Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
Paper
• 2602.11858 • Published
• 59
Matthew
PureMattness
·
AI & ML interests
Blockchain Development, Decentralized Physical Infrastructure, IOT, DAO, NFT, Generative Stereography, Generative Music.
Recent Activity
liked
a model 5 days ago
NousResearch/moe-10b-a1b-8k-wsd-lr3e4-1t liked
a model 5 days ago
sarvamai/sarvam-30b liked
a model 5 days ago
sarvamai/sarvam-105b Organizations
None yet
upvoted a paper 7 days ago
upvoted a collection 16 days ago
upvoted a collection about 2 months ago
upvoted a paper 2 months ago
upvoted 5 papers 4 months ago
Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance
Paper
• 2511.13254 • Published
• 136
UI2Code^N: A Visual Language Model for Test-Time Scalable Interactive UI-to-Code Generation
Paper
• 2511.08195 • Published
• 34
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
Paper
• 2511.06221 • Published
• 132
Kimi Linear: An Expressive, Efficient Attention Architecture
Paper
• 2510.26692 • Published
• 128
Scaling Latent Reasoning via Looped Language Models
Paper
• 2510.25741 • Published
• 229