SeongWan Kim's picture

111 3

SeongWan Kim

idgmatrix

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 3 days ago

SurveyX: Academic Survey Automation via Large Language Models

upvoted a paper 8 days ago

Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity

upvoted a paper 8 days ago

Multimodal Mamba: Decoder-only Multimodal State Space Model via Quadratic to Linear Distillation

View all activity

Organizations

None yet

idgmatrix's activity

upvoted a paper 3 days ago

SurveyX: Academic Survey Automation via Large Language Models

Paper • 2502.14776 • Published 8 days ago • 88

upvoted 3 papers 8 days ago

Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity

Paper • 2502.13063 • Published 10 days ago • 62

Multimodal Mamba: Decoder-only Multimodal State Space Model via Quadratic to Linear Distillation

Paper • 2502.13145 • Published 10 days ago • 35

Continuous Diffusion Model for Language Modeling

Paper • 2502.11564 • Published 12 days ago • 49

upvoted a paper 9 days ago

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

Paper • 2502.11079 • Published 12 days ago • 51

upvoted 2 papers 12 days ago

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

Paper • 2502.08946 • Published 16 days ago • 182

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

Paper • 2502.08910 • Published 16 days ago • 142

upvoted a paper 15 days ago

Fino1: On the Transferability of Reasoning Enhanced LLMs to Finance

Paper • 2502.08127 • Published 17 days ago • 49

upvoted 2 papers 16 days ago

TransMLA: Multi-head Latent Attention Is All You Need

Paper • 2502.07864 • Published 17 days ago • 45

Retrieval-augmented Large Language Models for Financial Time Series Forecasting

Paper • 2502.05878 • Published 19 days ago • 38

upvoted 4 papers 17 days ago

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

Paper • 2502.07316 • Published 18 days ago • 45

Competitive Programming with Large Reasoning Models

Paper • 2502.06807 • Published 25 days ago • 64

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

Paper • 2502.05171 • Published 21 days ago • 120

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

Paper • 2502.06703 • Published 18 days ago • 140

upvoted 3 papers 19 days ago

Fast Video Generation with Sliding Tile Attention

Paper • 2502.04507 • Published 22 days ago • 47

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

Paper • 2502.04363 • Published 24 days ago • 11

Goku: Flow Based Video Generative Foundation Models

Paper • 2502.04896 • Published 21 days ago • 90

upvoted 2 papers 23 days ago

Can LLMs Maintain Fundamental Abilities under KV Cache Compression?

Paper • 2502.01941 • Published 25 days ago • 14

Demystifying Long Chain-of-Thought Reasoning in LLMs

Paper • 2502.03373 • Published 23 days ago • 54

upvoted a paper 24 days ago

The Differences Between Direct Alignment Algorithms are a Blur

Paper • 2502.01237 • Published 25 days ago • 111