SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens
Paper
•
2510.24940
•
Published
•
17
Mingjia Shi
BDeM
AI & ML interests
Federated Learning, Transfer Learning, Multi-modal, Optimization and Generative Model
Recent Activity
upvoted
a
paper
about 2 months ago
SemCoT: Accelerating Chain-of-Thought Reasoning through
Semantically-Aligned Implicit Tokens
liked
a Space
5 months ago
Jerrylz/Drag-and-Drop-LLMs
liked
a model
6 months ago
zzwen/InstabilityZoo
Organizations
upvoted
a
paper
about 2 months ago
liked
a
Space
5 months ago
liked
a
model
6 months ago
authored
3
papers
6 months ago
Communication-efficient Federated Learning with Single-Step Synthetic Features Compressor for Faster Convergence
Paper
•
2302.13562
•
Published
REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
Paper
•
2505.16792
•
Published
Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
Paper
•
2506.16406
•
Published
•
130
upvoted
a
paper
6 months ago
updated
a
model
about 2 years ago