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

(1/n) Time-Aware World Model for Adaptive Prediction and Control Tue 15 Jul 11 a.m. PDT — 1:30 p.m. PDT West Exhibition Hall B2-B3 W-703 Authors: Anh Nhu, Sanghyun Son, Ming C. Lin Arxiv: arxiv.org/abs/2506.08441 Project Page: anh-nn01.github.io/time-aware-wor…

(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:

Are you interested in test-time AI alignment? If you are attending #ICML2025, please visit our poster: 📍 Poster Location: East Exhibition Hall A–B, Booth #E-2701 📅 When: Wednesday, July 16 | ⏰ 11:00 AM – 1:30 PM PDT Hao Zhu Mohamad Chehade Souradip Chakraborty will be presenting

🚀 Audio General Intelligence (AGI) is no longer a dream — it’s here. Introducing Audio Flamingo 3 — open-source, multimodal, and groundbreaking. It listens. It understands. It reasons across sound and language. 💥 Code, weights, datasets, paper — all open. 📄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

🤖 What if your LLM confidently misread a chart, and you couldn’t tell? 📊 Multimodal LLMs are improving, but still hallucinate when answering chart-based questions. 🎯 Presenting at ACL 2025 (Virtual): ChartLens grounds model answers to specific chart elements, helping users

I DEFENDED MY THESIS TODAY!!! Thanks to my advisor Ming Lin and also my committee and also my family. And like 300 other people

Excited to share our paper HALO is accepted to #CoRL2025! 🧭 HALO introduces a novel method to train vision-based reward models that align with human navigation preferences without requiring online rollouts or hand-engineered rewards. 📌 Key ideas: • We collect binary user

👁️👂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…

🚀 New @UMD_CollegeISR research by Vishnu Sashank Dorbala helps robots truly “get” situational context! 🤖 Introducing Situational EQA (S-EQA), enabling embodied agents to reason over multiple object states & relationships to answer complex, real-world queries like “Is the house ready for