11 papers
MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding
Bonan Zhang, Shiyu Dong, Quan Hung Tran +9
Vision encoders are a critical component of vision-language models, and scaling their capacity effectively improves performance. However, dense scaling increases compute cost and i…
Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness
Xilun Chen, Zhaleh Feizollahi, Ross Goodwin +5
Rubric-based evaluation of open-ended generation faces a fundamental tension between expressiveness and reliability. Authoring a faithful rubric requires expressing the structure o…
R3D: Quantitative 3D Spatial Reasoning for Egocentric Wearables
Maxwell Horton, Wei Lu, Quan Tran +6
Quantitative 3D spatial reasoning from egocentric RGB-D video is a critical capability for next-generation wearable assistants. Yet existing benchmarks do not reflect the challenge…
Plan, Watch, Recover: A Benchmark and Architectures for Proactive Procedural Assistance
Kaustav Kundu, Ritvik Shrivastava, Maxim Arap +13
We envision a proactive multi-modal assistant system which gives users real-time step-by-step guidance on a procedural task, autonomously deciding \textit{when} to interrupt, and \…
TRACE: A Framework for Analyzing and Enhancing Stepwise Reasoning in Vision-Language Models
Shima Imani, Seungwhan Moon, Lambert Mathias +2
Reliable mathematical and scientific reasoning remains an open challenge for large vision-language models. Standard final-answer evaluation often masks reasoning errors, allowing s…
SymPyBench: A Dynamic Benchmark for Scientific Reasoning with Executable Python Code
Shima Imani, Seungwhan Moon, Adel Ahmadyan +3
We introduce, a large-scale synthetic benchmark of 15,045 university-level physics problems (90/10% train/test split). Each problem is fully parameterized, supporting an effectivel…