Yongmin Kim @yongmini97

PhD. student at the University of Tokyo. at Matuso ・ Iwasawa Lab Japan Joined September 2023

Tweets

18
Followers

29
Following

235
Likes

214

Dhar Rawal @RawalDhar

2 months ago

@ramin_m_h @LiquidAI_ Discord invite? Is Discord open to all? It seems gated (unless I was looking at the wrong invite perma url)

1 1 0 992 0

Maxime Labonne @maximelabonne

4 weeks ago

Liquid just released two 450M and 1.6B param VLMs! They're super fast and leverage SigLIP2 NaFlex encoders to handle native resolutions without distortion. Available today on @huggingface!

17 83 642 103K 352

Download Image

Try LFM2 with llama.cpp today! We released today a collection of GGUF checkpoints for developers to run LFM2 everywhere with llama.cpp Select the most relevant precision for your use case and start building today. huggingface.co/LiquidAI/LFM2-…

6 36 127 29K 46

Download Image

Maxime Labonne @maximelabonne

2 months ago

Liquid AI open-sources a new generation of edge LLMs! 🥳 I'm so happy to contribute to the open-source community with this release on @huggingface! LFM2 is a new architecture that combines best-in-class inference speed and quality into 350M, 700M, and 1.2B models.

32 107 698 53K 424

Download Image

Maxime Labonne @maximelabonne

2 months ago

🤏 Can small models be strong reasoners? We created a 1B reasoning model at @LiquidAI_ that is both accurate and concise We applied a combination of SFT (to raise quality) and GRPO (to control verbosity) The result is a best-in-class model without specific math pre-training

11 63 485 29K 258

Download Image

Gouki Minegishi @GoukiMinegishi

3 months ago

What is the key difference between recent reasoning models and their base counterparts? Our new preprint reveals that reasoning models build distinctive “Reasoning Graphs” from their hidden states, characterized by more cycles, larger diameters, and stronger local connectivity.

4 11 33 4K 17

Download Gif

Gouki Minegishi @GoukiMinegishi

4 months ago

Our paper "Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence" has accepted at #ICML2025🎉 We found training Transformers in a few-shot setting leads to the emergence of 3 circuits. Joint work with @frt03_ @ishohei220 @yusuke_iwasawa_ @ymatsuo

1 20 81 34K 32

Download Gif

Kojima Takeshi @kojima_tks

4 months ago

🍻Two co-authored papers have been accepted to #ACL2025NLP🍻 Congrats to Andrew-san and Takashiro-san!

1 3 46 5K 6

Download Image

Kojima Takeshi @kojima_tks

4 months ago

🐥Our paper "Continual Pre-training on Character-Level Noisy Texts Makes Decoder-based Language Models Robust Few-shot Learners" has been accepted to #TACL🐥 We are now planning to make a presentation at #ACL2025NLP ! weblab.t.u-tokyo.ac.jp/news/2025-0502/

0 10 57 4K 15

Download Image

Kojima Takeshi @kojima_tks

9 months ago

🌈Our paper "Slender-Mamba: Fully Quantized Mamba in 1.58 Bits From Head to Toe" has been accepted to #coling2025 🌈 We apply BitNet b1.58 quantization to Mamba2 architecture including embedding and head layers to accelerate further lightweighting. Congrats @UTLLM_zxYu !

1 9 56 5K 10

Download Image

Kojima Takeshi @kojima_tks

12 months ago

🤗Our paper "Which Programming Language and What Features at Pre-training Stage Affect Downstream Logical Inference Performance?" has been accepted to #EMNLP2024 🤗 Congrats @FumiyaUchiyama! Read the following post for the details!