Rethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End Latency
Open paper
Benchmark
Model
Rank
Results
video-question-answering-on-lvbench
LoHi-SemDiv (Qwen3-VL-4B)
–
Accuracy: 45.9
video-question-answering-on-mlvu
LoHi-SemDiv (Qwen3-VL-4B)
–
Accuracy: 74.38
Rank counts only results with a code link.