DarkQA is a new benchmark that measures vision-language model performance on basic visual questions under controlled low-light degradations modeled from real camera physics.
Memory-centric embodied question answer
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Repurposing a VLA’s vision encoder to emit one action-supervised memory token per historical frame-view yields long-horizon manipulation with large success gains and low latency.
citing papers explorer
-
DarkQA: Benchmarking Vision-Language Models on Visual-Primitive Question Answering in Low-Light Indoor Scenes
DarkQA is a new benchmark that measures vision-language model performance on basic visual questions under controlled low-light degradations modeled from real camera physics.
-
NativeMEM: Native Memory Compression for Long-Horizon Robotic Manipulation
Repurposing a VLA’s vision encoder to emit one action-supervised memory token per historical frame-view yields long-horizon manipulation with large success gains and low latency.