6 papers
When Instructions Retrieve Trajectories: Diagnosing and Mitigating Generalization Failures in VLA Models
Hung-Jen Chen, Yu-Hsun Hou, Yan-Hong Chen +4
Vision-language-action (VLA) models can exceed 90% success on in-distribution tasks and withstand nuisance changes that preserve the required action, yet fail under counterfactual…
Dynamic Context Adapters: Efficiently Infusing History into Vision-and-Language Models
Yuhang Song, Bor-Jiun Lin, Jiaxu Liu +3
Historical context integration presents a fundamental challenge for Vision-Language Models (VLMs) in sequential decision-making tasks. Current VLMs process visual inputs independen…
Landscape-Awareness for Geometric View Diffusion Model
Yan-Ting Chen, Hao-Wei Chen, Tsu-Ching Hsiao +1
Accurate camera viewpoint estimation under sparse-view conditions remains challenging, particularly in two-view scenarios. Recent approaches leverage diffusion models such as Zero1…
When Demonstrations Fail: Diagnosing the Limits of In-Context Learning in Large Audio-Language Models with Progressive Cue Removal
Yen-Ting Piao, Jay Chiehen Liao, Wei-Tang Chien +5
While Large Audio-Language Models (LALMs) have been shown to exhibit degraded instruction-following capabilities, their ability to infer task patterns from in-context examples with…
MVA 2025 Small Multi-Object Tracking for Spotting Birds Challenge: Dataset, Methods, and Results
Yuki Kondo, Norimichi Ukita, Riku Kanayama +21
Small Multi-Object Tracking (SMOT) is particularly challenging when targets occupy only a few dozen pixels, rendering detection and appearance-based association unreliable. Buildin…
EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling
Jia-Hua Lee, Bor-Jiun Lin, Wei-Fang Sun +1
World models represent a promising approach for training reinforcement learning agents with significantly improved sample efficiency. While most world model methods primarily rely…