Yoshinari Fujinuma
@akkikiki.bsky.social
Member of Technical Staff@Cantina Labs (NYC);
CS PhD @CUBoulder;
Posts are my own;
Website: https://akkikiki.github.io/
Substack: http://substack.com/@akkikiki
Lived: 🇹🇭🇯🇵🇫🇷🇺🇸
Posts: JA/EN
CS PhD @CUBoulder;
Posts are my own;
Website: https://akkikiki.github.io/
Substack: http://substack.com/@akkikiki
Lived: 🇹🇭🇯🇵🇫🇷🇺🇸
Posts: JA/EN
Pinned
Yoshinari Fujinuma
@akkikiki.bsky.social
· Nov 23
Here's the starter pack for AI/ML/NLP conferences that I was able to find as of now. I couldn't remove myself from the starter pack so feel free to unfollow me after hitting the "follow all" button 🙂 go.bsky.app/9QQXJ1u
Does anybody know the list of social events happening at NeurIPS @ San Diego? Only found luma.com/NeurIPS so far
NeurIPS · Events Calendar
View and subscribe to events from NeurIPS on Luma. NeurIPS 2025 takes place in San Diego from December 2–7, bringing together leading researchers and engineers to share breakthroughs in AI, machine le...
luma.com
November 17, 2025 at 3:47 AM
Does anybody know the list of social events happening at NeurIPS @ San Diego? Only found luma.com/NeurIPS so far
I played around with the mlx and 4-bit version of Qwen3-30B-A3B locally on an Apple M4 Max chip, with Japanese and English. This is amazing. It seems feasible to run it locally for tasks other than long-horizon or complex ones.
April 30, 2025 at 9:42 PM
I played around with the mlx and 4-bit version of Qwen3-30B-A3B locally on an Apple M4 Max chip, with Japanese and English. This is amazing. It seems feasible to run it locally for tasks other than long-horizon or complex ones.
Reposted by Yoshinari Fujinuma
To be clear, the recipe to replicate o1 style models is not new techniques, but applying them in a new way.
This shouldn't be surprising.
This shouldn't be surprising.
January 21, 2025 at 3:46 PM
To be clear, the recipe to replicate o1 style models is not new techniques, but applying them in a new way.
This shouldn't be surprising.
This shouldn't be surprising.
I've just played around with DeepSeek-R1 and wow, such a long thoughts for a simple question "What is the square root of 16?" 😀
January 21, 2025 at 7:43 PM
I've just played around with DeepSeek-R1 and wow, such a long thoughts for a simple question "What is the square root of 16?" 😀
My LinkedIn feed is full of AWS re:Invent posts (since I work at AWS, and many colleagues share about it), Twitter/X is a mixture of everything, and Bluesky posts are mostly academic. Welcome to the filter bubbles!
December 4, 2024 at 5:16 AM
My LinkedIn feed is full of AWS re:Invent posts (since I work at AWS, and many colleagues share about it), Twitter/X is a mixture of everything, and Bluesky posts are mostly academic. Welcome to the filter bubbles!
I was taking a stab at the responding to author discussions for ARR for the last few days, but some common issues I see is that submitted drafts are pretty exaggerating how good the results are.
November 29, 2024 at 5:17 AM
I was taking a stab at the responding to author discussions for ARR for the last few days, but some common issues I see is that submitted drafts are pretty exaggerating how good the results are.
Where is the open-weight model that we can try it out? 😀
blogs.nvidia.com/blog/fugatto...
blogs.nvidia.com/blog/fugatto...
Now Hear This: World’s Most Flexible Sound Machine Debuts
Fugatto generates or transforms any mix of music, voices and sounds described with prompts using any combination of text and audio files.
blogs.nvidia.com
November 26, 2024 at 3:28 AM
Where is the open-weight model that we can try it out? 😀
blogs.nvidia.com/blog/fugatto...
blogs.nvidia.com/blog/fugatto...
Reposted by Yoshinari Fujinuma
Look who's here
@pnas.org ✔️
@science.org ✔️
@naturecellbiology.bsky.social ✔️
@natrevgenet.bsky.social ✔️
@naturebiotech.bsky.social ✔️
@naturemicrobiol.bsky.social ✔️
@naturechemistry.bsky.social ✔️
@genesdev.bsky.social ✔️
@cellchembiol.bsky.social ✔️
@genomeresearch.bsky.social ✔️
@jcellbiol.bsky.social ✔️
@pnas.org ✔️
@science.org ✔️
@naturecellbiology.bsky.social ✔️
@natrevgenet.bsky.social ✔️
@naturebiotech.bsky.social ✔️
@naturemicrobiol.bsky.social ✔️
@naturechemistry.bsky.social ✔️
@genesdev.bsky.social ✔️
@cellchembiol.bsky.social ✔️
@genomeresearch.bsky.social ✔️
@jcellbiol.bsky.social ✔️
November 25, 2024 at 1:47 PM
Look who's here
@pnas.org ✔️
@science.org ✔️
@naturecellbiology.bsky.social ✔️
@natrevgenet.bsky.social ✔️
@naturebiotech.bsky.social ✔️
@naturemicrobiol.bsky.social ✔️
@naturechemistry.bsky.social ✔️
@genesdev.bsky.social ✔️
@cellchembiol.bsky.social ✔️
@genomeresearch.bsky.social ✔️
@jcellbiol.bsky.social ✔️
@pnas.org ✔️
@science.org ✔️
@naturecellbiology.bsky.social ✔️
@natrevgenet.bsky.social ✔️
@naturebiotech.bsky.social ✔️
@naturemicrobiol.bsky.social ✔️
@naturechemistry.bsky.social ✔️
@genesdev.bsky.social ✔️
@cellchembiol.bsky.social ✔️
@genomeresearch.bsky.social ✔️
@jcellbiol.bsky.social ✔️
I like typeset.io/pdf-to-video 's pdf-to-video feature for getting a quick overview of the paper. Looking forward to having more fine-grained video (or even customizable controlled generation of pdf video summary) version of it 😀
November 26, 2024 at 1:22 AM
I like typeset.io/pdf-to-video 's pdf-to-video feature for getting a quick overview of the paper. Looking forward to having more fine-grained video (or even customizable controlled generation of pdf video summary) version of it 😀
Reposted by Yoshinari Fujinuma
Just a heads up to everyone: @deep-mind.bsky.social is unfortunately a fake account and has been reported. Please do not follow it nor repost anything from it.
November 25, 2024 at 11:24 PM
Just a heads up to everyone: @deep-mind.bsky.social is unfortunately a fake account and has been reported. Please do not follow it nor repost anything from it.
Here's the starter pack for AI/ML/NLP conferences that I was able to find as of now. I couldn't remove myself from the starter pack so feel free to unfollow me after hitting the "follow all" button 🙂 go.bsky.app/9QQXJ1u
November 23, 2024 at 1:49 AM
Here's the starter pack for AI/ML/NLP conferences that I was able to find as of now. I couldn't remove myself from the starter pack so feel free to unfollow me after hitting the "follow all" button 🙂 go.bsky.app/9QQXJ1u
Reposted by Yoshinari Fujinuma
Reposted by Yoshinari Fujinuma
📣 I am sure we have reached only a small fraction of New York's ML community in bsky. Please repost 🔁 this if you think you may have interested people close to you in the social graph.
I did a starter pack of people in New York (City) working on ML/AI. Please distribute and feel free to self nominate!
go.bsky.app/BoEtagz
go.bsky.app/BoEtagz
November 22, 2024 at 2:14 PM
📣 I am sure we have reached only a small fraction of New York's ML community in bsky. Please repost 🔁 this if you think you may have interested people close to you in the social graph.
Someone should really treat me some coffee for asking me to assign & finish the emergency review within a day 😀
November 22, 2024 at 7:43 PM
Someone should really treat me some coffee for asking me to assign & finish the emergency review within a day 😀
Reposted by Yoshinari Fujinuma
1. Find your friends! I've found most of mine with:
- Starter packs blueskydirectory.com/starter-pack...
- the Chrome extension 'Sky Follower Bridge' www.sky-follower-bridge.dev
- @theo.io's Follow Finder, which lists people who are followed by lots of people you follow bsky-follow-finder.theo.io
- Starter packs blueskydirectory.com/starter-pack...
- the Chrome extension 'Sky Follower Bridge' www.sky-follower-bridge.dev
- @theo.io's Follow Finder, which lists people who are followed by lots of people you follow bsky-follow-finder.theo.io
November 20, 2024 at 7:52 PM
1. Find your friends! I've found most of mine with:
- Starter packs blueskydirectory.com/starter-pack...
- the Chrome extension 'Sky Follower Bridge' www.sky-follower-bridge.dev
- @theo.io's Follow Finder, which lists people who are followed by lots of people you follow bsky-follow-finder.theo.io
- Starter packs blueskydirectory.com/starter-pack...
- the Chrome extension 'Sky Follower Bridge' www.sky-follower-bridge.dev
- @theo.io's Follow Finder, which lists people who are followed by lots of people you follow bsky-follow-finder.theo.io
Today's paper reading: Interesting, quantization can reverse unlearning up to 83% arxiv.org/abs/2410.16454
Does your LLM truly unlearn? An embarrassingly simple approach to recover unlearned knowledge
Large language models (LLMs) have shown remarkable proficiency in generating text, benefiting from extensive training on vast textual corpora. However, LLMs may also acquire unwanted behaviors from th...
arxiv.org
November 21, 2024 at 2:43 AM
Today's paper reading: Interesting, quantization can reverse unlearning up to 83% arxiv.org/abs/2410.16454
Reposted by Yoshinari Fujinuma
I did a starter pack of people in New York (City) working on ML/AI. Please distribute and feel free to self nominate!
go.bsky.app/BoEtagz
go.bsky.app/BoEtagz
November 19, 2024 at 1:38 AM
I did a starter pack of people in New York (City) working on ML/AI. Please distribute and feel free to self nominate!
go.bsky.app/BoEtagz
go.bsky.app/BoEtagz
Today's paper reading: arxiv.org/abs/2306.13649
On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
Knowledge distillation (KD) is widely used for compressing a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, current KD methods for auto-...
arxiv.org
November 20, 2024 at 5:37 AM
Today's paper reading: arxiv.org/abs/2306.13649
Too many people... @Shibuya station, Tokyo, Japan
December 23, 2023 at 8:56 AM
Too many people... @Shibuya station, Tokyo, Japan
Wow, more than 2000 papers were accepted in total for EMNLP
December 8, 2023 at 2:16 AM
Wow, more than 2000 papers were accepted in total for EMNLP
Heading to #EMNLP ! Co-authored papers 👇
[1] 12/9 11am in-person poster by Sharon Levy title "Comparing Biases and the Impact of Multilingual Training across Multiple Languages"
[2] 12/8 2pm virtual poster titled "A Multi-Modal Multilingual Benchmark for Document Image Classification"
[1] 12/9 11am in-person poster by Sharon Levy title "Comparing Biases and the Impact of Multilingual Training across Multiple Languages"
[2] 12/8 2pm virtual poster titled "A Multi-Modal Multilingual Benchmark for Document Image Classification"
December 6, 2023 at 7:51 AM
Heading to #EMNLP ! Co-authored papers 👇
[1] 12/9 11am in-person poster by Sharon Levy title "Comparing Biases and the Impact of Multilingual Training across Multiple Languages"
[2] 12/8 2pm virtual poster titled "A Multi-Modal Multilingual Benchmark for Document Image Classification"
[1] 12/9 11am in-person poster by Sharon Levy title "Comparing Biases and the Impact of Multilingual Training across Multiple Languages"
[2] 12/8 2pm virtual poster titled "A Multi-Modal Multilingual Benchmark for Document Image Classification"
Resolving Latex errors for uploading to arxiv...
October 25, 2023 at 4:26 AM
Resolving Latex errors for uploading to arxiv...
GPT-4V just fixed my circuit breaker (where I had been struggling for 10+ mins at midnight)
October 24, 2023 at 2:20 AM
GPT-4V just fixed my circuit breaker (where I had been struggling for 10+ mins at midnight)
Done finishing up the EMNLP findings camera ready
October 21, 2023 at 2:39 AM
Done finishing up the EMNLP findings camera ready
I finally read the attention sink paper [1] and the HF blog article [2]. Seems like another interesting data point that the models we usually interact with strongly attend to the first few tokens...
[1] arxiv.org/abs/2309.17453
[2] huggingface.co/blog/tomaars...
[1] arxiv.org/abs/2309.17453
[2] huggingface.co/blog/tomaars...
October 19, 2023 at 1:18 AM
I finally read the attention sink paper [1] and the HF blog article [2]. Seems like another interesting data point that the models we usually interact with strongly attend to the first few tokens...
[1] arxiv.org/abs/2309.17453
[2] huggingface.co/blog/tomaars...
[1] arxiv.org/abs/2309.17453
[2] huggingface.co/blog/tomaars...