tweetindex
TH

Alexia Jolicoeur-Martineau ✓

@jm_alexia · Montréal, Québec · joined 09 Mar 2017

Principal Researcher @ Microsoft 🐱‍💻 2025 ARC Prize Winner I build generative AI for images, videos, text, tabular data, weights, molecules, and video games.

26 120Followers
2 216Following
9 978Posts total
833.2KViews on collected posts

โพสต์ล่าสุด

@jm_alexia @JFPuget @RheaSukthanker @CameronPashmina @Emy_Aze I'm a bit disappointed you made the title so misleading. Just add *in post training* to it, like you did here. 80.6K views · 738 likes · 9 reposts · 7 replies Open on X →
Now also on HuggingFace. Code coming later. https://t.co/qtGwpETRUM 14.8K views · 60 likes · 6 reposts · 0 replies Open on X →
Linear attention has limited memory, so it must choose which tokens to remember and which to forget. Trying to learn this during post-training at a small cost is misguided. 18.5K views · 61 likes · 4 reposts · 4 replies Open on X →
Retrofitting an LLM to use linear attention sounds great in theory, but it does not deliver its promises. It adds cost and complexity while degrading performance on long context massively. 26.7K views · 67 likes · 4 reposts · 1 replies Open on X →
Simple beats complicated: We show that switching to a sliding-window attention mask with attention sinks (at no cost) beats linear attention post-training. Huge thanks to my collaborators @RheaSukthanker, @CameronPashmina, and @Emy_Aze. Paper: https://t.co/h8DIc223Su 538.4K views · 1.6K likes · 132 reposts · 55 replies Open on X →
Coming up on Monday morning if ArXiv doesn't act out 45.7K views · 444 likes · 10 reposts · 26 replies Open on X →
Thanks everyone who came to the first "inner loop" research seminar at Microsoft! I will share details soon for the next event that is happening in 2 weeks. 5.8K views · 41 likes · 0 reposts · 1 replies Open on X →
New paper coming up next week! The foundations of some will be shaken. https://t.co/t5xDe9JC9a 102.6K views · 625 likes · 25 reposts · 19 replies Open on X →

เทียบกับบัญชีขนาดเดียวกัน

8 โพสต์จาก 90 วันที่ผ่านมา เทียบกับช่วง 10K–100K ผู้ติดตาม แสดงในวงกว้าง แต่มีผู้ชมตอบสนองน้อย.

ยอดดูมัธยฐาน36 200บัญชีนี้924ค่ามัธยฐานของ 10K–100K
การเข้าถึง, %138.59%บัญชีนี้3.62%ค่ามัธยฐานของ 10K–100K
การมีส่วนร่วม, %0.55%บัญชีนี้1.52%ค่ามัธยฐานของ 10K–100K
ตัวชี้วัดบัญชีนี้ค่ามัธยฐานของ 10K–100Kอัตราส่วน
ยอดดูมัธยฐานต่อโพสต์36 20092439.2×
การเข้าถึง (ยอดดู ÷ ผู้ติดตาม)138.59%3.62%38.3×
อัตราการมีส่วนร่วม0.55%1.52%0.36×

บัญชีอื่นในช่วงนี้ →   เปรียบเทียบกับบัญชีอื่น →   ค่าอ้างอิงเหล่านี้คำนวณอย่างไร →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

102.6K25 Aug
5.8K27 Aug
45.7K28 Aug
538.4K31 Aug
26.7K
18.5K
14.8K
80.6K

Last 8 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.66%25 Aug
0.72%27 Aug
1.06%28 Aug
0.34%31 Aug
0.27%
0.37%
0.45%
0.94%

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.

What the audience does

Likes65.4%3 625 in total
Reposts3.4%190 in total
Replies2.0%113 in total
Quotes1.5%83 in total
Bookmarks27.6%1 528 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

บัญชีที่คล้ายกัน

Frequently asked questions about @jm_alexia

How many followers does @jm_alexia have?

26 120 followers.

How many posts has @jm_alexia published?

9 978 posts.

How do posts by @jm_alexia perform?

Collected posts: 8. Views: 833 233. Likes: 3 625.