9 papers
Looks the Same, Answers Differently: Flip-Direction Steering for Robust Vision-Language Reasoning
Yeonsung Jung, Joonhyun Jeong, Hoang Pham +4
Vision-language models (VLMs) achieve strong visual reasoning performance, yet subtle changes from routine image capture and processing can alter their reasoning trajectories even…
Co-Evolving Agents: Learning from Failures as Hard Negatives
Yeonsung Jung, Trilok Padhi, Sina Shaham +4
Self-evolving agents improve their performance on long-horizon tasks by learning from their own interactions with an environment. A common approach uses the resulting failed trajec…
Early Timestep Zero-Shot Candidate Selection for Instruction-Guided Image Editing
Joowon Kim, Ziseok Lee, Donghyeon Cho +4
Despite recent advances in diffusion models, achieving reliable image generation and editing remains challenging due to the inherent diversity induced by stochastic noise in the sa…
Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy
Joonhyun Jeong, Seyun Bae, Yeonsung Jung +2
Despite the remarkable versatility of Large Language Models (LLMs) and Multimodal LLMs (MLLMs) to generalize across both language and vision tasks, LLMs and MLLMs have shown vulner…
A Simple Remedy for Dataset Bias via Self-Influence: A Mislabeled Sample Perspective
Yeonsung Jung, Jaeyun Song, June Yong Yang +3
Learning generalized models from biased data is an important undertaking toward fairness in deep learning. To address this issue, recent studies attempt to identify and leverage bi…
Preserve or Modify? Context-Aware Evaluation for Balancing Preservation and Modification in Text-Guided Image Editing
Yoonjeon Kim, Soohyun Ryu, Yeonsung Jung +5
The development of vision-language and generative models has significantly advanced text-guided image editing, which seeks the preservation of core elements in the source image whi…
LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding
Doohyuk Jang, Sihwan Park, June Yong Yang +5
Auto-Regressive (AR) models have recently gained prominence in image generation, often matching or even surpassing the performance of diffusion models. However, one major limitatio…
PruNeRF: Segment-Centric Dataset Pruning via 3D Spatial Consistency
Yeonsung Jung, Heecheol Yun, Joonhyung Park +2
Neural Radiance Fields (NeRF) have shown remarkable performance in learning 3D scenes. However, NeRF exhibits vulnerability when confronted with distractors in the training images…
Fighting Fire with Fire: Contrastive Debiasing without Bias-free Data via Generative Bias-transformation
Yeonsung Jung, Hajin Shim, June Yong Yang +1
Deep neural networks (DNNs), despite their impressive ability to generalize over-capacity networks, often rely heavily on malignant bias as shortcuts instead of task-related inform…