R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing
Paper
•
2505.21600
•
Published
•
68
Zinan Lin
fjxmlzn
AI & ML interests
generative modeling, machine learning, privacy
Recent Activity
authored
a paper
16 days ago
MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation
Models
updated
a model
about 2 months ago
microsoft/distilled_decoding
Organizations
fjxmlzn's activity
upvoted
a
paper
8 days ago
authored
a
paper
16 days ago
updated
a
model
about 2 months ago
published
a
model
about 2 months ago
upvoted
a
paper
3 months ago
upvoted
a
collection
5 months ago
commented
a
paper
5 months ago
upvoted
a
paper
5 months ago
authored
3
papers
6 months ago
ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation
Paper
•
2406.02540
•
Published
•
3
RedCode: Risky Code Execution and Generation Benchmark for Code Agents
Paper
•
2411.07781
•
Published
•
1
GenMAC: Compositional Text-to-Video Generation with Multi-Agent Collaboration
Paper
•
2412.04440
•
Published
•
21
upvoted
a
paper
6 months ago
authored
a
paper
11 months ago
upvoted
a
paper
11 months ago
authored
4
papers
12 months ago
MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization
Paper
•
2405.17873
•
Published
•
3
Differentially Private Synthetic Data via Foundation Model APIs 2: Text
Paper
•
2403.01749
•
Published
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
Paper
•
2309.11765
•
Published
Improving the Training of Rectified Flows
Paper
•
2405.20320
•
Published
•
1
authored
2
papers
about 1 year ago