72 citations · 330 across the 48 of their papers we have counts for
51 papers
When Less Data Favors Smaller Teachers: Rethinking Teacher Capacity and Data Selection for Knowledge Distillation
Minjae Park, Taesun Yeom, Jaeho Lee
Data pruning reduces the training cost of knowledge distillation (KD). However, the preferred teacher capacity changes with the data budget: smaller teachers can outperform larger…
KV-COBRA: KV Cache Compression via Co-Optimized Bit-Rank Allocation
Sihyeon Ha, Jaeho Lee, Yo-Seb Jeon
What limits KV-cache compression at extreme bit-rates? We argue that it is not the choice of compression scheme, but how its budget is allocated across attention heads. Existing me…
Token-Oriented Semantic Communication with Pretrained Vision Transformers
Jiwoong Im, Minwoo Kim, Jaeho Lee +2
Token communications realize the semantic communication principle at the granularity of transformer tokens, providing a promising direction for client--server collaborative inferen…
Learned Image Compression for Vision-Language-Action Models
Hyeonjun Kim, Jegwang Ryu, Sangbeom Ha +4
Vision-language-action (VLA) models increasingly rely on high-frequency multi-camera observations, making visual communication a major bottleneck for real-time robotic control in b…
Multi-frame Restoration for 10 Hz Lissajous Confocal Laser Endomicroscopy
Minhee Lee, Sangyoon Lee, Jiwook Lee +4
Lissajous confocal laser endomicroscopy (CLE) is a promising solution for high-speed in vivo optical biopsy for handheld scenarios. However, Lissajous scanning traces a resonant tr…
Over-Alignment vs Over-Fitting: The Role of Feature Learning Strength in Generalization
Taesun Yeom, Taehyeok Ha, Jaeho Lee
Feature learning strength (FLS), i.e., the inverse of the effective output scaling of a model, plays a critical role in shaping the optimization dynamics of neural nets. While its…
Lost in the Prompt Order: Revealing the Limitations of Causal Attention in Language Models
Hyunjong Ok, Jaeho Lee
Large language models exhibit surprising sensitivity to the structure of the prompt, but the mechanisms underlying this sensitivity remain poorly understood. In this work, we condu…
Understanding the Effects of Distractors on Reasoning Vision-Language Models
Jiyun Bae, Hyunjong Ok, Sangwoo Mo +1
How does irrelevant information (i.e., distractors) affect test-time scaling in vision-language models (VLMs)? Prior work on text-only language models has shown that textual distra…
Neural Weight Compression for Language Models
Jegwang Ryu, Minkyu Kim, Seungjun Shin +3
Efficient compression of language model weights is increasingly critical as model scale and deployment grow. Yet, most existing methods rely on handcrafted transforms and heuristic…
Activation Quantization of Vision Encoders Needs Prefixing Registers
Seunghyeon Kim, Taesun Yeom, Jinho Kim +3
Large pretrained vision encoders are central to multimodal intelligence, powering applications from on-device vision processing to vision-language models. Since these applications…
AuditoryBench++: Can Language Models Understand Auditory Knowledge without Hearing?
Hyunjong Ok, Suho Yoo, Hyeonjun Kim +1
Even without directly hearing sounds, humans can effortlessly reason about auditory properties, such as pitch, loudness, or sound-source associations, drawing on auditory commonsen…
ZIP: An Efficient Zeroth-order Prompt Tuning for Black-box Vision-Language Models
Seonghwan Park, Jaehyeon Jeong, Yongjun Kim +2
Recent studies have introduced various approaches for prompt-tuning black-box vision-language models, referred to as black-box prompt-tuning (BBPT). While BBPT has demonstrated con…
On the Internal Representations of Graph Metanetworks
Taesun Yeom, Jaeho Lee
Weight space learning is an emerging paradigm in the deep learning community. The primary goal of weight space learning is to extract informative features from a set of parameters…
Speculative End-Turn Detector for Efficient Speech Chatbot Assistant
Hyunjong Ok, Suho Yoo, Jaeho Lee
Spoken dialogue systems powered by large language models have demonstrated remarkable abilities in understanding human speech and generating appropriate spoken responses. However,…
Imagine to Hear: Auditory Knowledge Generation can be an Effective Assistant for Language Models
Suho Yoo, Hyunjong Ok, Jaeho Lee
Language models pretrained on text-only corpora often struggle with tasks that require auditory commonsense knowledge. Previous work addresses this problem by augmenting the langua…
Prompt-based Depth Pruning of Large Language Models
Juyun Wee, Minjae Park, Jaeho Lee
Depth pruning aims to reduce the inference cost of a large language model without any hardware-specific complications, by simply removing several less important transformer blocks.…
Fast Training of Sinusoidal Neural Fields via Scaling Initialization
Taesun Yeom, Sangyoon Lee, Jaeho Lee
Neural fields are an emerging paradigm that represent data as continuous functions parameterized by neural networks. Despite many advantages, neural fields often have a high traini…
S2Cap: A Benchmark and a Baseline for Singing Style Captioning
Hyunjong Ok, Jaeho Lee
Singing voices contain much richer information than common voices, including varied vocal and acoustic properties. However, current open-source audio-text datasets for singing voic…
AudioBERT: Audio Knowledge Augmented Language Model
Hyunjong Ok, Suho Yoo, Jaeho Lee
Recent studies have identified that language models, pretrained on text-only datasets, often lack elementary visual knowledge, \textit{e.g.,} colors of everyday objects. Motivated…
Decoding with Limited Teacher Supervision Requires Understanding When to Trust the Teacher
Hyunjong Ok, Jegwang Ryu, Jaeho Lee
How can small-scale large language models (LLMs) efficiently utilize the supervision of LLMs to improve their generative quality? This question has been well studied in scenarios w…
Towards Federated Low-Rank Adaptation of Language Models with Rank Heterogeneity
Yuji Byun, Jaeho Lee
Low-rank adaptation (LoRA) offers an efficient alternative to full-weight adaptation in federated fine-tuning of language models, significantly reducing computational costs. By adj…
Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimization
Sungbin Shin, Wonpyo Park, Jaeho Lee +1
This work suggests fundamentally rethinking the current practice of pruning large language models (LLMs). The way it is done is by divide and conquer: split the model into submodel…
Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization
Seungwoo Son, Wonpyo Park, Woohyun Han +2
Despite recent advances in LLM quantization, activation quantization remains to be challenging due to the activation outliers. Conventional remedies, e.g., mixing precisions for di…
Attention-aware Semantic Communications for Collaborative Inference
Jiwoong Im, Nayoung Kwon, Taewoo Park +3
We propose a communication-efficient collaborative inference framework in the domain of edge inference, focusing on the efficient use of vision transformer (ViT) models. The partit…