CaST-Bench creates a benchmark with causal-chain annotations and novel metrics showing that current VLMs struggle to construct precise grounded causal chains in video QA.
Vrbench: A benchmark for multi-step reasoning in long nar- rative videos
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
background 1polarities
background 1representative citing papers
VideoDR is a new benchmark for open-web video deep research that tests multimodal models on cross-frame visual anchor extraction, interactive retrieval, and multi-hop reasoning over joint video-web evidence.
StoryVideoQA provides the largest auto-generated deep video understanding dataset to date with 363K QAs across TV and movies, paired with the PlotTree agent for hierarchical plot-based reasoning that existing VideoQA models struggle to match.
SagaQA is a new benchmark for long-range multi-hop reasoning in entire TV series, with evaluation showing hybrid planners outperform others on complex narrative tasks.
Chain-of-Glimpse is a reinforcement-learning-based framework that iteratively grounds visual evidence regions to enable multi-step object-aware reasoning in videos.
This is a survey that frames video MLLM research via a human-view formulation of perceptual representations, memory states, reasoning traces, and predictions, then reviews methods, datasets, benchmarks, and open problems.
citing papers explorer
-
CaST-Bench: Benchmarking Causal Chain-Grounded Spatio-Temporal Reasoning for Video Question Answering
CaST-Bench creates a benchmark with causal-chain annotations and novel metrics showing that current VLMs struggle to construct precise grounded causal chains in video QA.
-
Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning
VideoDR is a new benchmark for open-web video deep research that tests multimodal models on cross-frame visual anchor extraction, interactive retrieval, and multi-hop reasoning over joint video-web evidence.
-
StoryVideoQA: Scaling Deep Video Understanding with a Large-Scale, Multi-Genre and Auto-Generated Dataset
StoryVideoQA provides the largest auto-generated deep video understanding dataset to date with 363K QAs across TV and movies, paired with the PlotTree agent for hierarchical plot-based reasoning that existing VideoQA models struggle to match.
-
SagaQA: A Multi-hop Reasoning Benchmark for Long-form Narrative Understanding in TV Series
SagaQA is a new benchmark for long-range multi-hop reasoning in entire TV series, with evaluation showing hybrid planners outperform others on complex narrative tasks.
-
Chain-of-Glimpse: Search-Guided Progressive Object-Grounded Reasoning for Video Understanding
Chain-of-Glimpse is a reinforcement-learning-based framework that iteratively grounds visual evidence regions to enable multi-step object-aware reasoning in videos.
-
Watch, Remember, Reason: Human-View Video Understanding with MLLMs
This is a survey that frames video MLLM research via a human-view formulation of perceptual representations, memory states, reasoning traces, and predictions, then reviews methods, datasets, benchmarks, and open problems.