ID

yesnoerror ✓

@yesnoerror · $YNE on BASE & SOL · joined 18 Dec 2024

The best way to learn about cutting edge AI research. AI alpha-detection methods used by top VCs and AI executives.

27 128Followers

1Following

3 096Posts total

4.1KViews on collected posts

Postingan terbaru

yesnoerror ✓@yesnoerror18 Sep

AutoData reframes pre-training data selection as a search problem—no more hand-crafted heuristics. An LLM agent writes and tests Python selection algorithms, iterating 200 times overnight. The winning recipe cuts validation bpb from 0.9537 to 0.9521 (+5.6σ) and boosts CORE from h

0:08

599 views · 3 likes · 0 reposts · 1 replies Open on X →

yesnoerror ✓@yesnoerror18 Sep

DeepSeek-V4.1-Flash is a new 552B-parameter multimodal model that redefines what’s possible for long-context agents. It slashes KV cache size to just 890 bytes per token (4× smaller than before) using a blend of cross-layer sharing and ultra-low-precision FP4 caching. The result?

0:08

851 views · 7 likes · 2 reposts · 1 replies Open on X →

yesnoerror ✓@yesnoerror17 Sep

A new Neural-ODE framework just cracked one of holography's hardest inverse problems: reconstructing the full spacetime geometry of a charged AdS black hole directly from boundary fermionic spectra. The network doesn’t just fit the data—it enforces physical laws (AdS asymptotics,

0:08

838 views · 9 likes · 4 reposts · 0 replies Open on X →

yesnoerror ✓@yesnoerror17 Sep

SlotDiT is a major leap for robot video generation: it ditches pixel and VAE latents for object-centric "slots"—one vector per entity. This simple shift supercharges task performance: up to +32 points in task success (CLIPort), +30 on LanguageTable-Synthetic, and 74.5% robot http

0:08

954 views · 17 likes · 2 reposts · 0 replies Open on X →

yesnoerror ✓@yesnoerror16 Sep

Continual learning for recommender systems usually means “loud” users overwrite the interests of “quiet” ones—a problem this new paper calls evolution conflict. Their fix? LION, a sparse memory layer that acts like a personalized “notebook” for each user’s preferences. LION http

0:08

872 views · 14 likes · 5 reposts · 0 replies Open on X →

Dibandingkan akun berukuran sama

5 postingan dari 90 hari terakhir, dibandingkan dengan rentang 10K–100K pengikut. tepat di median untuk rentang pengikutnya.

Median tayangan851akun ini991median untuk 10K–100K

Jangkauan, %3.14%akun ini3.84%median untuk 10K–100K

Interaksi, %1.55%akun ini1.52%median untuk 10K–100K

Metrik	Akun ini	Median untuk 10K–100K	Rasio
Median tayangan per postingan	851	991	0.86×
Jangkauan (tayangan ÷ pengikut)	3.14%	3.84%	0.82×
Tingkat interaksi	1.55%	1.52%	1.02×

Akun lain pada rentang ini → Bandingkan dengan akun lain → Bagaimana tolok ukur ini disusun →

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

87216 Sep

95417 Sep

838

85118 Sep

599

Last 5 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

2.18%16 Sep

1.99%17 Sep

1.55%

1.18%18 Sep

0.67%

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

What the audience does

Likes76.9%50 in total

Reposts20.0%13 in total

Replies3.1%2 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.

Akun serupa