DynaTok introduces temporally adaptive budget allocation with EMA memory and spatial selection with memory to compress video tokens, retaining over 95% accuracy at 90% reduction on VideoQA benchmarks.
Sigmoid loss for language image pre-training
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
A 0.5B student VLM distills from a 3B teacher using visual-switch distillation and DBiLD loss to gain 3.6 points on average across 10 multimodal benchmarks without architecture changes.
citing papers explorer
-
DynaTok: Temporally Adaptive and Positional Bias-Aware Token Compression for Video-LLMs
DynaTok introduces temporally adaptive budget allocation with EMA memory and spatial selection with memory to compress video tokens, retaining over 95% accuracy at 90% reduction on VideoQA benchmarks.
-
Switch-KD: Visual-Switch Knowledge Distillation for Vision-Language Models
A 0.5B student VLM distills from a 3B teacher using visual-switch distillation and DBiLD loss to gain 3.6 points on average across 10 multimodal benchmarks without architecture changes.