Seoul National University

university

Verified

https://www.snu.ac.kr/

Activity Feed Request to join this org

AI & ML interests

None defined yet.

Recent Activity

mbkim authored a paper 22 days ago

Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning

williamrhee authored a paper about 1 month ago

TherA: Thermal-Aware Visual-Language Prompting for Controllable RGB-to-Thermal Infrared Translation

williamrhee authored a paper about 1 month ago

TIDY: Thermal Infrared Image Denoising via Wavelet Domain Entropy and Directional Stripe Index

View all activity

Papers

Can Natural Image Autoencoders Compactly Tokenize fMRI Volumes for Long-Range Dynamics Modeling?

Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection

View all Papers

authored a paper 3 days ago

4D Human-Scene Reconstruction from Low-Overlap Captures

Paper • 2607.09125 • Published 14 days ago • 53

published a model 2 months ago

snu/1B-UMoE-1024

submitted a paper to Daily Papers 4 months ago

Can Natural Image Autoencoders Compactly Tokenize fMRI Volumes for Long-Range Dynamics Modeling?

Paper • 2604.03619 • Published Apr 4 • 9

authored a paper 4 months ago

LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents

Paper • 2602.01053 • Published Feb 1 • 8

authored 2 papers 4 months ago

SummDiff: Generative Modeling of Video Summarization with Diffusion

Paper • 2510.08458 • Published Oct 9, 2025 • 1

TripleSumm: Adaptive Triple-Modality Fusion for Video Summarization

Paper • 2603.01169 • Published Mar 1 • 1

authored a paper 5 months ago

RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models

Paper • 2602.17053 • Published Feb 19 • 1

submitted a paper to Daily Papers 6 months ago

LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents

Paper • 2602.01053 • Published Feb 1 • 8

authored a paper 7 months ago

EgoX: Egocentric Video Generation from a Single Exocentric Video

Paper • 2512.08269 • Published Dec 9, 2025 • 124

authored 2 papers 10 months ago

QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models

Paper • 2509.17428 • Published Sep 22, 2025 • 9

L4Q: Parameter Efficient Quantization-Aware Training on Large Language Models via LoRA-wise LSQ

Paper • 2402.04902 • Published Feb 7, 2024 • 5

authored 2 papers about 1 year ago

How to Train Your Fact Verifier: Knowledge Transfer with Multimodal Open Models

Paper • 2407.00369 • Published Jun 29, 2024

Don't Look Only Once: Towards Multimodal Interactive Reasoning with Selective Visual Revisitation

Paper • 2505.18842 • Published May 24, 2025 • 36

authored 3 papers almost 2 years ago

Multi-Level Compositional Reasoning for Interactive Instruction Following

Paper • 2308.09387 • Published Aug 18, 2023

Online Continual Learning For Interactive Instruction Following Agents

Paper • 2403.07548 • Published Mar 12, 2024

Factorizing Perception and Policy for Interactive Instruction Following

Paper • 2012.03208 • Published Dec 6, 2020

authored a paper about 2 years ago

Grokfast: Accelerated Grokking by Amplifying Slow Gradients

Paper • 2405.20233 • Published May 30, 2024 • 7

authored 3 papers over 2 years ago

Rethinking RGB Color Representation for Image Restoration Models

Paper • 2402.03399 • Published Feb 5, 2024 • 1

StreamMultiDiffusion: Real-Time Interactive Generation with Region-Based Semantic Control

Paper • 2403.09055 • Published Mar 14, 2024 • 26

Clean Images are Hard to Reblur: Exploiting the Ill-Posed Inverse Task for Dynamic Scene Deblurring

Paper • 2104.12665 • Published Apr 26, 2021 • 2