-
An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models
Paper • 2403.06764 • Published • 28 -
VideoMamba: State Space Model for Efficient Video Understanding
Paper • 2403.06977 • Published • 30 -
Phased Consistency Model
Paper • 2405.18407 • Published • 48
Natalia Frumkin
nfrumkin
·
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 1 month ago
Jumping through Local Minima: Quantization in the Loss Landscape of
Vision Transformers
upvoted
a
paper
about 2 months ago
Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with
Quantization-Aware Scheduling
commented on
a paper
about 2 months ago
Q-Sched: Pushing the Boundaries of Few-Step Diffusion Models with
Quantization-Aware Scheduling
Organizations
-
An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models
Paper • 2403.06764 • Published • 28 -
VideoMamba: State Space Model for Efficient Video Understanding
Paper • 2403.06977 • Published • 30 -
Phased Consistency Model
Paper • 2405.18407 • Published • 48
models
0
None public yet
datasets
0
None public yet