9 citations · 14 across the 7 of their papers we have counts for
7 papers
Seeing Through Conflicts: Improving Instruction Hierarchy Alignment in Vision-Language Models
Nicholas Sansoterra, Zishuo Zheng, Sachin Kumar
Instruction hierarchy (IH) alignment teaches language models to prioritize higher-level instructions when inputs conflict. While studied primarily in text-only settings, vision-lan…
Reasoning Up the Instruction Ladder for Controllable Language Models
Zishuo Zheng, Vidhisha Balachandran, Chan Young Park +2
As large language model (LLM) based systems take on high-stakes roles in real-world decision-making, they must reconcile competing instructions from multiple sources within a singl…
MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World
Yining Hong, Zishuo Zheng, Peihao Chen +3
Human beings possess the capability to multiply a melange of multisensory cues while actively exploring and interacting with the 3D world. Current multi-modal large language models…
Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation with Cross-Scale Distortion Awareness
Zhijie Shen, Zishuo Zheng, Chunyu Lin +4
Based on the Manhattan World assumption, most existing indoor layout estimation schemes focus on recovering layouts from vertically compressed 1D sequences. However, the compressio…
RecRecNet: Rectangling Rectified Wide-Angle Images by Thin-Plate Spline Model and DoF-based Curriculum Learning
Kang Liao, Lang Nie, Chunyu Lin +2
The wide-angle lens shows appealing applications in VR technologies, but it introduces severe radial distortion into its captured image. To recover the realistic scene, previous wo…
Complementary Bi-directional Feature Compression for Indoor 360° Semantic Segmentation with Self-distillation
Zishuo Zheng, Chunyu Lin, Lang Nie +3
Recently, horizontal representation-based panoramic semantic segmentation approaches outperform projection-based solutions, because the distortions can be effectively removed by co…
PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation
Zhijie Shen, Chunyu Lin, Kang Liao +3
Existing panoramic depth estimation methods based on convolutional neural networks (CNNs) focus on removing panoramic distortions, failing to perceive panoramic structures efficien…