List your company

Multimodal Evaluation on COCO

100.22Average PercentageFastV
-4.008823.050650.1177.1694May 1, 2026

Evaluation results

MethodLinks
FastVBackbone=LLaVA-v1.5-13B, Compression Timing=During prefill, FLOPs (Tera)=12.4, Memory (GB)=0.36, TTFT (sec)=0.085, Vision Token Retention=55%2026.05100.221.16
VanillaBackbone=LLaVA-v1.5-13B, FLOPs (Tera)=19.4, Memory (GB)=0.55, TTFT (sec)=0.130, Vision Token Retention=55%2026.051001.16
VanillaBackbone=LLaVA-v1.5-7B, FLOPs (Tera)=10.2, Memory (GB)=0.35, TTFT (sec)=0.078, Vision Token Retention=55%2026.051001.1
LightKVBackbone=LLaVA-v1.5-13B, Compression Timing=During prefill, FLOPs (Tera)=12.6, Memory (GB)=0.37, TTFT (sec)=0.098, Vision Token Retention=55%2026.0599.941.15
LightKVBackbone=LLaVA-v1.5-7B, Compression Timing=During prefill, FLOPs (Tera)=6.6, Memory (GB)=0.23, TTFT (sec)=0.065, Vision Token Retention=55%2026.0599.791.11
LightKVBackbone=LLaVA-NeXT-7B, Compression Timing=During prefill, FLOPs (Tera)=22.3, Memory (GB)=0.67, TTFT (sec)=0.259, Vision Token Retention=55%2026.0598.850.98
LightKVBackbone=LLaVA-NeXT-13B, Compression Timing=During prefill, FLOPs (Tera)=37.3, Memory (GB)=1.05, TTFT (sec)=0.383, Vision Token Retention=55%2026.0598.120.96
HiREDBackbone=LLaVA-v1.5-7B, Compression Timing=During prefill, Vision Token Retention=55%2026.0596.451.03
ToMe (P)Backbone=LLaVA-v1.5-13B, Compression Timing=During prefill, FLOPs (Tera)=12.6, Memory (GB)=0.37, TTFT (sec)=0.094, Vision Token Retention=55%2026.0593.961.16
PiToMeBackbone=LLaVA-v1.5-13B, Compression Timing=During prefill, FLOPs (Tera)=12.6, Memory (GB)=0.37, TTFT (sec)=0.093, Vision Token Retention=55%2026.0593.421.14
ToFuBackbone=LLaVA-v1.5-13B, Compression Timing=During prefill, FLOPs (Tera)=12.6, Memory (GB)=0.37, TTFT (sec)=0.094, Vision Token Retention=55%2026.0593.361.14
ToMe (C)Backbone=LLaVA-v1.5-13B, Compression Timing=Post prefill, FLOPs (Tera)=19.0, Memory (GB)=0.33, TTFT (sec)=0.141, Vision Token Retention=55%2026.0587.11
ImgRandBackbone=LLaVA-v1.5-13B, Compression Timing=Post prefill, FLOPs (Tera)=19.0, Memory (GB)=0.31, TTFT (sec)=0.134, Vision Token Retention=55%2026.0585.090.95
RandBackbone=LLaVA-v1.5-13B, Compression Timing=Post prefill, FLOPs (Tera)=19.0, Memory (GB)=0.31, TTFT (sec)=0.134, Vision Token Retention=55%2026.0570.530.48
ElasticBackbone=LLaVA-v1.5-13B, Compression Timing=Post prefill, FLOPs (Tera)=19.3, Memory (GB)=0.31, TTFT (sec)=0.598, Vision Token Retention=55%2026.0568.540.96
ElasticBackbone=LLaVA-NeXT-13B, Compression Timing=Post prefill, TTFT (sec)=2.302, Vision Token Retention=55%2026.050—