Denoising Neural Processes model noisy inputs during meta-learning
On real air-quality sensors, DnNP cuts PM2.5 RMSE by up to 30% and NLL by up to 73% versus standard neural processes.
Stories per day · 30 days
2 RSS
Relatedair-quality1audio-video1autoregressive1bioacoustics1diffusion-models1digital-humans1generative-models1manipulation1meta-learning1model-distillation1neural-processes1open-weights1robotics1sam-audio1score-matching1streaming1taomate-hd1task-status1
9 stories, newest first · one card per story
Stories tagged #denoising
CallCleaner distills SAM-Audio into a 19M bioacoustic denoiser
Authors say the CPU model runs about 90 times faster than real time and leaves 11 dB less noise than Biodenoising.
Energy-Tweedie links Gibbs noise denoising to Stein scores
The identity extends the Gaussian posterior-mean relation to kernel scoring rules and user-chosen noise paths.
TaoMate-HD streams high-resolution audio-video with progressive denoising
Authors report a 1.6x speedup versus direct high-resolution generation and an 11.18-point drop in character error rate.
Echo denoises stop and failure signals inside vision-language action policies
Echo learns task status without frame-level progress labels and uses those signals to condition later action denoising.
ForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video Diffusion
ForcingBooster cuts autoregressive video diffusion steps about 50% by stopping easy patches early.
RNADyn: A Benchmark for Generating and Understanding RNA Dynamics
RNADynBench ships 2,585 quality-controlled 100-ns RNA molecular dynamics trajectories, plus RNADynNet, a unified model for trajectory generation and dynamics fingerprinting.
Rolling-WAM: World Action Models with Rolling Imagination
Rolling-WAM speeds robotic replanning 4.5x by spreading joint denoising across successive cycles.
Rolling-WAM: World Action Models with Rolling Imagination
Rolling-WAM speeds robot replanning 4.5x by staggering joint video-action denoising across cycles.