1 citations · 2 across the 10 of their papers we have counts for
15 papers
Omni-Modal LLMs Know More Than They Say
Na Min An, Taekyung Kim, Jaemyung Yu +2
Omni-modal large language models (Omni-LLMs) extend LLMs to process heterogeneous modalities (e.g., vision, audio, and IMU signals) alongside language, enabling a broader range of…
Learning Transferable World-Action Models from Task-Paired Human Videos
Jeongeun Park, Taekyung Kim, Dongyoon Han +1
World-action models inherit broad visual and physical priors from video pre-training. However, standard within-video next-frame prediction allows them to rely on appearance shared…
Cognitive Schemas, Laws and Tasks
Antal Jakovác, András Telcs
This paper asks how explicit representations can support reusable cognitive schemas in knowledge-based problem solving. We develop a structural framework in which schemas are organ…
Isotropic Embedding Perturbations for Robust Vision Language Encoders
Hyesong Choi, Daeun Kim, Song Park +5
Data augmentation is fundamental to training modern deep vision and multimodal models. While individual methods, such as RandAug, CutMix, Mixup, RandErase, and DropPath, offer stro…
Beneath the Surface of Chains-of-Thought: A Mechanistic Interpretation of Reasoning Operations in LLMs
Seogyeong Jeong, Jaehui Hwang, Dongyoon Han +3
Reasoning in large language models unfolds through diverse functional operations, such as problem formulation, goal decomposition, and deduction. Although these operations are expl…
Retrieve, Don't Retrain: Extending Vision Language Action Models to New Tasks at Test Time
Jeongeun Park, Juhan Park, Taekyung Kim +3
Extending a vision-language-action (VLA) policy to a new task typically requires task-specific teleoperated demonstrations and per-task fine-tuning, making adaptation costly in bot…
MuCo: Multi-turn Contrastive Learning for Multimodal Embedding Model
Geonmo Gu, Byeongho Heo, Jaemyung Yu +7
Universal Multimodal embedding models built on Multimodal Large Language Models (MLLMs) have traditionally employed contrastive learning, which aligns representations of query-targ…
VisualScratchpad: Inference-time Visual Concepts Analysis in Vision Language Models
Hyesu Lim, Jinho Choi, Taekyung Kim +3
High-performing vision language models still produce incorrect answers, yet their failure modes are often difficult to explain. To make model internals more accessible and enable s…
Is Your Safe Controller Actually Safe? A Critical Review of CBF Tautologies and Hidden Assumptions
Taekyung Kim
This tutorial provides a critical review of the practical application of Control Barrier Functions (CBFs) in robotic safety. While the theoretical foundations of CBFs are well-esta…
Exploring Conditions for Diffusion models in Robotic Control
Heeseong Shin, Byeongho Heo, Dongyoon Han +2
While pre-trained visual representations have significantly advanced imitation learning, they are often task-agnostic as they remain frozen during policy learning. In this work, we…
Token Bottleneck: One Token to Remember Dynamics
Taekyung Kim, Dongyoon Han, Byeongho Heo +2
Deriving compact and temporally aware visual representations from dynamic scenes is essential for successful execution of sequential scene understanding tasks such as visual tracki…
HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts
Wonjae Kim, Sanghyuk Chun, Taekyung Kim +2
In an era where the volume of data drives the effectiveness of self-supervised learning, the specificity and clarity of data semantics play a crucial role in model training. Addres…
Leveraging Temporal Contextualization for Video Action Recognition
Minji Kim, Dongyoon Han, Taekyung Kim +1
We propose a novel framework for video understanding, called Temporally Contextualized CLIP (TC-CLIP), which leverages essential temporal information through global interactions in…
Morphing Tokens Draw Strong Masked Image Models
Taekyung Kim, Byeongho Heo, Dongyoon Han
Masked image modeling (MIM) has emerged as a promising approach for pre-training Vision Transformers (ViTs). MIMs predict masked tokens token-wise to recover target signals that ar…
Learning with Unmasked Tokens Drives Stronger Vision Learners
Taekyung Kim, Sanghyuk Chun, Byeongho Heo +1
Masked image modeling (MIM) has become a leading self-supervised learning strategy. MIMs such as Masked Autoencoder (MAE) learn strong representations by randomly masking input tok…