Unsolvable Problem Detection: Evaluating Trustworthiness of Vision Language Modelsby Atsuyuki Miyai, Jingkang Yang, Jingyang Zhang,…
Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Predictionby Inhwan Bae, Junoh Lee, Hae-Gon JeonFirst…
An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLMby…
Beyond Embeddings: The Promise of Visual Table in Visual Reasoningby Yiwu Zhong, Zi-Yuan Hu, Michael…
The Unreasonable Ineffectiveness of the Deeper Layersby Andrey Gromov, Kushal Tirumala, Hassan Shapourian, Paolo Glorioso,…
Reasoning-Enhanced Object-Centric Learning for Videosby Jian Li, Pu Ren, Yang Liu, Hao SunFirst submitted to…
Multi-Agent VQA: Exploring Multi-Agent Foundation Models in Zero-Shot Visual Question Answeringby Bowen Jiang, Zhijun Zhuang,…
Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Surveyby Zeyu Han, Chao Gao, Jinyang Liu, Jeff…
Extracting Emotion Phrases from Tweets using BARTby Mahdi RezapourFirst submitted to arxiv on: 21 Mar…
VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learningby Yongshuo Zong, Ondrej Bohdal,…