david shavin

[Itay Itzhak @Itay_itzhak_]

🚨Spotlight update🚨

Our paper on bias origins in LLMs is a *spotlight* paper with oral presentation at CoLM 2025!✨

Honored to be among just 24 selected and super excited to present and discuss biases and finetuning limits.

Who’s joining in Montreal Tuesday morning? 👀

[Gal Fiebelman @GalFiebelman]

Excited to announce that "MV-Forcing" has been accepted to #ECCV2026! 🎉

Current methods generate long single-view videos or short multi-view videos, but not both. To bridge this gap, we present MV-Forcing, the first framework for long multi-view video generation.
[1/6]

[Guy Yariv @guy_yariv]

If you’re at #ACL2026, check out my oral presentation on augmenting LLMs via late multi-image fusion

July 6, 11:00–12:30
Harbor B-C

[david shavin @david_shavin]

@gabriberton You're right😂😂 , @elonmusk fault honestly

[david shavin @david_shavin]

Though didn't mention me explicitly 😅 I still very much appreciate this post. Thanks @gabriberton 🙏

[Gabriele Berton @gabriberton]

Masterclass in explainability by @BenaimSagie

A complex pipeline made simple thanks to a clear figure and color-coding of the various components

[david shavin @david_shavin]

@ItkRoni Amazing work!

[Roni Itkin @ItkRoni]

Thrilled to share that GlobalSplat is accepted to ECCV 2026! 🎉
Instead of tying Gaussians to input pixels, GlobalSplat aggregates multi-view input into a fixed-size bank of global scene tokens - align first, decode later - for compact, view-count-agnostic feed-forward novel-view synthesis. As few as 2K–32K Gaussians, ~4 MB, <78 ms single pass.
Work with @YehonatanKe @IssacharNoam @RoverXingyu @AnpeiC @BenaimSagie.
🎥 Project page: https://t.co/DTQJe8Zx8k
💻 Code coming soon - star the repo and stay tuned!
#ECCV2026 #GaussianSplatting #3DVision

[Itai Lang @ItaiLang]

📌 Want to know how we match semantic parts across modalities and domains without any supervision? Come to hear about our Best Segmentation Buddies work TODAY! 👋

🏔 #CVPR2026
🕑 11:45 am – 1:45 pm
📍 ExHall F, poster #584

🌐 https://t.co/6t3AaCSajo

[Noam Issachar @IssacharNoam]

1/6 Diffusion models are scaling up, but deploying a massive, monolithic network uniformly across the entire generative timeline is inherently inefficient.
Introducing Complexity-Balanced Splitting (CBS): a principled framework that allocates capacity exactly where needed!👇🧵

[david shavin @david_shavin]

@omerbenishu Awesome work!!

[Omer Benishu @omerbenishu]

🚨 Excited to share our new paper: "PhyGenHOI: Physically-Aware 4D Generation of Dynamic Human-Object Interactions"! 🎉 We tackle generating photorealistic 4D interactions by deeply coupling generative human motion diffusion with physical simulation! 🧠💥🧵👇(1/4)

[Hadar Davidson @HadarDavidson]

Excited to share Colored Noise Sampling (CNS)!🎉
Instead of injecting white noise, our SDE sampler exploits the inherent spectral bias of diffusion models. We dynamically color the injected noise to focus on frequencies where details are missing, substantially improving FID.🧵1/9

[Noy Sternlicht @NoySternlicht]

🎉 Happy to share that CHIMERA has been accepted to #ACL2026NLP (main conference)!

📄 Paper - https://t.co/11tMhA07P2
🤗 Data - https://t.co/g8GgYsfj9E
🌐 Project Page - https://t.co/c4j8gEm6V5
💻 Git - https://t.co/lVC8UAzOti

Joint work with @Hoper_Tom

[Guy Yariv @guy_yariv]

Our paper:
"LaMI: Augmenting Large Language Models via Late Multi-Image Fusion"

has been selected for an Oral Presentation at #ACL2026!

LaMI boosts LLM visual commonsense by generating complementary images from a text prompt and late-fusing their evidence into the prediction
🧵

[david shavin @david_shavin]

@guy_yariv Amazing work, and congratulations on the incredible achievement of the oral, honestly inspiring and we'll deserved 🎉🎉

[Guy Yariv @guy_yariv]

✨Happy to share that our paper DyPE has been accepted to #ICML2026!

[Guy Kaplan @ ACL 2026 @GKaplan38844]

Fine-Tuning LLMs on New Knowledge Encourages Hallucinations. (@zorikgekhman)
But why? We found something unexpected:
1M facts about city-like names →hallucinations explode.
1M facts about random identifiers →near zero!
Same model. Same number of facts. Only the names change.🧵

[david shavin @david_shavin]

2D VFMs lack 3D awareness—"Splat and Distill" fixes this with feed-forward 3D Gaussian Splatting!🚀

Catch me tomorrow at #ICLR2026 to chat 3D-aware lifting &amp; distillation:
📅 Thurs, Apr 23 | 3:15 PM
📍 Pavilion 4, #3804
🔗 https://t.co/d5q7K3U2tt

See you in Rio! 🇧🇷☀️

[Roni Itkin @ItkRoni]

We introduce 🌍GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens.🌍

Most feed-forward 3DGS methods still start from pixel, voxel, or dense view-aligned primitives.
We take a different route: align first, decode later. 🧵👇

[Gal Fiebelman @GalFiebelman]

Excited to announce that "Let it Snow!" has been accepted to #CVPR2026!🎉

We present a framework for scene-wide dynamic editing of static 3D Gaussian Splatting scenes with dynamic weather effects.

https://t.co/578C2u20hm
[1/5]