6 citations · 14 across the 13 of their papers we have counts for
13 papers
Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniques
Daehoon Gwak, Minhyung Lee, Junwoo Park +1
Diffusion large language models (dLLMs) offer a theoretical advantage in parallel generation over standard autoregressive models. However, parallel generation alone does not guaran…
Not the Example, but the Process: How Self-Generated Examples Enhance LLM Reasoning
Daehoon Gwak, Minseo Jung, Junwoo Park +4
Recent studies have shown that Large Language Models (LLMs) can improve their reasoning performance through self-generated few-shot examples, achieving results comparable to manual…
Reward-Weighted Sampling: Enhancing Non-Autoregressive Characteristics in Masked Diffusion LLMs
Daehoon Gwak, Minseo Jung, Junwoo Park +4
Masked diffusion models (MDMs) offer a promising non-autoregressive alternative for large language modeling. Standard decoding methods for MDMs, such as confidence-based sampling,…
Uncertainty-aware Accurate Elevation Modeling for Off-road Navigation via Neural Processes
Sanghun Jung, Daehoon Gwak, Byron Boots +1
Terrain elevation modeling for off-road navigation aims to accurately estimate changes in terrain geometry in real-time and quantify the corresponding uncertainties. Having precise…
Revisiting LLMs as Zero-Shot Time-Series Forecasters: Small Noise Can Break Large Models
Junwoo Park, Hyuck Lee, Dohyun Lee +2
Large Language Models (LLMs) have shown remarkable performance across diverse tasks without domain-specific training, fueling interest in their potential for time-series forecastin…
Forecasting Future International Events: A Reliable Dataset for Text-Based Event Modeling
Daehoon Gwak, Junwoo Park, Minho Park +4
Predicting future international events from textual information, such as news articles, has tremendous potential for applications in global policy, strategic decision-making, and g…
Self-Supervised Contrastive Learning for Long-term Forecasting
Junwoo Park, Daehoon Gwak, Jaegul Choo +1
Long-term forecasting presents unique challenges due to the time and memory complexity of handling long sequences. Existing methods, which rely on sliding windows to process long s…
PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning
Hojoon Lee, Hanseul Cho, Hyunseung Kim +5
In Reinforcement Learning (RL), enhancing sample efficiency is crucial, particularly in scenarios when data acquisition is costly and risky. In principle, off-policy RL algorithms…
Conditional Generation of Periodic Signals with Fourier-Based Decoder
Jiyoung Lee, Wonjae Kim, Daehoon Gwak +1
Periodic signals play an important role in daily lives. Although conventional sequential models have shown remarkable success in various fields, they still come short in modeling p…
Natural Attribute-based Shift Detection
Jeonghoon Park, Jimin Hong, Radhika Dua +4
Despite the impressive performance of deep networks in vision, language, and healthcare, unpredictable behaviors on samples from the distribution different than the training distri…
Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation
Sanghun Jung, Jungsoo Lee, Daehoon Gwak +2
Identifying unexpected objects on roads in semantic segmentation (e.g., identifying dogs on roads) is crucial in safety-critical applications. Existing approaches use images of une…
Evaluation of Out-of-Distribution Detection Performance of Self-Supervised Learning in a Controllable Environment
Jeonghoon Park, Kyungmin Jo, Daehoon Gwak +3
We evaluate the out-of-distribution (OOD) detection performance of self-supervised learning (SSL) techniques with a new evaluation framework. Unlike the previous evaluation methods…
Neural Ordinary Differential Equations for Intervention Modeling
Daehoon Gwak, Gyuhyeon Sim, Michael Poli +3
By interpreting the forward dynamics of the latent representation of neural networks as an ordinary differential equation, Neural Ordinary Differential Equation (Neural ODE) emerge…