Shoval Messica

🚨I’m excited to share our #INTERSPEECH2024 paper "NAST: Noise Aware Speech Tokenization for Speech Language Models” 🥳 W/ @adiyossLC Paper-arxiv.org/abs/2406.11037 Code-github.com/ShovalMessica/…

@OmriFahn Amazing!

MFA is a beautiful visualization, but not only that. It’s a practical tool: competitive localization and better steering, while revealing that concepts live in regions, not just single directions. Grateful I got to contribute to this with an awesome team!

8/ 📄 Read the full paper: arxiv.org/abs/2505.21218 Thanks for reading! #AI #LLM #Uncertainty #Interpretability #Research

🤔Can an LLM "unconscious" feel a lie bubbling up before it speaks? 🤔And what mysteries hide in its linear space of uncertainty? Thrilled to share our new paper: “Pre-trained LLMs Learn Multiple Types of Uncertainty” (@roicohen9•@OmriFahn•@GerardDeMelo) arxiv.org/abs/2505.21218

🚨New paper on SLM evaluation🚨 We present SALMon🍣 which is a suite of benchmarks for evaluating how much Speech Language Models model acoustic elements like sentiment or background noise. Project: pages.cs.huji.ac.il/adiyoss-lab/sa… 🧵👇🏻

Which is better, running a 70B model once, or a 7B model 10 times? The answer might be surprising! Presenting our new @COLM_conf paper: "The Larger the Better? Improved LLM Code-Generation via Budget Reallocation" arxiv.org/abs/2404.00725 1/n

@MohammadSalaama Very interesting!

I am excited to share my first work: "Dataset Size Recovery from LoRA Weights". Ever wondered if you could find out how many samples was a model trained on using just its weights? Well now you can! Project: vision.huji.ac.il/dsire/ 👇

Speech tokenizers are fundamental in building speech LMs. In a recent study we show the common tokenization method (a.k.a “semantic tokens”) is not robust to different signal variations. We then present NAST! a noise aware speech tokenizer w. @ShovalMessica Code and models 👇

1/ Commonsense reasoning needs multimodal knowledge, yet current LLMs focus mostly on text, limiting their integration of crucial visual information. We introduce vLMIG, a method that enhances LLMs' visual commonsense by integrating images into the decision-making process

NAST: Noise Aware Speech Tokenization for Speech Language Models. arxiv.org/abs/2406.11037

``Joint Audio and Symbolic Conditioning for Temporally Controlled Text-to-Music Generation,'' Or Tal, Alon Ziv, Itai Gat, Felix Kreuk, Yossi Adi, ift.tt/tP4Hua8

Today we released JASCO 🥁🎵🪇! JASCO uses time-aligned conditions (e.g. drums, melody) as guiding controls for text-to-music generation. 📜Full Paper: arxiv.org/abs/2406.10970 🔊Samples: pages.cs.huji.ac.il/adiyoss-lab/JA… @lonziks @itai_gat @FelixKreuk @adiyossLC Stay tuned for updates.

``NAST: Noise Aware Speech Tokenization for Speech Language Models,'' Shoval Messica, Yossi Adi, ift.tt/TwrHMcg