Scale-wise Distillation of Diffusion Models
Paper • 2503.16397 • Published • 42
xziayro
xziayro
AI & ML interests
None yet
Recent Activity
upvoted a paper about 3 hours ago
Scale-wise Distillation of Diffusion Models liked a model about 3 hours ago
PeiqingYang/MatAnyone2 liked a model 1 day ago
syxbb/SAMA-14BOrganizations
upvoted a paper about 3 hours ago
liked a
model about 3 hours ago
liked a
model 1 day ago
upvoted 2
papers 1 day ago
reactedto DedeProGames's post with 🤗 1 day ago
Post
3717
Can small models program?
Although even if they are reasoning AIs, small AIs cannot create extensive and high-quality code, at least that's what is commonly thought.
We present OrionLLM/NanoCoder-0.6b, an AI with just 600 million parameters based on qwen3-0.6b and trained with the dataset nvidia/OpenCodeReasoning.
While not good at complex code, we observed a significant improvement in code generation (especially in Python code), demonstrating that, when trained correctly, small AIs can, in fact, program.
Although even if they are reasoning AIs, small AIs cannot create extensive and high-quality code, at least that's what is commonly thought.
We present OrionLLM/NanoCoder-0.6b, an AI with just 600 million parameters based on qwen3-0.6b and trained with the dataset nvidia/OpenCodeReasoning.
While not good at complex code, we observed a significant improvement in code generation (especially in Python code), demonstrating that, when trained correctly, small AIs can, in fact, program.
- 2 replies
liked a
model 1 day ago
upvoted a paper 1 day ago
upvoted 4
papers 2 days ago
Mixture-of-Depths Attention
Paper • 2603.15619 • Published • 73
Attention Residuals
Paper • 2603.15031 • Published • 131
LaDe: Unified Multi-Layered Graphic Media Generation and Decomposition
Paper • 2603.17965 • Published • 4
LoST: Level of Semantics Tokenization for 3D Shapes
Paper • 2603.17995 • Published • 21
liked a
model 2 days ago
upvoted a paper 2 days ago
liked a
model 3 days ago
upvoted 3
papers 3 days ago
Recursive Language Models Meet Uncertainty: The Surprising Effectiveness of Self-Reflective Program Search for Long Context
Paper • 2603.15653 • Published • 7
SK-Adapter: Skeleton-Based Structural Control for Native 3D Generation
Paper • 2603.14152 • Published • 6
SegviGen: Repurposing 3D Generative Model for Part Segmentation
Paper • 2603.16869 • Published • 16
liked a
dataset 3 days ago
liked a
Space 4 days ago