GAMMA UMD
@gammaumd
Followers
723
Following
212
Media
321
Statuses
1K
Geometric Algorithms for Modeling, Motion, and Animation research group: UNC Chapel Hill (1992-2018); University of Maryland, College Park (2018 onwards)
College Park, MD
Joined October 2009
🤖 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.
0
0
1
RT @NVIDIAAIDev: 🥇Audio Flamingo 3 from #NVIDIAResearch is now #1 on the MMAU leaderboard showcasing superpowers in sound, music and speech….
0
46
0
RT @amritsinghbedi3: Are you interested in test-time AI alignment?. If you are attending #ICML2025, please visit our poster:.📍 Poster Locat….
0
4
0
🚀 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:
0
2
5
RT @amritsinghbedi3: Can decades old ideas from #psychology help fix critical issues in modern LLM alignment? 🤔. We're tapping into #Bounde….
0
11
0
(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, @SOURADIPCHAKR18, Avinash Reddy, @dmanocha, @HaoZhu6, @amritsinghbedi3 .Paper:.
0
1
3
(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: @SreyanG, Zhifeng Kong, Sonal Kumar, S Sakshi, Jaehyeon Kim, Wei Ping, Rafael Valle,.
0
2
5
(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: @laurayuzheng, Wenjie Wei, Tony Wu, Jacob Clements, Shreelekha Revankar, Andre Harrison, Yu.
0
1
3
(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_n_nhu, @SanghyunSon, @MingCLinCS Arxiv: .Project Page:
arxiv.org
In this work, we introduce the Time-Aware World Model (TAWM), a model-based approach that explicitly incorporates temporal dynamics. By conditioning on the time-step size, Δt, and training...
0
1
1
RT @anh_n_nhu: I will be presenting our work on Time-Aware World Model (TAWM) at #ICML2025 next Tuesday (Jul 15) at West Exhibition Hall B2….
arxiv.org
In this work, we introduce the Time-Aware World Model (TAWM), a model-based approach that explicitly incorporates temporal dynamics. By conditioning on the time-step size, Δt, and training...
0
4
0
📢 We are proud to share that one paper led by our PhD student Jing Liang @Jing53582 was accepted by #ISER2025!. MOSU: Autonomous Long-range Robot Navigation with Multi-modal Scene Understanding. Paper: Authors: Jing Liang @Jing53582, Kasun Weerakoon
0
4
10