6 papers
ChimeraLoRA: Multi-Head LoRA-Guided Synthetic Datasets
Hoyoung Kim, Minwoo Jang, Jabin Koo +2
Beyond general recognition tasks, specialized domains and fine-grained settings often encounter data scarcity, especially for tail classes. To obtain less biased and more reliable…
Probabilistic Language-Image Pre-Training
Sanghyuk Chun, Wonjae Kim, Song Park +1
Vision-language models (VLMs) embed aligned image-text pairs into a joint space but often rely on deterministic embeddings, assuming a one-to-one correspondence between images and…
KVzip: Query-Agnostic KV Cache Compression with Context Reconstruction
Jang-Hyun Kim, Jinuk Kim, Sangwoo Kwon +3
Transformer-based large language models (LLMs) cache context as key-value (KV) pairs during inference. As context length grows, KV cache sizes expand, leading to substantial memory…
Large-Scale Targeted Cause Discovery via Learning from Simulated Data
Jang-Hyun Kim, Claudia Skok Gibbs, Sangdoo Yun +2
We propose a novel machine learning approach for inferring causal variables of a target variable from observations. Our focus is on directly inferring a set of causal factors witho…
Emergence of Text Readability in Vision Language Models
Jaeyoo Park, Sanghyuk Chun, Wonjae Kim +2
We investigate how the ability to recognize textual content within images emerges during the training of Vision-Language Models (VLMs). Our analysis reveals a critical phenomenon:…
LongProLIP: A Probabilistic Vision-Language Model with Long Context Text
Sanghyuk Chun, Sangdoo Yun
Recently, Probabilistic Language-Image Pre-Training (ProLIP) has been proposed to tackle the multiplicity issue of vision-language (VL) tasks. Despite their success in probabilisti…