We at NVIDIA and GAMMA UMD are excited to release Audio Flamingo 3, the most powerful, open, and capable large audio-language model to date! Paper: arxiv.org/abs/2507.08128 Open-source model, code, and data: research.nvidia.com/labs/adlr/AF3/ Try it out here: huggingface.co/spaces/nvidia/…

I’ll be presenting this Thursday 4:30pm at the West hall, poster 418. Drop by to learn more about our latest experience in burning compute!

Canary-Qwen-2.5B is our latest, and the first of its kind, ASR model from NVIDIA NeMo team. 🏆 1st place on Open ASR Leaderboard with WER 5.63% 🔥 RTFx=418 on A100 GPU - remarkably fast for its size 💰 CC-BY-4.0 license, commercial-friendly 🌎 English-only

Hi all, we are seeking an ICASSP '26 reviewer in the speech and language processing area. Please consider becoming a reviewer and contributing to our community!

NeKo (ネコ) aims to be your pet model to work with ASR/AST/OCR NVIDIA AI Developer Yenting Lin et al. - back to 2020 conformer-transducer is dominant; people were not very interested in working in ASR-LM (i.e., internal LM of ASR / contextual biasing were popular) appreciate Andreas

I noticed that OpenAI added learnable bias to attention logits before softmax. After softmax, they deleted the bias. This is similar to what I have done in my ICLR2025 paper: openreview.net/forum?id=78Nn4…. I used learnable key bias and set corresponding value bias zero. In this way,

3. OpusLM: Unified Speech-Language Models (led by Jinchuan Tian (田晋川)) Open family of speech language models scaled up to 7B. Poster — Wed, 8:30–10:30 | Foyer 3.2 arxiv.org/abs/2506.17611 Grateful to all collaborators who made this possible!

a nice done of “beyond end2end 🗣️ ASR: integrating long context acoustics & linguistics” tutorial w/ Shinji Watanabe Taejin park (NVIDIA), Kyu Han (Oracle) at INTERSPEECH 2025 happy to cover the semantics parts during my hotel coding vibe 🤣 | 📖 slides: docs.google.com/presentation/d…

More than ever, semiconductors hold the key to the 21st century. Yet Donald Trump’s approach to chipmaking is self-defeating. To remain the world’s foremost technological power, America needs its friends econ.st/4mOcyYZ

Our work on OWSM v4 received the Best Student Paper Award at #Interspeech2025! 🏆🎉 Huge congratulations to the team! 🚀👏 I’m especially happy to see our open science efforts for speech foundation models recognized by the community. 🙌 🔗 isca-archive.org/interspeech_20…

The NVIDIA Jetson Thor is here. 🎉 This powerful new robotics computer is designed to power the next generation of general and #HumanoidRobots in manufacturing, logistics, construction, healthcare, and beyond. It’s a massive leap forward for physical AI. Early adopters

新しいPreprintが出ました。 Video perceptionにおける最も基本的なタスクの一つであるvideo segmentationを、自己回帰モデルとしてReframeすることで、統一されたアーキテクチャやテスト時のスケーリングなど、様々な利点を持つモデルを実現しました。

"Audio-Centric AI: Towards Real-World Multimodal Reasoning and Application Use Cases" has been accepted as an AAAI 2026 workshop🎉 We're looking forward to seeing your contributions, with submissions due by 24 October 2025. sites.google.com/view/audio-aaa…

Ah, mystery since March 2023 finally solved 🦄👇 x.com/thinkymachines…

Together, NVIDIA and OpenAI are expanding the frontier of AI — transforming nearly every industry and unlocking use cases once unimaginable.   “There’s no partner but NVIDIA that can do this at this kind of scale, at this kind of speed,” said OpenAI CEO Sam Altman.

Are you ready for web-scale pre-training with RL ? 🚀 🔥 New paper: RLP : Reinforcement Learning Pre‑training We flip the usual recipe for reasoning LLMs: instead of saving RL for post‑training, we bring exploration into pretraining. Core idea: treat chain‑of‑thought as an

Over the past year, my lab has been working on fleshing out theory/applications of the Platonic Representation Hypothesis. Today I want to share two new works on this topic: Eliciting higher alignment: arxiv.org/abs/2510.02425 Unpaired rep learning: arxiv.org/abs/2510.08492 1/9

btw Alex is a second-month PhD student; he did this work in 4 weeks i have my suspicions that Alex has secret recursive Alexes that do his work for him, but i haven't been able to confirm that haha really fun post on recursive LMs with interesting trace examples, check it out!