SeongWan Kim

idgmatrix

AI & ML interests

None yet

Recent Activity

upvoted a paper about 14 hours ago

Can LLMs Maintain Fundamental Abilities under KV Cache Compression?

upvoted a paper about 14 hours ago

Demystifying Long Chain-of-Thought Reasoning in LLMs

upvoted a paper 2 days ago

The Differences Between Direct Alignment Algorithms are a Blur

View all activity

Organizations

None yet

idgmatrix's activity

upvoted 2 papers about 14 hours ago

Can LLMs Maintain Fundamental Abilities under KV Cache Compression?

Paper • 2502.01941 • Published 3 days ago • 9

Demystifying Long Chain-of-Thought Reasoning in LLMs

Paper • 2502.03373 • Published 1 day ago • 19

upvoted 2 papers 2 days ago

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published 3 days ago • 105

Process Reinforcement through Implicit Rewards

Paper • 2502.01456 • Published 3 days ago • 53

upvoted a paper 3 days ago

Reward-Guided Speculative Decoding for Efficient LLM Reasoning

Paper • 2501.19324 • Published 6 days ago • 32

upvoted 2 papers 4 days ago

Qwen2.5-1M Technical Report

Paper • 2501.15383 • Published 12 days ago • 54

GuardReasoner: Towards Reasoning-based LLM Safeguards

Paper • 2501.18492 • Published 7 days ago • 78

upvoted 2 papers 7 days ago

SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Paper • 2501.17161 • Published 9 days ago • 100

Optimizing Large Language Model Training Using FP4 Quantization

Paper • 2501.17116 • Published 9 days ago • 32

upvoted 3 papers 14 days ago

Autonomy-of-Experts Models

Paper • 2501.13074 • Published 15 days ago • 40

DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Paper • 2501.12948 • Published 15 days ago • 301

Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation

Paper • 2501.12202 • Published 16 days ago • 33

upvoted a paper 17 days ago

GameFactory: Creating New Games with Generative Interactive Videos

Paper • 2501.08325 • Published 23 days ago • 61

upvoted a paper 18 days ago

Evolving Deeper LLM Thinking

Paper • 2501.09891 • Published 21 days ago • 105

upvoted 2 papers 22 days ago

MangaNinja: Line Art Colorization with Precise Reference Following

Paper • 2501.08332 • Published 23 days ago • 56

Tensor Product Attention Is All You Need

Paper • 2501.06425 • Published 27 days ago • 80

upvoted 3 papers 23 days ago

upvoted a paper 25 days ago

The GAN is dead; long live the GAN! A Modern GAN Baseline

Paper • 2501.05441 • Published 28 days ago • 87