GAMMA is presenting 5 papers at EMNLP EMNLP 2025 starting Wednesday (11/13), integrating language modeling with topics from audio, vision, and speech! Here are some more details on where you can find us this week 🧵

GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities Sreyan Ghosh, S Kumar, A Seth, CKR Evuru, U Tyagi, S Sakshi, O Nieto, Ramani Duraiswami, Dinesh Manocha 11/13; Session 06 10:30-12:00, Ashe Auditorium Website: sreyan88.github.io/gamaaudio/

AUTOHALLUSION: Automatic Generation of Hallucination Benchmarks for VLMs Xiyang Wu*, Tianrui Guan (On Job Market)*, D Li, S Huang, X Liu, Xijun Wang, Ruiqi Xian, Abhinav Shrivastava, Furong Huang, Jordan Boyd-Graber, Tianyi Zhou, Dinesh Manocha 11/3; 16:00-17:30 - Riverfront Hall Website: wuxiyang1996.github.io/autohallusion_…

🐢👂🗣️Univ. of Maryland CS Ph.D. student Sreyan Ghosh (Sreyan Ghosh) earns the prestigious NVIDIA 2025-26 Graduate Fellowship for advancing AI audio reasoning. His research aims to revolutionize how AI understands sound. Congrats! Read more: go.umd.edu/Ghosh

Congratulations to Kasun (Kasun Weerakoon) for receiving the George Harhalakis Outstanding Systems  Engineering Graduate Student Award for 2023 - 2024! Kasun's recent work focuses on outdoor robot navigation using multimodal guidance with vision and language. kasunweerakoon.org

Sanghyun will be presenting his joint work with UMD Department of Computer Science and Adobe Research on differentiable meshes tomorrow at NeurIPS Conference! 🫖 Check out more details in the quoted tweet 👇 UMD Research UMD Science

Souradip will be presenting his paper on Inference-Time Alignment of LLMs, tomorrow at NeurIPS Conference! Thu, 12 Dec, 11-2 pm PST Check out his thread below for more details 👇 UMD Science UMD Department of Computer Science

I am grateful to receive this award from #CECS, #UCF, Thanks to the support and inspiration from my mentors, colleagues, and students. Excited to keep learning and contributing! UCF UCF Computer Science UCF Engineering UCF SAFERR AI Lab

🥍🥍Excited to share that "Collab: Controlled Decoding Using Mixture of Agents for AI Alignment" has been accepted at #ICLR2025 Q. How to provably combine multiple #expert #LLMs for a target task at #inferencetime ?? 💥 Collab More Details coming soon...

Can decades old ideas from #psychology help fix critical issues in modern LLM alignment? 🤔 We're tapping into #BoundedRationality & 'satisficing principles' to build an alternate way to align LLMs. Our new #ICML2025 paper 👇 🧵 arxiv.org/pdf/2505.23729

📣 📣 Full paper submissions due TOMORROW - June 27, 2025, 11:59 PM AoE for our workshop: 🎬 Short-Form Video Understanding #ICCV2025 #ICCV2025 🌐 …rt-form-video-understanding.github.io 📝 Revise your work, 🧘‍♀️ take a deep breath, and hit 🚀 Submit. You've got this!

(1/n) AURELIA: Test-time Reasoning Distillation in Audio-Visual LLMs We present an actor-critic audio-visual reasoning framework and AVReasonBench to reveal and address AVLLMs’ reasoning limitations, achieving up to 100% improvement with our method. 📄 Paper:

🎓 We’re thrilled to announce that Xijun Wang Xijun Wang, Tianrui Guan Tianrui Guan, and Pooja Guhan Pooja Guhan have successfully defended their PhD theses! Huge congratulations to all three. Your hard work and dedication have truly paid off. We’re so proud of you! 👏🥳

📢 We are proud to share that one paper led by our PhD student Jing Liang Jing was accepted by #ISER2025! MOSU: Autonomous Long-range Robot Navigation with Multi-modal Scene Understanding Paper: cs.gmu.edu/~xiao/papers/m… Authors: Jing Liang Jing, Kasun Weerakoon

🎉 Our lab is proud to present 4 papers at #ICML2025! Here's a quick look at our contributions:

(2/n) Adaptive Sensitivity Analysis for Robust Augmentation against Natural Corruptions in Image Segmentation Thu 17 Jul 11 a.m. PDT — p.m. PDT West Exhibition Hall B2-B3 W-306 Authors: laura, Wenjie Wei, Tony Wu, Jacob Clements, Shreelekha Revankar, Andre Harrison, Yu

(3/n) Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities Wed 16 Jul 4:30 p.m. PDT — 7 p.m. PDT East Exhibition Hall A-B E-2805 Authors: Sreyan Ghosh, Zhifeng Kong, Sonal Kumar, S Sakshi, Jaehyeon Kim, Wei Ping, Rafael Valle,

(4/n) Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time Wed 16 Jul 11 a.m. PDT — 1:30 p.m. PDT East Exhibition Hall A-B E-2701 Author: Mohamad Chehade, Soumya Suvra Ghosal, Souradip Chakraborty, Avinash Reddy, Dinesh Manocha, Hao Zhu, Amrit Singh Bedi Paper:

🥇Audio Flamingo 3 from #NVIDIAResearch is now #1 on the MMAU leaderboard showcasing superpowers in sound, music and speech understanding skills. 🎶 🙌Leaderboard: sakshi113.github.io/mmau_homepage/ 📗Paper: arxiv.org/abs/2507.08128

👁️👂UMD Department of Computer Science Ph.D. student Sanjoy Chowdhury (Sanjoy Chowdhury) advances research in multimodal AI, developing models that integrate audio and visual signals for improved understanding and reasoning. Read more: go.umd.edu/Chowdhury-8-20…