OVO-S-Bench provides 1680 human-annotated questions on 348 videos to measure streaming spatial intelligence in MLLMs across instantaneous perception, spatiotemporal tracking, spatial simulation, and allocentric mapping.
Fluxmem: Adaptive hierarchical memory for streaming video understanding
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 6roles
baseline 1polarities
baseline 1representative citing papers
SAVEMem improves streaming video understanding scores by adding semantic awareness to memory compression and query-adaptive retrieval without any model training.
Presents Streaming-Train-248K dataset, Streaming Harness system, and Streaming-Eval benchmark to enable VLMs for proactive, memory-equipped streaming video understanding.
VLA-Pro improves cross-task generalization in vision-language-action models by storing task-specific LoRA adapters as procedural memories and retrieving/fusing them at inference.
MemEye benchmark evaluates multimodal memory on visual granularity and evidence synthesis, finding that 13 methods across 4 VLMs struggle with fine details and temporal state changes.
CausalMem constructs a dynamic fixed-budget memory bank for streaming video in MLLMs via online semantic basis updates, achieving 20x token compression and accuracy gains on benchmarks when applied to LLaVA-OneVision and Qwen2.5-VL.
citing papers explorer
-
OVO-S-Bench: A Hierarchical Benchmark for Streaming Spatial Intelligence in Multimodal LLMs
OVO-S-Bench provides 1680 human-annotated questions on 348 videos to measure streaming spatial intelligence in MLLMs across instantaneous perception, spatiotemporal tracking, spatial simulation, and allocentric mapping.
-
Semantic-Aware Adaptive Visual Memory for Streaming Video Understanding
SAVEMem improves streaming video understanding scores by adding semantic awareness to memory compression and query-adaptive retrieval without any model training.
-
Harnessing Streaming Video in the Wild
Presents Streaming-Train-248K dataset, Streaming Harness system, and Streaming-Eval benchmark to enable VLMs for proactive, memory-equipped streaming video understanding.
-
VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action Models
VLA-Pro improves cross-task generalization in vision-language-action models by storing task-specific LoRA adapters as procedural memories and retrieving/fusing them at inference.
-
MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory
MemEye benchmark evaluates multimodal memory on visual granularity and evidence synthesis, finding that 13 methods across 4 VLMs struggle with fine details and temporal state changes.
-
Towards a Dynamic and Fixed-budget Memory Bank for Efficient Streaming Video Understanding
CausalMem constructs a dynamic fixed-budget memory bank for streaming video in MLLMs via online semantic basis updates, achieving 20x token compression and accuracy gains on benchmarks when applied to LLaVA-OneVision and Qwen2.5-VL.