When it rains, it pours.
Baichuan releases Baichuan-Omni-1.5
Open-source Omni-modal Foundation Model Supporting Text, Image, Video, and Audio Inputs as Well as Text and Audio Outputs.
Both model ( huggingface.co/baichuan-inc... ) and base ( huggingface.co/baichuan-inc... ).
Baichuan releases Baichuan-Omni-1.5
Open-source Omni-modal Foundation Model Supporting Text, Image, Video, and Audio Inputs as Well as Text and Audio Outputs.
Both model ( huggingface.co/baichuan-inc... ) and base ( huggingface.co/baichuan-inc... ).
January 26, 2025 at 9:14 PM
When it rains, it pours.
Baichuan releases Baichuan-Omni-1.5
Open-source Omni-modal Foundation Model Supporting Text, Image, Video, and Audio Inputs as Well as Text and Audio Outputs.
Both model ( huggingface.co/baichuan-inc... ) and base ( huggingface.co/baichuan-inc... ).
Baichuan releases Baichuan-Omni-1.5
Open-source Omni-modal Foundation Model Supporting Text, Image, Video, and Audio Inputs as Well as Text and Audio Outputs.
Both model ( huggingface.co/baichuan-inc... ) and base ( huggingface.co/baichuan-inc... ).
The DeepSeek competitors in China racing to make the next big breakthrough in AI, defying US export controls
Startups like Moonshot, Zhipu, MiniMax, StepFun, 01 ai and Baichuan are focusing on improving compute efficiency
tinyurl.com/5exjeb97
@bloomberg.com
#AI
Startups like Moonshot, Zhipu, MiniMax, StepFun, 01 ai and Baichuan are focusing on improving compute efficiency
tinyurl.com/5exjeb97
@bloomberg.com
#AI
February 6, 2025 at 3:41 AM
The DeepSeek competitors in China racing to make the next big breakthrough in AI, defying US export controls
Startups like Moonshot, Zhipu, MiniMax, StepFun, 01 ai and Baichuan are focusing on improving compute efficiency
tinyurl.com/5exjeb97
@bloomberg.com
#AI
Startups like Moonshot, Zhipu, MiniMax, StepFun, 01 ai and Baichuan are focusing on improving compute efficiency
tinyurl.com/5exjeb97
@bloomberg.com
#AI
Researchers at Baichuan Inc. have unveiled a novel attention mechanism called KV Shifting Attention. Detailed in their paper "KV Shifting Attention Enhances Language Modeling", this method fundamentally rethinks how transformers handle induction tasks.
www.linkedin.com/pulse/revolu...
#ai #llm
www.linkedin.com/pulse/revolu...
#ai #llm
Revolutionizing Language Models with KV Shifting Attention
Researchers at Baichuan Inc. have unveiled a novel attention mechanism called KV Shifting Attention.
www.linkedin.com
December 2, 2024 at 2:19 PM
Researchers at Baichuan Inc. have unveiled a novel attention mechanism called KV Shifting Attention. Detailed in their paper "KV Shifting Attention Enhances Language Modeling", this method fundamentally rethinks how transformers handle induction tasks.
www.linkedin.com/pulse/revolu...
#ai #llm
www.linkedin.com/pulse/revolu...
#ai #llm
surprising deepseek isn't on there, and baichuan is
July 13, 2026 at 9:22 PM
surprising deepseek isn't on there, and baichuan is
Found a new (multilingual) model that shared checkpoints, wanted to celebrate it together with you
baichuan-inc/Baichuan2-7B-Intermediate-Checkpoints
(others are Olmo, the llm360 ones, pythia all in github.com/borgr/ColPret as they also shared losses)
baichuan-inc/Baichuan2-7B-Intermediate-Checkpoints
(others are Olmo, the llm360 ones, pythia all in github.com/borgr/ColPret as they also shared losses)
GitHub - borgr/ColPret: Efficient Scaling laws and collaborative pretraining.
Efficient Scaling laws and collaborative pretraining. - borgr/ColPret
github.com
December 14, 2024 at 12:01 PM
Found a new (multilingual) model that shared checkpoints, wanted to celebrate it together with you
baichuan-inc/Baichuan2-7B-Intermediate-Checkpoints
(others are Olmo, the llm360 ones, pythia all in github.com/borgr/ColPret as they also shared losses)
baichuan-inc/Baichuan2-7B-Intermediate-Checkpoints
(others are Olmo, the llm360 ones, pythia all in github.com/borgr/ColPret as they also shared losses)
Baichuan Li, Jayanaka Dantanarayana, Savini Kashmira, Lingjia Tang, Jason Mars: Automated Prefetching for Object Spatial Programming Using Temporal Trace Graphs https://arxiv.org/abs/2609.38439 https://arxiv.org/pdf/2609.38439 https://arxiv.org/html/2609.38439
October 1, 2026 at 6:40 AM
Baichuan Li, Jayanaka Dantanarayana, Savini Kashmira, Lingjia Tang, Jason Mars: Automated Prefetching for Object Spatial Programming Using Temporal Trace Graphs https://arxiv.org/abs/2609.38439 https://arxiv.org/pdf/2609.38439 https://arxiv.org/html/2609.38439
Delicious new Promethion-powered science from Baichuan Deng & colleagues at the South China Agricultural University in lovely Guangzhou, China- by affecting the gut microbiota, gallic acid upmodulates eWAT & BAT, thus alleviating obesity! 🧪 www.sciencedirect.com/science/arti...
Gallic acid prevents obesity in mice on a high-fat diet via the gut microbiota-adipose tissue axis
Obesity is closely related to the gut microbiota, and gallic acid (GA) has anti-obesity properties, but its relationship with the gut microbiota is un…
www.sciencedirect.com
May 18, 2025 at 4:41 PM
Delicious new Promethion-powered science from Baichuan Deng & colleagues at the South China Agricultural University in lovely Guangzhou, China- by affecting the gut microbiota, gallic acid upmodulates eWAT & BAT, thus alleviating obesity! 🧪 www.sciencedirect.com/science/arti...
Historical romance webdrama #ReincarnatedLove, starring #ZhaoYiqin, #HuYiyao, #BaiChuan and more, holds filming ceremony.
#临安若梦
#临安若梦
July 27, 2025 at 3:00 PM
Historical romance webdrama #ReincarnatedLove, starring #ZhaoYiqin, #HuYiyao, #BaiChuan and more, holds filming ceremony.
#临安若梦
#临安若梦
China’s selective push for open-weight models (e.g., *Qwen*, *Baichuan*) doesn’t equate to systemic adoption—*OpenPhilanthropy* links data access to capability, not architecture.
🤝
Fuente: CBS News
🔗
https://www.cbsnews.com/news/open-weight-ai-models-safety-risks/
🤝
Fuente: CBS News
🔗
https://www.cbsnews.com/news/open-weight-ai-models-safety-risks/
October 2, 2026 at 6:49 PM
China’s selective push for open-weight models (e.g., *Qwen*, *Baichuan*) doesn’t equate to systemic adoption—*OpenPhilanthropy* links data access to capability, not architecture.
🤝
Fuente: CBS News
🔗
https://www.cbsnews.com/news/open-weight-ai-models-safety-risks/
🤝
Fuente: CBS News
🔗
https://www.cbsnews.com/news/open-weight-ai-models-safety-risks/
El titular confunde "open-weight models" (modelos con pesos abiertos) con "open-weight AI" (IA con pesos abiertos), término no estandarizado. China promueve modelos con pesos accesibles (ej. *Qwen*, *Baichuan*), pero no existe un "abrazar" masivo de esta modalidad: son iniciativas ...
October 2, 2026 at 6:49 PM
El titular confunde "open-weight models" (modelos con pesos abiertos) con "open-weight AI" (IA con pesos abiertos), término no estandarizado. China promueve modelos con pesos accesibles (ej. *Qwen*, *Baichuan*), pero no existe un "abrazar" masivo de esta modalidad: son iniciativas ...
Zihao Zheng, Jiayu Long, Baichuan Li, Junyi Yao: Stale Does Not Mean Unsafe: Guard Precision for Tool-Using LLM Agents under Infrastructure State Races https://arxiv.org/abs/2609.29522 https://arxiv.org/pdf/2609.29522 https://arxiv.org/html/2609.29522
September 25, 2026 at 6:39 AM
Zihao Zheng, Jiayu Long, Baichuan Li, Junyi Yao: Stale Does Not Mean Unsafe: Guard Precision for Tool-Using LLM Agents under Infrastructure State Races https://arxiv.org/abs/2609.29522 https://arxiv.org/pdf/2609.29522 https://arxiv.org/html/2609.29522
can someone familiar with Chinese AI space map
Moonshot AI/Baichuan/MiniMax/Ziphu AI vs DeepSeek/Qwen for me? What about InternLM?
I know models/papers but I have no sense of relative scale of companies 🙏
Moonshot AI/Baichuan/MiniMax/Ziphu AI vs DeepSeek/Qwen for me? What about InternLM?
I know models/papers but I have no sense of relative scale of companies 🙏
January 20, 2025 at 10:46 PM
can someone familiar with Chinese AI space map
Moonshot AI/Baichuan/MiniMax/Ziphu AI vs DeepSeek/Qwen for me? What about InternLM?
I know models/papers but I have no sense of relative scale of companies 🙏
Moonshot AI/Baichuan/MiniMax/Ziphu AI vs DeepSeek/Qwen for me? What about InternLM?
I know models/papers but I have no sense of relative scale of companies 🙏
Baichuan is making big moves today 🔥
✨ Released Baichuan-M1-14B Medical LLM on the hub
Model:
huggingface.co/baichuan-inc...
huggingface.co/baichuan-inc...
✨ Launched All-Scenario Reasoning Model with medical expertise as one of its key highlights.
ying.baichuan-ai.com/chat
✨ Released Baichuan-M1-14B Medical LLM on the hub
Model:
huggingface.co/baichuan-inc...
huggingface.co/baichuan-inc...
✨ Launched All-Scenario Reasoning Model with medical expertise as one of its key highlights.
ying.baichuan-ai.com/chat
baichuan-inc/Baichuan-M1-14B-Base · Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
January 24, 2025 at 2:09 PM
Baichuan is making big moves today 🔥
✨ Released Baichuan-M1-14B Medical LLM on the hub
Model:
huggingface.co/baichuan-inc...
huggingface.co/baichuan-inc...
✨ Launched All-Scenario Reasoning Model with medical expertise as one of its key highlights.
ying.baichuan-ai.com/chat
✨ Released Baichuan-M1-14B Medical LLM on the hub
Model:
huggingface.co/baichuan-inc...
huggingface.co/baichuan-inc...
✨ Launched All-Scenario Reasoning Model with medical expertise as one of its key highlights.
ying.baichuan-ai.com/chat
oh i think it's 大模型六小虎 which are Zhipu AI, Moonshot AI, MiniMax, Baichuan Intelligence, StepFun, and 01.AI
July 13, 2026 at 9:22 PM
oh i think it's 大模型六小虎 which are Zhipu AI, Moonshot AI, MiniMax, Baichuan Intelligence, StepFun, and 01.AI
Reinforcement learning for retrieval-augmented reasoning 🚀
Baichuan introduces ReSearch, an RL framework that teaches LLMs to reason with search from scratch
Outperforms RAG baselines
No supervised data on reasoning steps
Simple & generalizable
Trending #1 on alphaXiv 📈
Baichuan introduces ReSearch, an RL framework that teaches LLMs to reason with search from scratch
Outperforms RAG baselines
No supervised data on reasoning steps
Simple & generalizable
Trending #1 on alphaXiv 📈
March 31, 2025 at 5:54 PM
Reinforcement learning for retrieval-augmented reasoning 🚀
Baichuan introduces ReSearch, an RL framework that teaches LLMs to reason with search from scratch
Outperforms RAG baselines
No supervised data on reasoning steps
Simple & generalizable
Trending #1 on alphaXiv 📈
Baichuan introduces ReSearch, an RL framework that teaches LLMs to reason with search from scratch
Outperforms RAG baselines
No supervised data on reasoning steps
Simple & generalizable
Trending #1 on alphaXiv 📈
📦 hiyouga / LLaMA-Efficient-Tuning
⭐ 4,655 (+37)
🗒 Python
Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)
⭐ 4,655 (+37)
🗒 Python
Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)
GitHub - hiyouga/LLaMA-Efficient-Tuning: Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)
Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2) - GitHub - hiyouga/LLaMA-Efficient-Tuning: Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Ba...
github.com
October 8, 2023 at 2:50 PM
📦 hiyouga / LLaMA-Efficient-Tuning
⭐ 4,655 (+37)
🗒 Python
Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)
⭐ 4,655 (+37)
🗒 Python
Easy-to-use LLM fine-tuning framework (LLaMA-2, BLOOM, Falcon, Baichuan, Qwen, ChatGLM2)
cover compare
two different copies of same 1936 edition of Luye xianzong 綠野仙蹤 (mid 18th C.), by Li Baichuan 李百川
🀄📚
two different copies of same 1936 edition of Luye xianzong 綠野仙蹤 (mid 18th C.), by Li Baichuan 李百川
🀄📚
January 31, 2025 at 4:58 PM
cover compare
two different copies of same 1936 edition of Luye xianzong 綠野仙蹤 (mid 18th C.), by Li Baichuan 李百川
🀄📚
two different copies of same 1936 edition of Luye xianzong 綠野仙蹤 (mid 18th C.), by Li Baichuan 李百川
🀄📚
「📸 | Yu Zheng anuncia o ator novato recém-contratado pela Huanyu e criador de conteúdo de hanfu/cultura tradicional #BaiChuan como protagonista masculino de seu novo curta-metragem #LuckyStrike
December 2, 2024 at 12:50 PM
「📸 | Yu Zheng anuncia o ator novato recém-contratado pela Huanyu e criador de conteúdo de hanfu/cultura tradicional #BaiChuan como protagonista masculino de seu novo curta-metragem #LuckyStrike
「📸 | Yu Zheng revelou novos pôsteres anunciando elenco de seu novo drama curto histórico #LuckyStrike. Os protagonistas serão #WuJiayi e #BaiChuan, acompanhados por um elenco que inclui #LiuQing, #ShuTong, #SunJingjing, #XuMengyuan e #TengZewen ... +
#吉天照
#吉天照
December 17, 2024 at 3:16 AM
「📸 | Yu Zheng revelou novos pôsteres anunciando elenco de seu novo drama curto histórico #LuckyStrike. Os protagonistas serão #WuJiayi e #BaiChuan, acompanhados por um elenco que inclui #LiuQing, #ShuTong, #SunJingjing, #XuMengyuan e #TengZewen ... +
#吉天照
#吉天照
Check out the @JMaterChem A issue 12 back cover featuring a Review by Baichuan Cui and Jijian Xu titled Enabling rational electrolyte design for lithium batteries through precise descriptors: progress and future perspectives
Read the Review here: doi.org/10.1039/D4TA...
Read the Review here: doi.org/10.1039/D4TA...
March 20, 2025 at 3:29 PM
Check out the @JMaterChem A issue 12 back cover featuring a Review by Baichuan Cui and Jijian Xu titled Enabling rational electrolyte design for lithium batteries through precise descriptors: progress and future perspectives
Read the Review here: doi.org/10.1039/D4TA...
Read the Review here: doi.org/10.1039/D4TA...
From ChatGPT Healthcare to Claude for healthcare, AI in medicine is speeding up🚀
Now BaichuanAI joins with Baichuan-M3 🏥 open medical LLM trained for clinical decision-making
huggingface.co/collections/...
✨ 235B - Apache2.0
✨ Lower hallucinations via Fact-Aware RL
✨ Built for long medical chats
Now BaichuanAI joins with Baichuan-M3 🏥 open medical LLM trained for clinical decision-making
huggingface.co/collections/...
✨ 235B - Apache2.0
✨ Lower hallucinations via Fact-Aware RL
✨ Built for long medical chats
Baichuan-M3 - a baichuan-inc Collection
Modeling Clinical Inquiry for Reliable Medical Decision-Making
huggingface.co
January 13, 2026 at 1:22 PM
From ChatGPT Healthcare to Claude for healthcare, AI in medicine is speeding up🚀
Now BaichuanAI joins with Baichuan-M3 🏥 open medical LLM trained for clinical decision-making
huggingface.co/collections/...
✨ 235B - Apache2.0
✨ Lower hallucinations via Fact-Aware RL
✨ Built for long medical chats
Now BaichuanAI joins with Baichuan-M3 🏥 open medical LLM trained for clinical decision-making
huggingface.co/collections/...
✨ 235B - Apache2.0
✨ Lower hallucinations via Fact-Aware RL
✨ Built for long medical chats
Les chercheurs ont constaté que les modèles chinois (BaiChuan, DeepSeek et ChatGLM) étaient plus enclins à refuser de répondre ou à fournir des informations inexactes sur des sujets tels que le statut de Taïwan, les minorités ethniques ou les militants pro-démocratie
Les chatbots chinois basés sur l’IA se rendent coupables de censure sur des sujets politiquement sensibles #chatbots #IA #censure #Chine #politique
Les chatbots chinois basés sur l’IA se rendent coupables de censure sur des sujets politiquement sensibles
Principaux renseignements Une étude récente publiée dans PNAS Nexus révèle une différence significative dans la manière dont les chatbots chinois et non chinois répondent aux questions politiquement sensibles. Les chercheurs ont constaté que les modèles chinois, notamment BaiChuan, DeepSeek et ChatGLM, étaient plus enclins à refuser de répondre ou à fournir des informations inexactes lorsqu’ils […]
fr.businessam.be
February 20, 2026 at 3:31 PM
Les chercheurs ont constaté que les modèles chinois (BaiChuan, DeepSeek et ChatGLM) étaient plus enclins à refuser de répondre ou à fournir des informations inexactes sur des sujets tels que le statut de Taïwan, les minorités ethniques ou les militants pro-démocratie
📦 hiyouga / LLaMA-Factory
⭐ 9,528 (+53)
🗒 Python
Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)
⭐ 9,528 (+53)
🗒 Python
Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)
GitHub - hiyouga/LLaMA-Factory: Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)
Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM) - GitHub - hiyouga/LLaMA-Factory: Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen...
github.com
January 13, 2024 at 12:50 PM
📦 hiyouga / LLaMA-Factory
⭐ 9,528 (+53)
🗒 Python
Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)
⭐ 9,528 (+53)
🗒 Python
Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)
[1/3] 2026-07-17 18:00:43 - [Baichuan Intelligent WAIC demonstrates M4's professional capabilities for the first time] On July 17, at the 2026 World Artificial Intelligence Conference and the High-level Conference on Artificial Intelligence Global Governance, Baichuan Intelligent
July 17, 2026 at 10:14 AM
[1/3] 2026-07-17 18:00:43 - [Baichuan Intelligent WAIC demonstrates M4's professional capabilities for the first time] On July 17, at the 2026 World Artificial Intelligence Conference and the High-level Conference on Artificial Intelligence Global Governance, Baichuan Intelligent