Sreyan Ghosh

We at @nvidia and @gammaumd 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/…

📢 Call for Papers is out - salma-workshop.github.io/salma-2026/ We invite submissions to SALMA 2026: Speech and Audio Language Models Workshop, co-located with EMNLP 2026.🎙️ 🗓️ Direct Submission: July 27, 2026 ARR Commitment: August 26, 2026 Please spread the word and consider submitting!

Excited to announce SALMA 2026: Speech and Audio Language Models Workshop, co-located with EMNLP 2026 in Budapest, Hungary! 🎙️

No more endless chasing AudioLM updates! 🏹🔊 Speech-Hands Agent has been accepted to @aclmeeting for oral & open-sourced, with a 5.69% WER as Voice-Agent and 77.37% Acc. on @DCASE_Challenge 25 AudioQA dev-set. Check our demo and open-claw PR 🦞arxiv.org/pdf/2601.09413 a joint work with Zhen Wan @ZhehuaiC @leoyerrrr @goelarushi27 @MXzBFhjFpS1jyMI @shinjiw_at_cmu @SreyanG @RafaelValleArt @RHachiuma @hirota_yusuke et al.

Speaking tomorrow at Stanford about the opportunity to build deep tech in India. If you want to train models, build products, create population scale impact, or are just curious what we are up to then RSVP and show up - sarvam.ai/events/stanfor…

The future of Math is mathematicians and AI agents working together. Very pleased to introduce @GoogleDeepMind's AI co-mathematician: a multi-agent system designed to actively collaborate with human experts on open-ended research mathematics. Mathematicians testing the agent across areas as diverse as group theory, Hamiltonian systems, and algebraic combinatorics have reported impressive results. In autonomous mode evaluation on the rigorous FrontierMath Tier 4 problems, AI co-mathematician scored an unprecedented 48% — a new high score among all AI systems evaluated.

Dr. Tara Sainath, Distinguished Research Scientist, Google DeepMind, presents the first Industry Keynote: “Audio Processing with Large Language Models”

We’re partnering with the developers of @EveOnline to explore the next frontier of AI research in games. EVE's complex, player-driven universe is the perfect safe sandbox to test agents on memory, continual learning, and long-term planning. Find out more → goo.gle/4epQIdy

Today we launch smol-audio A collection of notebooks & scripts to build on cutting-edge local audio models ⚡️ Already in the cookbook: > Fine-tune Whisper / Parakeet / Voxtral / Granite Speech > Fine-tune Audio Flamingo 3 (full + LoRA) > Dialogue TTS with Dia-1.6B > Zero-shot

NVIDIA just released Nemotron 3 Nano Omni on Hugging Face A 30B parameter multimodal foundation model with native text, image, video, and audio understanding.

NVIDIA Nemotron™ 3 Nano Omni is live on OpenRouter. An open 30B-A3B multimodal model for agentic workflows: text, image, video, and audio in → text out, with a 256k context window and efficient MoE architecture for computer use, documents, and AV reasoning.

NVIDIA releases Nemotron-3-Nano-Omni, a new 30B open multimodal MoE model. Nemotron-3-Nano-Omni-30B-A3B is the strongest omni model for its size and supports audio, video, image and text. Run on ~25GB RAM. GGUF: huggingface.co/unsloth/NVIDIA… Guide: unsloth.ai/docs/models/ne…

🎉 Congrats to @NVIDIAAI on Nemotron 3 Nano Omni — a 30B hybrid Transformer-Mamba MoE (3B active) that unifies vision, audio, video, and text in a single reasoning loop. 256K context, FP8 / NVFP4 quantization, open weights. Day-0 support in vLLM — tool calling, reasoning, and efficient video sampling for long-video workloads, verified on NVIDIA GPUs. 🔗 vllm.ai/blog/nemotron-… 🔗 recipes.vllm.ai/nvidia/Nemotro…

Today we're releasing Nemotron 3 Nano Omni. Audio, Video, Image, Text ➡️ Text Ask questions about all your data. Amazing efficiency powered by the Nemotron Hybrid SSM MoE architecture. State of the art multimodal intelligence.

Today we released Nemotron-3-Nano-Omni-30B-A3B - our first Omni model, with speech and audio understanding capabilities powered by parakeet-tdt-0.6b-v2 encoder. 🫡1st position on VoiceBench 🌏English only 🎙️5.95% WER on Open ASR Leaderboard 📽️Video+audio understanding

RT @huckiyang: Grateful to share four LM Post-training papers on Multimodal / Audio / Time-Series presented at @iclr_conf 2026, all open-s…

This is Decoupled DiLoCo: our new resilient and flexible way to train advanced AI models across multiple data centres. 🧵

Vaibhavi Lokegaonkar, Aryan Vijay Bhosale, Vishnu Raj, Gouthaman KV, Ramani Duraiswami, Lie Lu, Sreyan Ghosh, Dinesh Manocha, "Video-Robin: Autoregressive Diffusion Planning for Intent-Grounded Video-to-Music Generation," arxiv.org/abs/2604.17656

We’re introducing our eighth generation of TPUs. This time, we’re taking a dual chip approach: TPU 8t, optimized for training, and TPU 8i, optimized for inference. 💪TPU 8t achieves nearly three times the compute performance per pod over our previous generation, Ironwood. ⚡TPU

Congratulations to Sreyan Ghosh @SreyanG on his PhD defense at UMD! 🎉 His dissertation, “Advancing Audio Processing in the Age of Large Language Models,” pushes forward audio, music, and long-form multimodal understanding through open models, large-scale data, new benchmarks, and temporally grounded reasoning. Really exciting work with broad impact on audio-language and audio-visual AI. Huge congratulations, Sreyan!