Blanc Swan PRO

blancsw

https://www.infomaniak.com

swan-blanc-no-code-team

AI & ML interests

ChatBot

Recent Activity

upvoted a paper 3 days ago

VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training

upvoted a paper 3 days ago

Does Your Reasoning Model Implicitly Know When to Stop Thinking?

upvoted a paper 8 days ago

Less is Enough: Synthesizing Diverse Data in Feature Space of LLMs

View all activity

Organizations

Collections 3

View 3 collections

models 3

datasets 2

blancsw/oasst2_top1_chat_format

Viewer • Updated Jan 23, 2024 • 10.7k • 55 • 12

blancsw/oa_dolly_15k_multilingual

Viewer • Updated Aug 9, 2023 • 60.1k • 9 • 1

Blanc Swan PRO

AI & ML interests

Recent Activity

Organizations

Collections 3

Qwen/Qwen3-VL-30B-A3B-Thinking

Qwen/Qwen3-Next-80B-A3B-Thinking

Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning

lmarena-ai/arena-human-preference-140k

lmarena-ai/arena-expert-5k

nvidia/ToolScale

ytz20/LMSYS-Chat-GPT-5-Chat-Response

Qwen/Qwen3-VL-30B-A3B-Thinking

Qwen/Qwen3-Next-80B-A3B-Thinking

Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning

lmarena-ai/arena-human-preference-140k

lmarena-ai/arena-expert-5k

nvidia/ToolScale

ytz20/LMSYS-Chat-GPT-5-Chat-Response

models 3

blancsw/Pelliculum-Chatbot

blancsw/SmolLM2-135M-Instruct-structure-output

blancsw/lang-detection

datasets 2

blancsw/oasst2_top1_chat_format

blancsw/oa_dolly_15k_multilingual

Blanc Swan PRO

AI & ML interests

Recent Activity

Organizations

Collections 3

models 3 Sort: Recently updated

datasets 2 Sort: Recently updated

models 3

datasets 2