5 papers
SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem
Soohyun Ryu, Sohee Kim, Eunho Yang
Large Vision-Language Models (LVLMs) have achieved strong performance on diverse visual tasks, yet their ability to reconstruct and reason about the 3D structure of the scene depic…
Discounted Beta-Bernoulli Reward Estimation for Sample-Efficient Reinforcement Learning with Verifiable Rewards
Haechan Kim, Soohyun Ryu, Gyouk Chu +2
Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective post-training paradigm for improving the reasoning capabilities of large language models. However,…
Unveiling the Response of Large Vision-Language Models to Visually Absent Tokens
Sohee Kim, Soohyun Ryu, Joonhyung Park +1
Large Vision-Language Models (LVLMs) generate contextually relevant responses by jointly interpreting visual and textual inputs. However, our finding reveals they often mistakenly…
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…
TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
Sanghyun Jo, Soohyun Ryu, Sungyub Kim +2
We identify a critical bias in contemporary CLIP-based models, which we denote as single tag bias. This bias manifests as a disproportionate focus on a singular tag (word) while ne…