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.
Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Training-free adaptive reuse of stable visual state in video VLMs reduces follow-up latency by 15-36x on Qwen2.5-VL while preserving correctness on VideoMME, with smaller first-query speedups via pruning.
Video Parallel Scaling improves VideoLLM performance by aggregating outputs from parallel inferences on complementary disjoint frame subsets, effectively contracting the Chinchilla scaling law via uncorrelated visual evidence.
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.
-
VLMaxxing through FrameMogging Training-Free Anti-Recomputation for Video Vision-Language Models
Training-free adaptive reuse of stable visual state in video VLMs reduces follow-up latency by 15-36x on Qwen2.5-VL while preserving correctness on VideoMME, with smaller first-query speedups via pruning.
-
Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs
Video Parallel Scaling improves VideoLLM performance by aggregating outputs from parallel inferences on complementary disjoint frame subsets, effectively contracting the Chinchilla scaling law via uncorrelated visual evidence.