7 papers
Co-Adaptive Entropy Modeling and Rate-Distortion-Optimal Bit Allocation for Perceptual Audio Coding
Soohyun Kim, Jiwon Jeong, Marina Bosi
We present a perceptual audio coder in which the entropy-coding model and the bit allocation co-adapt across blocks without model side information. Mantissas are coded by a hybrid…
How Vision Transformers Represent Position: A Mechanistic Comparison of Absolute and Rotary Positional Encodings
Mahmoud Mannes, Nikhil Maturi, Parva Mehta +2
Positional embeddings encode the spatial position of each image patch in a Vision Transformer (ViT), allowing the model to distinguish different spatial arrangements of visual cont…
RaLMPH: Reliability-aware Learning for Multi-Pathologist Harmonization in Whole-Slide Image Classification
Sungrae Hong, Jiwon Jeong, Soeun Cheon +5
Multiple Instance Learning (MIL) is a standard paradigm for Whole-Slide Image (WSI) analysis and has achieved strong results in computational pathology. However, most MIL pipelines…
One Sequential Recommendation Model Pretrained from Synthetic Priors Predicts Multiple Datasets
Woosung Kang, Jiwon Jeong, Jonghyeok Shin +2
Existing sequential recommendation models rely on dataset-specific training, where the learned parameters are fitted to the item catalog and the observed interaction distribution o…
MechELK: A Mechanistic Interpretability Framework for Eliciting Latent Knowledge in Large Language Models
Ji-jun Park, Soo-joon Choi, Jiwon Jeong +2
Large language models (LLMs) frequently encode factual and reasoning knowledge in their internal representations that is not faithfully reflected in their surface-level outputs --…
Information-computation trade-offs in non-linear transforms
Connor Ding, Abhiram Rao Gorle, Jiwon Jeong +2
In this work, we explore the interplay between information and computation in non-linear transform-based compression for broad classes of modern information-processing tasks. We fi…
Universal Discrete Filtering with Lookahead or Delay
Pumiao Yan, Jiwon Jeong, Naomi Sagan +1
We consider the universal discrete filtering problem, where an input sequence generated by an unknown source passes through a discrete memoryless channel, and the goal is to estima…