2 citations · 2 across the 4 of their papers we have counts for
5 papers · 1 filter
Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual Information
Chanho Park, Daehyeon Choi, Jihyun Lee +1
Vision-language models (VLMs) can locate an image region referred to by a text prompt and route the corresponding visual evidence to the output, yet the internal mechanism behind t…
Token Warping Helps MLLMs Look from Nearby Viewpoints
Phillip Y. Lee, Chanho Park, Mingue Park +3
Can warping tokens, rather than pixels, help multimodal large language models (MLLMs) understand how a scene appears from a nearby viewpoint? While MLLMs perform well on visual rea…
BoxSplitGen: A Generative Model for 3D Part Bounding Boxes in Varying Granularity
Juil Koo, Wei-Tung Lin, Chanho Park +2
Human creativity follows a perceptual process, moving from abstract ideas to finer details during creation. While 3D generative models have advanced dramatically, models specifical…
Perspective-Aware Reasoning in Vision-Language Models via Mental Imagery Simulation
Phillip Y. Lee, Jihyeon Je, Chanho Park +3
We present a framework for perspective-aware reasoning in vision-language models (VLMs) through mental imagery simulation. Perspective-taking, the ability to perceive an environmen…
Posterior Distillation Sampling
Juil Koo, Chanho Park, Minhyuk Sung
We introduce Posterior Distillation Sampling (PDS), a novel optimization method for parametric image editing based on diffusion models. Existing optimization-based methods, which l…