64 citations · 176 across the 23 of their papers we have counts for
23 papers
Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation
Youngrok Park, Sangmin Bae, Hojung Jung +6
Weak-to-strong generalization asks whether stronger models can learn from weaker supervisors and surpass them. This is particularly important for successive model generations and m…
LLM-as-a-Tutor: Policy-Aware Prompt Adaptation for Non-Verifiable RL
Yujin Kim, Namgyu Ho, Sangmin Hwang +7
Reinforcement learning (RL) for non-verifiable instruction following increasingly relies on LLM judges with prompt-specific rubrics as reward signals. While recent methods adapt th…
Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion Drafting
Soowon Oh, Nam Cao, Yujin Kim +4
Block-diffusion drafters have recently emerged as a powerful alternative for speculative decoding by predicting multiple future-token distributions in a single parallel step. Howev…
Temporal Alignment Guidance: On-Manifold Sampling in Diffusion Models
Youngrok Park, Hojung Jung, Sangmin Bae +1
Diffusion models have achieved remarkable success as generative models. However, even a well-trained model can accumulate errors throughout the generation process. These errors bec…
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
Sangmin Bae, Yujin Kim, Reza Bayat +8
Scaling language models unlocks impressive capabilities, but the accompanying computational and memory demands make both training and deployment expensive. Existing efficiency effo…
Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation
Sungnyun Kim, Sungwoo Cho, Sangmin Bae +2
Audio-visual speech recognition (AVSR) incorporates auditory and visual modalities to improve recognition accuracy, particularly in noisy environments where audio-only speech syste…
MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition
Sungnyun Kim, Kangwook Jang, Sangmin Bae +2
Audio-visual speech recognition (AVSR) has become critical for enhancing speech recognition in noisy environments by integrating both auditory and visual modalities. However, exist…
Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA
Sangmin Bae, Adam Fisch, Hrayr Harutyunyan +3
Large language models (LLMs) are expensive to deploy. Parameter sharing offers a possible path towards reducing their size and cost, but its effectiveness in modern LLMs remains fa…
Automated Filtering of Human Feedback Data for Aligning Text-to-Image Diffusion Models
Yongjin Yang, Sihyeon Kim, Hojung Jung +4
Fine-tuning text-to-image diffusion models with human feedback is an effective method for aligning model behavior with human intentions. However, this alignment process often suffe…
VACoDe: Visual Augmented Contrastive Decoding
Sihyeon Kim, Boryeong Cho, Sangmin Bae +2
Despite the astonishing performance of recent Large Vision-Language Models (LVLMs), these models often generate inaccurate responses. To address this issue, previous studies have f…
Learning Video Temporal Dynamics with Cross-Modal Attention for Robust Audio-Visual Speech Recognition
Sungnyun Kim, Kangwook Jang, Sangmin Bae +2
Audio-visual speech recognition (AVSR) aims to transcribe human speech using both audio and video modalities. In practical environments with noise-corrupted audio, the role of vide…
Block Transformer: Global-to-Local Language Modeling for Fast Inference
Namgyu Ho, Sangmin Bae, Taehyeon Kim +6
We introduce the Block Transformer which adopts hierarchical global-to-local modeling to autoregressive transformers to mitigate the inference bottlenecks associated with self-atte…
Fine-tuned In-Context Learning Transformers are Excellent Tabular Data Classifiers
Felix den Breejen, Sangmin Bae, Stephen Cha +1
The recently introduced TabPFN pretrains an In-Context Learning (ICL) transformer on synthetic data to perform tabular data classification. In this work, we extend TabPFN to the fi…
Fine-Tuning the Retrieval Mechanism for Tabular Deep Learning
Felix den Breejen, Sangmin Bae, Stephen Cha +3
While interests in tabular deep learning has significantly grown, conventional tree-based models still outperform deep learning methods. To narrow this performance gap, we explore…
Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding
Sangmin Bae, Jongwoo Ko, Hwanjun Song +1
To tackle the high inference latency exhibited by autoregressive language models, previous studies have proposed an early-exiting framework that allocates adaptive computation path…
Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification
Sangmin Bae, June-Woo Kim, Won-Yang Cho +7
Respiratory sound contains crucial information for the early diagnosis of fatal lung diseases. Since the COVID-19 pandemic, there has been a growing interest in contact-free medica…
Coreset Sampling from Open-Set for Fine-Grained Self-Supervised Learning
Sungnyun Kim, Sangmin Bae, Se-Young Yun
Deep learning in general domains has constantly been extended to domain-specific tasks requiring the recognition of fine-grained characteristics. However, real-world applications f…
Re-thinking Federated Active Learning based on Inter-class Diversity
SangMook Kim, Sangmin Bae, Hwanjun Song +1
Although federated learning has made awe-inspiring advances, most studies have assumed that the client's data are fully labeled. However, in a real-world scenario, every client may…
Self-Contrastive Learning: Single-viewed Supervised Contrastive Framework using Sub-network
Sangmin Bae, Sungnyun Kim, Jongwoo Ko +3
Contrastive loss has significantly improved performance in supervised classification tasks by using a multi-viewed framework that leverages augmentation and label information. The…
Preservation of the Global Knowledge by Not-True Distillation in Federated Learning
Gihun Lee, Minchan Jeong, Yongjin Shin +2
In federated learning, a strong global model is collaboratively learned by aggregating clients' locally trained models. Although this precludes the need to access clients' data dir…
Accurate and Fast Federated Learning via Combinatorial Multi-Armed Bandits
Taehyeon Kim, Sangmin Bae, Jin-woo Lee +1
Federated learning has emerged as an innovative paradigm of collaborative machine learning. Unlike conventional machine learning, a global model is collaboratively learned while da…
MixCo: Mix-up Contrastive Learning for Visual Representation
Sungnyun Kim, Gihun Lee, Sangmin Bae +1
Contrastive learning has shown remarkable results in recent self-supervised approaches for visual representation. By learning to contrast positive pairs' representation from the co…
SIPA: A Simple Framework for Efficient Networks
Gihun Lee, Sangmin Bae, Jaehoon Oh +1
With the success of deep learning in various fields and the advent of numerous Internet of Things (IoT) devices, it is essential to lighten models suitable for low-power devices. I…