613 citations · 1.2k across the 67 of their papers we have counts for
10 papers · 1 filter
What Defines Good Reasoning in LLMs? Dissecting Reasoning Steps with Multi-Aspect Evaluation
Heejin Do, Jaehui Hwang, Dongyoon Han +2
Evaluating large language models (LLMs) on final-answer correctness is the dominant paradigm. This approach, however, provides a coarse signal for model improvement and overlooks t…
RL makes MLLMs see better than SFT
Junha Song, Sangdoo Yun, Dongyoon Han +2
A dominant assumption in Multimodal Language Model (MLLM) research is that its performance is largely inherited from the LLM backbone, given its immense parameter scale and remarka…
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…
Revisiting Reliability in the Reasoning-based Pose Estimation Benchmark
Junsu Kim, Naeun Kim, Jaeho Lee +3
The reasoning-based pose estimation (RPE) benchmark has emerged as a widely adopted evaluation standard for pose-aware multimodal large language models (MLLMs). Despite its signifi…
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…
When Test-Time Adaptation Meets Self-Supervised Models
Jisu Han, Jihee Park, Dongyoon Han +1
Training on test-time data enables deep learning models to adapt to dynamic environmental changes, enhancing their practical applicability. Online adaptation from source to target…
Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation
Min-Seop Kwak, Junho Kim, Sangdoo Yun +4
We introduce a diffusion-based framework that performs aligned novel view image and geometry generation via a warping-and-inpainting methodology. Unlike prior methods that require…
Beyond Synthetic Replays: Turning Diffusion Features into Few-Shot Class-Incremental Learning Knowledge
Junsu Kim, Yunhoe Ku, Dongyoon Han +1
Few-shot class-incremental learning (FSCIL) is challenging due to extremely limited training data while requiring models to acquire new knowledge without catastrophic forgetting. R…
DNNs May Determine Major Properties of Their Outputs Early, with Timing Possibly Driven by Bias
Song Park, Sanghyuk Chun, Byeongho Heo +1
This paper argues that deep neural networks (DNNs) mostly determine their outputs during the early stages of inference, where biases inherent in the model play a crucial role in sh…
Peri-LN: Revisiting Normalization Layer in the Transformer Architecture
Jeonghoon Kim, Byeongchan Lee, Cheonbok Park +7
Selecting a layer normalization (LN) strategy that stabilizes training and speeds convergence in Transformers remains difficult, even for today's large language models (LLM). We pr…