Causal video research
CausalVideoGroup studies how actions, interactions, and prior events shape what happens next in a video. Our research spans long-term coherence, video editing, multi-shot generation, and physical realism. This site documents our research projects and the technical discussions behind them.
Research
Each project page brings together its research question, method, evidence, limitations, paper, code, and related discussions.
Weekly reading group
Each entry prepares the necessary background before the meeting, then records the assumptions, failure cases, and experiments identified during discussion.
A survey of video editing mechanisms and controllable changes, with method deep dives, interactive examples, and open problems in object interaction, editing history, world models, agents, and evaluation.
before-meeting video-editing action-editing world-model agents benchmark
Read discussion →A design-space view of how simulators, explicit controls, training signals, latent dynamics, and inference-time alignment can make generated videos obey real-world physical laws, and what current benchmarks can actually establish.
before-meeting video-generation physics-consistency world-model controllable-generation benchmark evaluation
Read discussion →A data-backed discussion of how video-generation evaluation moves from perceptual proxy scores toward geometric, revisit, and out-of-sight world consistency.
before-meeting video-generation world-model benchmark evaluation
Read discussion →