15 papers
REZE: Recognition-Based Zero-Shot Extraction for Video Temporal Grounding
Boyang Li, Chenhui Gou, Jianfei Cai
Video temporal grounding (VTG) refers to the task of identifying the time interval in a video that corresponds to a given natural-language query. A common zero-shot strategy asks a…
The ART of Composition: Attention-Regularized Training for Compositional Visual Grounding
Jiayun Luo, Mir Rayat Imtiaz Hossain, Pritam Sarkar +2
Vision-Language Models (VLMs) have achieved strong performance on implicit and explicit visual grounding and related tasks. However, such abilities are generally tested on simple,…
Towards Minimizing Feature Drift in Model Merging: Layer-wise Task Vector Fusion for Adaptive Knowledge Integration
Wenju Sun, Qingyong Li, Wen Wang +3
Multi-task model merging aims to consolidate knowledge from multiple fine-tuned task-specific experts into a unified model while minimizing performance degradation. Existing method…
Copycat vs. Original: Multi-modal Pretraining and Variable Importance in Box-office Prediction
Qin Chao, Eunsoo Kim, Boyang Li
The movie industry is associated with an elevated level of risk, which necessitates the use of automated tools to predict box-office revenue and facilitate human decision-making. I…
GELD: A Unified Neural Model for Efficiently Solving Traveling Salesman Problems Across Different Scales
Yubin Xiao, Di Wang, Rui Cao +3
The Traveling Salesman Problem (TSP) is a well-known combinatorial optimization problem with broad real-world applications. Recent advancements in neural network-based TSP solvers…
SPHERE: Unveiling Spatial Blind Spots in Vision-Language Models Through Hierarchical Evaluation
Wenyu Zhang, Wei En Ng, Lixin Ma +5
Current vision-language models may grasp basic spatial cues and simple directions (e.g. left, right, front, back), but struggle with the multi-dimensional spatial reasoning necessa…