Goku provides a 2M-pair dataset for multi-task structural video editing, Goku-Edit model with MLLM and dual-branch design, and Goku-Bench yielding up to 8% gains in instruction following.
In: Proceedings of the AAAI Conference on Artificial Intelligence
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.CV 3years
2026 3representative citing papers
Predicting quantized latent residuals (Latent Drift with FSQ) avoids identity collapse and noise interpolation, improving patient-specific 3D MRI neuro-forecasting over diffusion and autoregressive baselines.
ICDepth adapts text-to-video diffusion transformers for video depth estimation via in-context conditioning, achieving SOTA results on benchmarks with 6-13x less training data than prior generative methods.
citing papers explorer
-
Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing
Goku provides a 2M-pair dataset for multi-task structural video editing, Goku-Edit model with MLLM and dual-branch design, and Goku-Bench yielding up to 8% gains in instruction following.
-
Progression as Latent Drift: Generative Forecasting of Slow-Evolving Pathologies
Predicting quantized latent residuals (Latent Drift with FSQ) avoids identity collapse and noise interpolation, improving patient-specific 3D MRI neuro-forecasting over diffusion and autoregressive baselines.
-
ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning
ICDepth adapts text-to-video diffusion transformers for video depth estimation via in-context conditioning, achieving SOTA results on benchmarks with 6-13x less training data than prior generative methods.