Excited to announce SALMA: The first workshop on Speech and Audio Language Models colocated with @ieeeICASSP 2025. We are already accepting submissions! Call for papers: Co-organizing it with: @shinjiw_at_cmu, @dmanocha, @ramani_d, @sohamdesh_ and others

RT @xwang_lk: Suggestion to @ReviewAcl: we need more thorough author-reviewer discussions and fewer submission deadlines. How about 6 -> 4…

RT @sohamdesh_: SALMA is scheduled on 7th April 2025 at ICASSP 2025! We look forward to seeing you there! #ICASSP2025 @ieeeICASSP

RT @_weiping: Introducing AceMath, a cutting-edge suite of math models designed to excel at solving complex math problems, complemented by…

RT @ArxivSound: ``Audio-CoT: Exploring Chain-of-Thought Reasoning in Large Audio Language Model,'' Ziyang Ma, Zhuo Chen, Yuping Wang, Eng S…

RT @NVIDIAAI: #NVIDIACosmos world foundation model platform was voted Best #AI and Best Overall at #CES2025. 🎉 Read to see how Cosmos is a…

RT @Benioff: Rarely am I so captivated and inspired by a CEO’s keynote that it holds my attention for two hours, but Jensen Huang’s indefat…

RT @ArashVahdat: NVIDIA Cosmos world foundation model is now available with the Apache-2 license. Very exciting cool work:

RT @TsungYiLinCV: NVIDIA Cosmos: an open-source World Foundation Model platform! Thrilled to have contributed alongside incredible colleagu…

RT @DrJimFan: Introducing NVIDIA Cosmos, an open-source, open-weight Video World Model. It's trained on 20M hours of videos and weighs from…

RT @liu_mingyu: Cosmos is a developer-first platform designed to help physical AI builders accelerate their develop…

RT @BinWang_Eng: 🎙️ Explore the Collection of Audio Large Language Models – a comprehensive repository of research papers and tools in the…

RT @FelixHill84: Do you work in AI? Do you find things uniquely stressful right now, like never before? Haver you ever suffered from a…

RT @L0SG: Curious about a saxophone that sounds like a meowing cat? 🎷🐱 Meet ETTA, our SOTA text-to-audio model using synthetic audio capti…

RT @RafaelValleArt: New releases before the new year! 1) Audio generation for Music and FX (SOTA) ETTA: Elucidating the Design Space of T…

RT @ArxivSound: ``ETTA: Elucidating the Design Space of Text-to-Audio Models,'' Sang-gil Lee, Zhifeng Kong, Arushi Goel, Sungwon Kim, Rafae…

@LiuXub Yet to read others, but really love Sound-VECaps! Congrats!

@nrehiew_ Not for language modelling, but we found a very related idea useful for generating synthetic data: Interestingly, we modeling this with diffusion first, which worked better, but reviewers wanted us to do AR models in 2023

We at @gammaumd will be hosting the Audio Question Answering challenge, in collaboration with @nvidia @NVIDIAAI Get ready for a challenging task that would require you to build AI systems with advanced audio perception and reasoning capabilities. @dmanocha @umdcs

RT @gammaumd: Congratulations to @SreyanG for receiving the @nvidia 2025-2026 Graduate Fellowship! In the future, he plans to design scala…

RT @umdcs: 🐢👂🗣️@UofMaryland CS Ph.D. student Sreyan Ghosh (@SreyanG) earns the prestigious @nvidia 2025-26 Graduate Fellowship for advancin…