SeongWan Kim

idgmatrix's activity

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

upvoted 5 papers 1 day ago

MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models

Paper • 2510.16641 • Published 11 days ago • 4

When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling

Paper • 2510.15346 • Published 12 days ago • 32

RL makes MLLMs see better than SFT

Paper • 2510.16333 • Published 11 days ago • 46

DeepSeek-OCR: Contexts Optical Compression

Paper • 2510.18234 • Published 8 days ago • 63

Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs

Paper • 2510.13251 • Published 14 days ago • 12

upvoted 2 papers 6 days ago

Unified Reinforcement and Imitation Learning for Vision-Language Models

Paper • 2510.19307 • Published 7 days ago • 25

Are they lovers or friends? Evaluating LLMs' Social Reasoning in English and Korean Dialogues

Paper • 2510.19028 • Published 8 days ago • 6

upvoted 2 papers 8 days ago

Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis

Paper • 2411.01156 • Published Nov 2, 2024 • 11

Language Models Model Language

Paper • 2510.12766 • Published 15 days ago • 23

upvoted a paper 9 days ago

Latent Diffusion Model without Variational Autoencoder

Paper • 2510.15301 • Published 12 days ago • 47

upvoted 8 papers 12 days ago

PIG: Physics-Informed Gaussians as Adaptive Parametric Mesh Representations

Paper • 2412.05994 • Published Dec 8, 2024 • 19

Underwater SONAR Image Classification and Analysis using LIME-based Explainable Artificial Intelligence

Paper • 2408.12837 • Published Aug 23, 2024 • 1

Synth-SONAR: Sonar Image Synthesis with Enhanced Diversity and Realism via Dual Diffusion Models and GPT Prompting

Paper • 2410.08612 • Published Oct 11, 2024 • 2

FlashWorld: High-quality 3D Scene Generation within Seconds

Paper • 2510.13678 • Published 14 days ago • 69

TokDrift: When LLM Speaks in Subwords but Code Speaks in Grammar

Paper • 2510.14972 • Published 13 days ago • 29

Large Language Models Do NOT Really Know What They Don't Know

Paper • 2510.09033 • Published 19 days ago • 16

Attention Is All You Need for KV Cache in Diffusion LLMs

Paper • 2510.14973 • Published 13 days ago • 36

BitNet Distillation

Paper • 2510.13998 • Published 14 days ago • 51

upvoted a paper 13 days ago

A Survey of Vibe Coding with Large Language Models

Paper • 2510.12399 • Published 15 days ago • 46

upvoted a paper 14 days ago

Diffusion Transformers with Representation Autoencoders

Paper • 2510.11690 • Published 16 days ago • 160