GC-TTT adapts goal-conditioned policies at test time by fine-tuning on self-supervised selected goal-related offline data, yielding performance gains in loco-navigation and manipulation tasks.
One-minute video generation with test-time training
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
representative citing papers
FFN performs efficient test-time training on multi-hour videos by forgetting the exiting frame, anticipating the next, and adapting only when a surprise metric exceeds a dynamic threshold.
FAR baseline plus asymmetric kernels for long short-term context modeling achieves SOTA short and long video generation in autoregressive setups.
citing papers explorer
-
Test-time Offline Reinforcement Learning on Goal-related Experience
GC-TTT adapts goal-conditioned policies at test time by fine-tuning on self-supervised selected goal-related offline data, yielding performance gains in loco-navigation and manipulation tasks.
-
Forget, Anticipate and Adapt: Test Time Training for Long Videos
FFN performs efficient test-time training on multi-hour videos by forgetting the exiting frame, anticipating the next, and adapting only when a surprise metric exceeds a dynamic threshold.
-
Long-Context Autoregressive Video Modeling with Next-Frame Prediction
FAR baseline plus asymmetric kernels for long short-term context modeling achieves SOTA short and long video generation in autoregressive setups.