SeongWan Kim

idgmatrix's activity

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

upvoted 2 papers 15 days ago

GenRecal: Generation after Recalibration from Large to Small Vision-Language Models

Paper • 2506.15681 • Published 17 days ago • 36

Truncated Proximal Policy Optimization

Paper • 2506.15050 • Published 17 days ago • 10

upvoted 3 papers 18 days ago

Discrete Diffusion in Large Language and Multimodal Models: A Survey

Paper • 2506.13759 • Published 19 days ago • 41

Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning

Paper • 2506.10521 • Published 23 days ago • 65

Wait, We Don't Need to "Wait"! Removing Thinking Tokens Improves Reasoning Efficiency

Paper • 2506.08343 • Published 25 days ago • 48

upvoted 3 papers 19 days ago

EmbodiedGen: Towards a Generative 3D World Engine for Embodied Intelligence

Paper • 2506.10600 • Published 23 days ago • 7

PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework

Paper • 2506.10741 • Published 23 days ago • 27

Magistral

Paper • 2506.10910 • Published 23 days ago • 61

upvoted a paper 22 days ago

Time to Talk: LLM Agents for Asynchronous Group Communication in Mafia Games

Paper • 2506.05309 • Published 30 days ago • 14

upvoted 2 papers 23 days ago

SpatialLM: Training Large Language Models for Structured Indoor Modeling

Paper • 2506.07491 • Published 26 days ago • 38

Vision Transformers Don't Need Trained Registers

Paper • 2506.08010 • Published 26 days ago • 20

upvoted a paper 24 days ago

Reinforcement Pre-Training

Paper • 2506.08007 • Published 26 days ago • 240

upvoted a paper 25 days ago

PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

Paper • 2506.05573 • Published 30 days ago • 69

upvoted 5 papers 26 days ago

Audio-Aware Large Language Models as Judges for Speaking Styles

Paper • 2506.05984 • Published 29 days ago • 14

Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation

Paper • 2506.04225 • Published about 1 month ago • 25

Small Language Models are the Future of Agentic AI

Paper • 2506.02153 • Published Jun 2 • 7

Inference-Time Hyper-Scaling with KV Cache Compression

Paper • 2506.05345 • Published 30 days ago • 27

Video World Models with Long-term Spatial Memory

Paper • 2506.05284 • Published 30 days ago • 53

upvoted 2 papers about 1 month ago

Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning

Paper • 2505.24726 • Published May 30 • 258

Differentiable Solver Search for Fast Diffusion Sampling

Paper • 2505.21114 • Published May 27 • 10