Dongyoon Han

calintz's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 2 papers 18 days ago

RL makes MLLMs see better than SFT

Paper • 2510.16333 • Published 29 days ago • 47

Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs

Paper • 2510.13251 • Published Oct 15 • 12

upvoted a collection 3 months ago

Model Stock

Collection

Model Stock: All we need is just a few fine-tuned models [ECCV 2024] • 4 items • Updated Aug 9 • 1

upvoted 12 papers 4 months ago

LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS

Paper • 2507.07136 • Published Jul 9 • 38

T-LoRA: Single Image Diffusion Model Customization Without Overfitting

Paper • 2507.05964 • Published Jul 8 • 118

Masked Image Modeling via Dynamic Token Morphing

Paper • 2401.00254 • Published Dec 30, 2023 • 2

Deep Pyramidal Residual Networks

Paper • 1610.02915 • Published Oct 10, 2016 • 1

Neglected Free Lunch; Learning Image Classifiers Using Annotation Byproducts

Paper • 2303.17595 • Published Mar 30, 2023 • 2

MaskRIS: Semantic Distortion-aware Data Augmentation for Referring Image Segmentation

Paper • 2411.19067 • Published Nov 28, 2024 • 8

Peri-LN: Revisiting Layer Normalization in the Transformer Architecture

Paper • 2502.02732 • Published Feb 4 • 2

Token Bottleneck: One Token to Remember Dynamics

Paper • 2507.06543 • Published Jul 9 • 20

HyperCLOVA X Technical Report

Paper • 2404.01954 • Published Apr 2, 2024 • 25

DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs

Paper • 2403.19588 • Published Mar 28, 2024 • 4

Token-Supervised Value Models for Enhancing Mathematical Reasoning Capabilities of Large Language Models

Paper • 2407.12863 • Published Jul 12, 2024 • 1

Rethinking Channel Dimensions for Efficient Model Design

Paper • 2007.00992 • Published Jul 2, 2020 • 1

upvoted a paper 9 months ago

Sparse Autoencoders for Scientifically Rigorous Interpretation of Vision Models

Paper • 2502.06755 • Published Feb 10 • 7

upvoted a paper 10 months ago

Qwen2.5-1M Technical Report

Paper • 2501.15383 • Published Jan 26 • 72

upvoted a paper 11 months ago

Tint Your Models Task-wise for Improved Multi-task Model Merging

Paper • 2412.19098 • Published Dec 26, 2024 • 3