Soyeong

starsuzi's activity

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

liked a model 13 days ago

KORMo-Team/KORMo-10B-sft

Text Generation • 11B • Updated 13 days ago • 2.06k • 100

upvoted a paper 13 days ago

KORMo: Korean Open Reasoning Model for Everyone

Paper • 2510.09426 • Published 17 days ago • 72

upvoted a paper 14 days ago

Multimodal Prompt Optimization: Why Not Leverage Multiple Modalities for MLLMs

Paper • 2510.09201 • Published 17 days ago • 46

authored 17 papers 17 days ago

Test-Time Self-Adaptive Small Language Models for Question Answering

Paper • 2310.13307 • Published Oct 20, 2023

Knowledge-Augmented Language Model Verification

Paper • 2310.12836 • Published Oct 19, 2023

Discrete Prompt Optimization via Constrained Generation for Zero-shot Re-ranker

Paper • 2305.13729 • Published May 23, 2023 • 1

Improving Zero-shot Reader by Reducing Distractions from Irrelevant Documents in Open-Domain Question Answering

Paper • 2310.17490 • Published Oct 26, 2023

Unsupervised Document Expansion for Information Retrieval with Stochastic Text Generation

Paper • 2105.00666 • Published May 3, 2021

Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbation

Paper • 2203.07735 • Published Mar 15, 2022

Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity

Paper • 2403.14403 • Published Mar 21, 2024 • 7

CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark

Paper • 2406.05967 • Published Jun 10, 2024 • 6

Self-Knowledge Distillation for Learning Ambiguity

Paper • 2406.09719 • Published Jun 14, 2024

Unified Multi-Modal Interleaved Document Representation for Information Retrieval

Paper • 2410.02729 • Published Oct 3, 2024

EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation

Paper • 2412.12559 • Published Dec 17, 2024 • 2

Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations

Paper • 2404.13948 • Published Apr 22, 2024 • 2

Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding

Paper • 2502.05609 • Published Feb 8 • 19

UniversalRAG: Retrieval-Augmented Generation over Multiple Corpora with Diverse Modalities and Granularities

Paper • 2504.20734 • Published Apr 29 • 61

CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation

Paper • 2505.24456 • Published May 30

PRISM: Fine-Grained Paper-to-Paper Retrieval with Multi-Aspect-Aware Query Optimization

Paper • 2507.10057 • Published Jul 14

When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs

Paper • 2510.07499 • Published 19 days ago • 45