zhao yu

Sniper's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

commented 2 papers 30 days ago

A State-Transition Framework for Efficient LLM Reasoning

Paper • 2602.01198 • Published Feb 1 •

1

Difficulty-Estimated Policy Optimization

Paper • 2602.06375 • Published Feb 6 • 1 •

1

New activity in AIDC-AI/Marco-o1 over 1 year ago

Model fails the strawberry test

15

#16 opened over 1 year ago by

Dev68

Try this SYSTEM prompt

2

#15 opened over 1 year ago by

owao

Nice try, but the model is just not what it pretends to be...

👍 4

1

#14 opened over 1 year ago by

MrDevolver

Is this an open research project? May I join it?

👍 3

1

#11 opened over 1 year ago by

witness0411

testing on MGSM in different languages is insightful

👍 1

1

#12 opened over 1 year ago by

Kechen-Li

explain why the performance differs between the En and Zh MGSM

1

#9 opened over 1 year ago by

TonySilva423

This is only a cot-sft version of qwen-instruction model?

#8 opened over 1 year ago by

longddr

Interesting research work. How many languages does this model support?

#7 opened over 1 year ago by

minghaowu

9.11>9.9😅

👍 3

1

#6 opened over 1 year ago by

cydxg

Misleading advertisement as reasoning model

👍 5

8

#5 opened over 1 year ago by

esozbek

More Benchmarks

4

#4 opened over 1 year ago by

PSM24

Can you provide code for inference with MCTS?

👍 6

6

#3 opened over 1 year ago by

sszymczyk

How many 'S' letters are in the word "Mississippi".

👍 2

2

#25 opened over 1 year ago by

jasgeo75

Model only speaks Chinese even when system prompt is in English.

3

#23 opened over 1 year ago by

AppleExpl01t

Update README.md

#26 opened over 1 year ago by

akash98758

Update README.md

#2 opened over 1 year ago by

ariG23498

update

1

#1 opened over 1 year ago by

Andrick