Certain Gaussian initial noises act as winning tickets that bias motion diffusion toward specific semantics; retrieving and KL-refining them improves text-motion alignment without retraining.
In: ICLR (2019)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
Splash partitions MLLM parameters into dormant and critical subspaces via significance quantification, updating only the dormant subspace for tactile alignment while preserving general capabilities and achieving SOTA on visuo-tactile benchmarks.
citing papers explorer
-
Retrieving and Refining Winning Noise Tickets for Diffusion-Based Motion Generation
Certain Gaussian initial noises act as winning tickets that bias motion diffusion toward specific semantics; retrieving and KL-refining them improves text-motion alignment without retraining.
-
Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs
Splash partitions MLLM parameters into dormant and critical subspaces via significance quantification, updating only the dormant subspace for tactile alignment while preserving general capabilities and achieving SOTA on visuo-tactile benchmarks.