Noam Rotstein (@NoamRot) header
Noam Rotstein (@NoamRot) profile picture

Noam Rotstein

@NoamRot
Joined April 2009
  • Tweets201
  • Following674
  • Followers158
55Media
Photo by Noam Rotstein (@NoamRot)Photo by Noam Rotstein (@NoamRot)Photo by Noam Rotstein (@NoamRot)Photo by Noam Rotstein (@NoamRot)Photo by Noam Rotstein (@NoamRot)Photo by Noam Rotstein (@NoamRot)Photo by Noam Rotstein (@NoamRot)Photo by Noam Rotstein (@NoamRot)Photo by Noam Rotstein (@NoamRot)Photo by Noam Rotstein (@NoamRot)
🎬 Excited to share our paper: Joints, Camera, Action! (JCA) JCA generates video & 3D motion together for any rig! Video models generate motion you can watch. But what if you could use that motion to animate a 3D asset, with motion that responds to its surroundings? research.nvidia.com/labs/par… 🧵
4
42
6
99
7,300
Super exciting to see Time-to-Move extended to MiniMax H3! The results look awesome! 🚀
Stable Diffusion Tutorials (@SD_Tutorial) profile pictureStable Diffusion Tutorials@SD_TutorialOct 30
Minimax h3 😲 Motion Time to move implementation of time-to-move dual clock denoising for Minimax H3, allowing for motion control by dragging objects into motion, or mask part of a video and change what happens. github: github.com/PxTicks/h3-motion workflow: drive.google.com/file/d/1mOH…
11
402
Meet ReLift, our latest work on 3D tracking! 🏋️ Rethinking 3D tracking with the right combination: Strong 2D trackers ＋ 3D geometry ＋ Efficient trajectory corrector ────────────── 　 Dense 3D tracking, 　 even through occlusions!
Assaf Singer (@assaf_singer) profile pictureAssaf Singer
@assaf_singerNov 2
🚀 Introducing ReLift: dense 3D tracking from monocular video. Strong 2D trackers provide correspondences. Geometry models produce depth & cameras. We show how to combine them, repair 3D errors, and recover occluded motion for SOTA 3D tracking. All it takes: one small corrector + off-the-shelf models. 🌐 Project: relift3d.github.io/ @MarounKhriesh @NoamRot @yoni_kasten @orlitany
1
3
31
1,708
Coding agents can build an app. What if they could give it a body? Meet Metatron: a versatile System 1 controller for humanoids. A goal-based interface connects System 2 planners, including coding agents, to whole-body movement. A few examples below. 1/5
3
34
11
129
17,105
Noam Rotstein retweeted
Yftah Ziser (@YftahZ) profile picture
Yftah Ziser@YftahZOct 22
1/4 We trained an 8B safety classifier on just 1,275 carefully annotated prompts. It beat GPT-5.4, Claude Sonnet 4.6, and leading open-weight guardrails trained on far more data, on average across 5 safety benchmarks. Quality > quantity.
Image from Yftah Ziser (@YftahZ)
3
13
2
27
1,721
We build ~200K video–motion pairs across diverse rigs. A major part is “Objaverse in Video”: a video editor places existing animated asset renders in suitable scenes, creating data at scale for arbitrary rigs. We add human and robot data.
1
1
143
For more details, check out the paper! Project page: research.nvidia.com/labs/par… Paper: arxiv.org/abs/2610.28632 Big shoutout to my collaborators! @YoadTewel @ChenTessler @HaggaiMaron @GalChechik @orlitany @yoni_kasten @AtzmonYuval at @nvidia Research
3
218
Noam Rotstein retweeted
Uri Berger (@uriberger88) profile picture
Uri Berger@uriberger88Oct 13
Do vision-language models look at the image regions they describe? In our new paper, we present Self-Saliency, a method for aligning visual attention with reasoning text. research.nvidia.com/labs/par… w/ @GalChechik @DalalGal
Self-Saliency: Look Where You Say You're Looking

Self-Saliency: Look Where You Say You're Looking

Grounding a VLM's own reasoning chain, and rewarding it for attending to the regions it just described.

research.nvidia.com
4
22
120
3,968
Noam Rotstein retweeted
Saar Huberman (@HubermanSaar) profile picture
Saar Huberman@HubermanSaarOct 4
Excited to share our work, “Token-to-Token Alignment of Text Embeddings for Semantic Blending,” accepted as a NeurIPS 2026 Spotlight 🌟 Can we directly interpolate between semantic concepts? Text embedding spaces already encode a continuous semantic structure, the missing piece is alignment. Once aligned, simple interpolation becomes meaningful, naturally enabling multiple applications. Joint work with @MokadyRon @OPatashnik @DanielCohenOr1
Image from Saar Huberman (@HubermanSaar)
2
17
2
51
3,457
Noam Rotstein retweeted
Or Litany (@orlitany) profile picture
Or Litany@orlitanyOct 2
Meet DyRAD: Radar NVS for dynamic driving scenes. 📡🚗 Radar directly senses motion through Doppler, but prior radar NVS methods ignore this signal where it matters most: dynamic scenes. 🌐 dyrad-nvs.github.io 📄 arxiv.org/abs/2609.39841 💻 github.com/Dyrad-NVS/DyRAD 🧵
Image from Or Litany (@orlitany)
1
20
30
923
To Pareto and beyond! 🚀
Shelly Golan (@Shelly_Golan1) profile pictureShelly Golan@Shelly_Golan1Sep 30
Excited to share that our paper "ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control" has been accepted to @NeurIPSConf as an oral! 🎉 ParetoSlider enables continuous inference-time control over competing reward trade-offs with a single diffusion model, without retraining or maintaining multiple checkpoints. Huge thanks to the great team @mikikiFin, @ArielBAMath, @YotamNitzan, @OPatashnik Paper: arxiv.org/abs/2604.20816 Project page: shelley-golan.github.io/Pare… Code: github.com/Shelley-Golan/Par…
ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control

ParetoSlider: Diffusion Models Post-Training for Continuous Reward Control

Reinforcement Learning (RL) post-training has become the standard for aligning generative models with human preferences, yet most methods rely on a single scalar reward. When multiple criteria...

arxiv.org
1
2
264
Noam Rotstein retweeted
Roy Ganz (@roy_ganz) profile picture
Roy Ganz@roy_ganzAug 26
1/11 Can a stronger coding model rescue a run started by a cheaper one? Can a cheaper model continue a stronger model's work - retaining quality at lower cost? The two directions behave very differently... Check out our new paper: The Handoff Tax 🧵 📄 arxiv.org/abs/2608.24358
Image from Roy Ganz (@roy_ganz)
2
7
1
24
1,067
Noam Rotstein retweeted
Dvir Samuel (@dvir_samuel) profile picture
Dvir Samuel@dvir_samuelAug 16
🥳 Excited to share UniProbe: A learnable, token-level hallucination detection for large VLMs 🔎 UniProbe looks inside a VLM’s internals to identify hallucinated response tokens and mitigate them before they reach the user. 📉 55% fewer hallucinations ⚡ Just 1.06× latency
1
11
1
25
2,145
Noam Rotstein retweeted
Dvir Samuel (@dvir_samuel) profile picture
Dvir Samuel@dvir_samuelJul 6
I'm going to present Fast-AR at #ICML26 tomorrow (Tuesday) @ 2pm - poster #1204! Come and say hi 👋 If you're around this week, feel free to DM me. Project page: dvirsamuel.github.io/fast-au… Details below ⬇️
Dvir Samuel (@dvir_samuel) profile pictureDvir Samuel@dvir_samuelFeb 3
🚀 Excited to share our new paper: “Fast Autoregressive Video Diffusion & World Models with Temporal Cache Compression & Sparse Attention.” We address attention bottlenecks in auto-regressive video diffusion, enabling ×5–×10 speedup and constant memory over long rollouts.
3
9
1
23
8,694
Noam Rotstein retweeted
Tomer Borreda (@TomerBorreda) profile picture
Tomer Borreda@TomerBorredaJun 21
Excited to share that my first PhD paper, RadarGen, got accepted to #ECCV2026! 🎉 Let’s talk about radar simulation in Malmö 🇸🇪
Tomer Borreda (@TomerBorreda) profile pictureTomer Borreda@TomerBorreda22 Dec 2025
📢 RadarGen: Automotive Radar Point Cloud Generation from Cameras Can we generate realistic radar point clouds solely from camera images? 🚗📡 We introduce RadarGen, a diffusion-based framework that synthesizes radar returns aligned with visual scenes. radargen.github.io
10
79
11,002
Load more