Neta Shaul

@shaulneta

PhD Student at @WeizmannScience

neta93.github.io

Joined June 2023

Following

477

Followers

Replies Reposts Media

Neta Shaul
@shaulneta
Jul 29
1/ New paper: Parallel Decoding Distillation (PDD)!🚀 To accelerate diffusion/flow models, trajectory distillation usually merges consecutive ODE steps into 1 larger step. PDD changes this by predicting MULTIPLE ODE steps in 1 network eval.🧵 w/ @julberner @ArashVahdat Chao Liu
00:00
5
Neta Shaul
@shaulneta
Jul 7
Flow Matching obtains its training supervising velocity by conditioning on data samples. But what if you don’t have a dataset, only an unnormalized density? Flow Sampling gets the supervising drift by conditioning on the source instead of the target. Catch @aaronjhavens at #ICML
GIF
Aaron Havens
@aaronjhavens
Jul 7
Excited to be at ICML to present our Spotlight paper: Flow Sampling! We propose a simple fixed-point objective for learning diffusion samplers, built on the flow matching marginal construction. More details to come soon! Paper: arxiv.org/abs/2605.03984
2
Neta Shaul
@shaulneta
Mar 25
Congrats @YarivLior! Very interesting direction for accelerating flow/diffusion models🚀
Lior Yariv
@YarivLior
Mar 25
Why pay full compute for pixels you're not even looking at? In our new work, Foveated Diffusion, we introduce a new concept for efficient image and video generation, motivated by how the human visual system works. (See full thread below)
1
Neta Shaul
@shaulneta
Jan 18
After multiple requests for the code of the visuals from my talk about Transition Matching, I made a notebook that reproduces the DTM vs. FM GIF! This demo is a good way to build intuition on how TM and FM differ. github.com/neta93/visual-… @urielsinger
GitHub - neta93/visual-illustrations: Python code for creating visual illustrations that explain my...
From github.com
Neta Shaul
@shaulneta
Jan 18
Very cool! Transition matching for fast inference.
Julius Berner
@julberner
Jan 16
🚀🎬We introduce TMD (Transition Matching Distillation): 480p videos generated from text prompts in < 3 NFEs! 1️⃣Main backbone for feature extraction and lightweight head for iterative refinement 2️⃣Distilled from Wan2.1 14B T2V combining MeanFlow & DMD2 🔗research.nvidia.com/labs/genair/tmd
00:00