SeongWan Kim

idgmatrix's activity

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

upvoted a paper about 18 hours ago

Phantom: Subject-consistent video generation via cross-modal alignment

Paper • 2502.11079 • Published 5 days ago • 46

upvoted 2 papers 4 days ago

The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding

Paper • 2502.08946 • Published 8 days ago • 179

InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU

Paper • 2502.08910 • Published 8 days ago • 136

upvoted a paper 7 days ago

Fino1: On the Transferability of Reasoning Enhanced LLMs to Finance

Paper • 2502.08127 • Published 9 days ago • 48

upvoted 2 papers 8 days ago

TransMLA: Multi-head Latent Attention Is All You Need

Paper • 2502.07864 • Published 9 days ago • 41

Retrieval-augmented Large Language Models for Financial Time Series Forecasting

Paper • 2502.05878 • Published 12 days ago • 38

upvoted 4 papers 9 days ago

CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

Paper • 2502.07316 • Published 10 days ago • 40

Competitive Programming with Large Reasoning Models

Paper • 2502.06807 • Published 17 days ago • 59

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach

Paper • 2502.05171 • Published 13 days ago • 112

Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling

Paper • 2502.06703 • Published 10 days ago • 132

upvoted 3 papers 11 days ago

Fast Video Generation with Sliding Tile Attention

Paper • 2502.04507 • Published 14 days ago • 46

On-device Sora: Enabling Diffusion-Based Text-to-Video Generation for Mobile Devices

Paper • 2502.04363 • Published 16 days ago • 11

Goku: Flow Based Video Generative Foundation Models

Paper • 2502.04896 • Published 13 days ago • 86

upvoted 2 papers 15 days ago

Can LLMs Maintain Fundamental Abilities under KV Cache Compression?

Paper • 2502.01941 • Published 17 days ago • 13

Demystifying Long Chain-of-Thought Reasoning in LLMs

Paper • 2502.03373 • Published 15 days ago • 51

upvoted 2 papers 16 days ago

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published 18 days ago • 111

Process Reinforcement through Implicit Rewards

Paper • 2502.01456 • Published 17 days ago • 54

upvoted 3 papers 18 days ago

Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Paper • 2501.19324 • Published 20 days ago • 37

Qwen2.5-1M Technical Report

Paper • 2501.15383 • Published 26 days ago • 61

GuardReasoner: Towards Reasoning-based LLM Safeguards

Paper • 2501.18492 • Published 21 days ago • 81