5 papers · 1 filter
TwinPrune: Density-Aware Two-Phase Token Pruning for Vision-Language Models
Kai Liu, Anqi Li, Junxian Li +4
We propose a unified spatial-density signal to score token importance for both inference phases: bipartite merge for prefill and KV eviction for decode, yielding measurable gains i…
OrganLens: Organ-Specific Representation Learning for CT Foundation Models
Zhixuan Ge, Anqi Li, Sadeer Al-Kindi +2
A CT examination captures multiple organs, but many biomedical questions concern abnormalities, prognosis, or longitudinal change in a specific organ. These questions require a sep…
DRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language Models
Xinrui Shi, Kai Liu, Ziqing Zhang +3
Lightweight vision-language models perform competitively on standard benchmarks yet fail systematically in dense-scene reasoning, where multiple objects, attributes, and relations…
Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention
Junhao Du, Jialong Xue, Anqi Li +2
Video large language models (Video-LLMs) face high computational costs due to large volumes of visual tokens. Existing token compression methods typically adopt a two-stage spatiot…
FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models
Jintao Tong, Wenwei Jin, Pengda Qin +5
Large vision-language models (LVLMs) excel at multimodal understanding but suffer from high computational costs due to redundant vision tokens. Existing pruning methods typically r…