9 papers
Triggering Generalist Reasoning via Predictive Uncertainty for Dual-System VLA
Hyemin Yang, Wooseong Jeong, Giwon Lee +1
Dual-system Vision-Language-Action (VLA) models improve real-time robotic control by pairing a slow, reasoning-capable generalist with a fast specialist action expert. However, exi…
Label-Free Cross-Task LoRA Merging with Null-Space Compression
Wonyoung Lee, Wooseong Jeong, Kuk-Jin Yoon
Model merging combines independently fine-tuned checkpoints without joint multi-task training. In the era of foundation-model, fine-tuning with Low-Rank Adaptation (LoRA) is preval…
Preference-Aligned LoRA Merging: Preserving Subspace Coverage and Addressing Directional Anisotropy
Wooseong Jeong, Wonyoung Lee, Kuk-Jin Yoon
Merging multiple Low-Rank Adaptation (LoRA) modules is promising for constructing general-purpose systems, yet challenging because LoRA update directions span different subspaces a…
Interaction-Merged Motion Planning: Effectively Leveraging Diverse Motion Datasets for Robust Planning
Giwon Lee, Wooseong Jeong, Daehee Park +2
Motion planning is a crucial component of autonomous robot driving. While various trajectory datasets exist, effectively utilizing them for a target domain remains challenging due…
Synchronizing Task Behavior: Aligning Multiple Tasks during Test-Time Training
Wooseong Jeong, Jegyeong Cho, Youngho Yoon +1
Generalizing neural networks to unseen target domains is a significant challenge in real-world deployments. Test-time training (TTT) addresses this by using an auxiliary self-super…
Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learning
Wooseong Jeong, Kuk-Jin Yoon
Multi-Task Learning (MTL) enables multiple tasks to be learned within a shared network, but differences in objectives across tasks can cause negative transfer, where the learning o…
DC-TTA: Divide-and-Conquer Framework for Test-Time Adaptation of Interactive Segmentation
Jihun Kim, Hoyong Kwon, Hyeokjun Kweon +2
Interactive segmentation (IS) allows users to iteratively refine object boundaries with minimal cues, such as positive and negative clicks. While the Segment Anything Model (SAM) h…
Selective Task Group Updates for Multi-Task Optimization
Wooseong Jeong, Kuk-Jin Yoon
Multi-task learning enables the acquisition of task-generic knowledge by training multiple tasks within a unified architecture. However, training all tasks together in a single arc…
Quantifying Task Priority for Multi-Task Optimization
Wooseong Jeong, Kuk-Jin Yoon
The goal of multi-task learning is to learn diverse tasks within a single unified network. As each task has its own unique objective function, conflicts emerge during training, res…