Through-The-Mask: Mask-based Motion Trajectories for Image-to-Video Generation website: guyyariv.github.io/TTM/ abs: arxiv.org/abs/2501.03059

Release Announcement!📢💣 🥁🎷JASCO 🎶🪇 training & inference code + model weights are out! Paper📜: arxiv.org/abs/2406.10970 Samples🔊: pages.cs.huji.ac.il/adiyoss-lab/JA… Code🐍: github.com/facebookresear… Models🤗: huggingface.co/facebook/jasco… Alon Ziv Itai Gat Felix Kreuk Yossi Adi

VideoJAM is our new framework for improved motion generation from AI at Meta We show that video generators struggle with motion because the training objective favors appearance over dynamics. VideoJAM directly adresses this **without any extra data or scaling** 👇🧵

Who recognizes where it is? 🔥 Excited to share that our paper, led by Issar Tzachor, "EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition," has been accepted at #ICLR2025! The VPR task aims to answer this question ⬇️

🗣️🧠 Speech Language Models require lots of compute to train, right? In our new paper, we test is it possible to train an SLM on 1xA5000 gpu in 24 hours? The results may surprise you (they even surprised us)! Tips, open source resources, full paper 👇🏻

🚨 New Paper Alert 🚨 Can you train a **good** speech language model using 24G in only one day? Yes! Yes you can! We show exactly how this can be done and release everything to the public, including code and datasets. More info can be found in the tweet below

I'm thrilled to announce that Through-The-Mask (TTM) has been accepted to #CVPR2025! TTM is an I2V generation framework that leverages mask-based motion trajectories to enhance object-specific motion and maintain consistency, especially in multi-object scenarios More details👇

Introducing RewardSDS, a text-to-3D score distillation method that enhances SDS by using reward-weighted sampling to prioritize noise samples based on alignment scores, achieving fine-grained user alignment. Led by the great Itay Chachy

🚨 New paper alert! 🚨 Millions of neural networks now populate public repositories like Hugging Face 🤗, but most lack documentation. So, we decided to build an Atlas 🗺️ Project: horwitz.ai/model-atlas Demo: huggingface.co/spaces/Eliahu/… 🧵👇🏻 Here's what we found:

New #ICLR2024 paper! The KoLMogorov Test: can CodeLMs compress data by code generation? The optimal compression for a sequence is the shortest program that generates it. Empirically, LMs struggle even on simple sequences, but can be trained to outperform current methods! 🧵1/7

🚀Introducing SISO – a plug-and-play approach for image personalization using just one image!

Many modern SpeechLMs are trained with Speech-Text interleaving. How does this impact scaling trends? In our new paper, we train several dozen SLMs, and show - quite a lot! So there is room for optimism 😊 Key insights, code, models, full paper 👇🏻

The longer reasoning LLM thinks - the more likely to be correct, right? Apparently not. Presenting our paper: “Don’t Overthink it. Preferring Shorter Thinking Chains for Improved LLM Reasoning”. Link: arxiv.org/abs/2505.17813 1/n

🚨 Happy to share our #Interspeech2025 paper! "WhiStress: Enriching Transcriptions with Sentence Stress Detection" Sentence stress is a word-level prosodic cue that marks contrast or intent. WhiStress detects it alongside transcription—no alignment needed. Paper, code, demo 👇

Beyond excited to share FlowMo! We found that the latent representations by video models implicitly encode motion information, and can guide the model toward coherent motion at inference time Very proud of ariel shaulov Itay Hazan for this work! Plus, it’s open source! 🥳

Which modeling to choose for text-to-music generation? We run a head-to-head comparison to figure it out. Same data, same architecture - AR vs FM. 👇 If you care about fidelity, speed, control, or editing see this thread. 🔗huggingface.co/spaces/ortal16… 📄arxiv.org/abs/2506.08570 1/6

🎵💬 If you are interested in Audio Tokenisers, you should check out our new work! We empirically analysed existing tokenisers from every way - reconstruction, downstream, LMs and more. Grab yourself a ☕/🍺 and sit down for a read!

Excited to share our recent work on corrector sampling in language models! A new sampling method that mitigates error accumulation by iteratively revisiting tokens in a window of previously generated text. With: Neta Shaul Uriel Singer Yaron Lipman Link: arxiv.org/abs/2506.06215

[1/n] New paper alert! 🚀 Excited to introduce 𝐓𝐫𝐚𝐧𝐬𝐢𝐭𝐢𝐨𝐧 𝐌𝐚𝐭𝐜𝐡𝐢𝐧𝐠 (𝐓𝐌)! We're replacing short-timestep kernels from Flow Matching/Diffusion with... a generative model🤯, achieving SOTA text-2-image generation! Uriel Singer Itai Gat Yaron Lipman