5 papers
Beyond the Mean: Three-Axis Fidelity for Aligning LLM-Based Survey Simulators from Small Pilot Data
Eun Cheol Choi, Youngrae Kim, Prabhu Pugalenthi +2
Large language models (LLMs) are increasingly used to simulate social survey responses, yet their outputs exhibit systematic biases: marginal distributions are skewed, response var…
Locality-Aware Redundancy Pruning for LLM Depth Compression
Vincent-Daniel Yun, Youngrae Kim, Woosang Lim +3
Large language models are known to contain representational redundancy across network depth, making depth pruning an effective approach for improving inference efficiency. Existing…
Rethinking Layer Redundancy: Calibration Matters More Than Search in LLM Depth Pruning
Minkyu Kim, Vincent-Daniel Yun, Youngrae Kim +3
Depth pruning improves the inference efficiency of large language models by removing Transformer blocks. Prior work typically treats layer redundancy as an inherent structural prop…
MemRoPE: Training-Free Infinite Video Generation via Evolving Memory Tokens
Youngrae Kim, Qixin Hu, C. -C. Jay Kuo +1
Autoregressive diffusion enables real-time frame streaming, yet existing sliding-window caches discard past context, causing fidelity degradation, identity drift, and motion stagna…
Feature Augmentation based Test-Time Adaptation
Younggeol Cho, Youngrae Kim, Junho Yoon +2
Test-time adaptation (TTA) allows a model to be adapted to an unseen domain without accessing the source data. Due to the nature of practical environments, TTA has a limited amount…