruning as task-conditioned evidence search and allocates a fixed vision token budget using question cues and frozen sparse heads without extra LLM passes.
Transactions of the Association for Computational Linguistics , volume =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
SAGE adds duality consistency as an auxiliary reward in GRPO training with a dynamic operation pool to improve spatial reasoning robustness and generalization in VLMs.
citing papers explorer
-
How Many Visual Tokens Do Multimodal Language Models Need? Scaling Visual Token Pruning with F^3A
F^3A is a training-free visual token pruning router that treats pruning as task-conditioned evidence search and allocates a fixed vision token budget using question cues and frozen sparse heads without extra LLM passes.
-
Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency
SAGE adds duality consistency as an auxiliary reward in GRPO training with a dynamic operation pool to improve spatial reasoning robustness and generalization in VLMs.