EgoMemReason is a new benchmark showing that even the best multimodal models achieve only 39.6% accuracy on reasoning tasks that require integrating sparse evidence across days in egocentric video.
Frame-voyager: Learning to query frames for video large language models
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7verdicts
UNVERDICTED 7representative citing papers
GridProbe uses posterior probing on a KxK frame grid to adaptively select question-relevant frames, delivering up to 3.36x TFLOPs reduction with accuracy within 1.6 pp of the full-frame baseline on Video-MME-v2.
CATS uses temporal curvature of query-frame relevance to select informative frames, achieving 93-95% of heavy multi-stage accuracy at 3-4% of the preprocessing cost on long-video benchmarks.
OASIS organizes streaming video into hierarchical events and retrieves memory on-demand via intent-driven refinement to improve long-horizon accuracy and compositional reasoning with bounded token costs.
Q-Gate dynamically routes keyframe selection in long videos via query-modulated gating across visual grounding, global matching, and contextual alignment experts to improve MLLM performance.
MACF decouples agent perception budgets from overall video length using latent token collaboration to scale video understanding in MLLMs beyond current limits.
A survey that taxonomizes efficiency methods for LVLMs across the full inference pipeline, decouples the problem into information density, long-context attention, and memory limits, and outlines four future research frontiers with pilot insights.
citing papers explorer
-
EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding
EgoMemReason is a new benchmark showing that even the best multimodal models achieve only 39.6% accuracy on reasoning tasks that require integrating sparse evidence across days in egocentric video.
-
GridProbe: Posterior-Probing for Adaptive Test-Time Compute in Long-Video VLMs
GridProbe uses posterior probing on a KxK frame grid to adaptively select question-relevant frames, delivering up to 3.36x TFLOPs reduction with accuracy within 1.6 pp of the full-frame baseline on Video-MME-v2.
-
CATS: Curvature Aware Temporal Selection for efficient long video understanding
CATS uses temporal curvature of query-frame relevance to select informative frames, achieving 93-95% of heavy multi-stage accuracy at 3-4% of the preprocessing cost on long-video benchmarks.
-
OASIS: On-Demand Hierarchical Event Memory for Streaming Video Reasoning
OASIS organizes streaming video into hierarchical events and retrieves memory on-demand via intent-driven refinement to improve long-horizon accuracy and compositional reasoning with bounded token costs.
-
Where to Focus: Query-Modulated Multimodal Keyframe Selection for Long Video Understanding
Q-Gate dynamically routes keyframe selection in long videos via query-modulated gating across visual grounding, global matching, and contextual alignment experts to improve MLLM performance.
-
Scaling Video Understanding via Compact Latent Multi-Agent Collaboration
MACF decouples agent perception budgets from overall video length using latent token collaboration to scale video understanding in MLLMs beyond current limits.
-
Efficient Inference for Large Vision-Language Models: Bottlenecks, Techniques, and Prospects
A survey that taxonomizes efficiency methods for LVLMs across the full inference pipeline, decouples the problem into information density, long-context attention, and memory limits, and outlines four future research frontiers with pilot insights.