arxiv:2509.25175
Yongliang Shen
tricktreat
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
5 days ago
Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge
upvoted
a
paper
8 days ago
Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning
Organizations
models
25
tricktreat/iChainGPT-Instruct
Updated
tricktreat/ichaingpt
8B
•
Updated
•
10
tricktreat/llama-2-7b-chat-merged-with-llama-2-7b-chat-12layers-T6-25000steps-lora612-hhrlhf
Text Generation
•
7B
•
Updated
•
29
tricktreat/llama-2-7b-chat-merged-with-llama-2-7b-chat-12layers-T6-25000steps-peft-lora-orpo
Text Generation
•
7B
•
Updated
•
26
tricktreat/llama-2-7b-chat-12layers-T6-25000steps-llama-2-7b-chat-12layers-T6-25000steps-peft-lora-orpo
Text Generation
•
3B
•
Updated
•
25
tricktreat/llama-2-7b-chat-12layers-T6-25000steps-llama-2-7b-chat-12layers-T6-25000steps-lora612-hhrlhf
Text Generation
•
3B
•
Updated
•
32
tricktreat/llama-2-7b-chat-12layers-T6-25000steps-llama-2-7b-chat-12layers-T6-25000steps-peft-lora-orpo-2
Text Generation
•
3B
•
Updated
•
24
tricktreat/llama-2-7b-chat-merged-with-llama-2-7b-chat-12layers-T6-25000steps-peft-lora-orpo-2
Text Generation
•
7B
•
Updated
•
20
tricktreat/llama-2-7b-chat-12layers-T6-merged-with-llama-2-7b-chat-peft-lora-orpo
Text Generation
•
3B
•
Updated
•
25
tricktreat/llama-2-7b-chat-merged-with-llama-2-7b-chat-peft-lora-orpo
Text Generation
•
7B
•
Updated
•
14
datasets
0
None public yet