PyramidDrop accelerates LVLMs by staged, similarity-based dropping of visual tokens that become redundant in deeper layers, delivering 40% faster training and 55% lower inference cost with comparable accuracy.
Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2representative citing papers
TaleDiffusion introduces an iterative framework using LLM-generated per-frame descriptions, bounded attention-based per-box masks, identity-consistent self-attention, region-aware cross-attention, and CLIPSeg-based dialogue rendering to produce consistent multi-character story visualizations.
citing papers explorer
-
PyramidDrop: Accelerating Your Large Vision-Language Models via Pyramid Visual Redundancy Reduction
PyramidDrop accelerates LVLMs by staged, similarity-based dropping of visual tokens that become redundant in deeper layers, delivering 40% faster training and 55% lower inference cost with comparable accuracy.
-
TaleDiffusion: Multi-Character Story Generation with Dialogue Rendering
TaleDiffusion introduces an iterative framework using LLM-generated per-frame descriptions, bounded attention-based per-box masks, identity-consistent self-attention, region-aware cross-attention, and CLIPSeg-based dialogue rendering to produce consistent multi-character story visualizations.