Sources · Twitter/X

@randall_balestr

Active

randall_balestr

Linked items 17
Errors 5
Last fetched 2026-06-14 00:41
Priority P3
Must-read No

Edit

Human-friendly label. Leave blank to fall back to the identifier.

Drives ingestion cadence and the default ranking weight applied to items from this source.

Includes every eligible item from this source in the Must Read section, even when the normal item cap or duplicate grouping would skip it.

How often the watch loop polls this source. Minimum 5 min. Leave blank for the per-type default.

Optional. Pin a specific summarization model for items from this source.

Cancel

Recent items

The 15 most-recently-ingested items from this source, newest first.

Title Type Fetched
@randall_balestr: We extended the deadline until Jun 15th (AOE)! Randall Balestriero (@randall_balestr) Our lineup ... article 2026-06-12
@randall_balestr: Our lineup of speakers is growing! Many more to be announced.... and don't forget to submit your pap... article 2026-06-12
@randall_balestr: Delighted to announce our 3rd world modeling workshop! After NYC and Montreal, we are now headed to ... article 2026-05-12
@randall_balestr: - end-to-end image only JEPA world model training with SIGReg (no teacher-student, no EMA, no proble... article 2026-03-23
@randall_balestr: The DINO-WM result shows the need for stable-worldmodel ecosystem. We can't move forward if every pa... article 2026-02-24
@randall_balestr: It turns out that DINO-WM (take a strong foundation model and learn a forward dynamics model on top)... article 2026-02-24
@randall_balestr: World Modeling research needs fast iteration, reproducibility, optimized baselines, open-source, and... article 2026-02-24
@randall_balestr: JMM26 is coming! Here are two exciting events we are organizing around AI theory and SSL! The worksh... article 2026-01-02
@randall_balestr: We start having provable measures of alignment between pretraining setups and eval perfs: - CV arxiv... article 2026-01-01
@randall_balestr: We start having provable measures of alignment between pretraining setups and eval perfs: - CV arxiv... article 2026-01-01
@randall_balestr: From world modeling research to vulnerability discovery--OpenApps offers a fully open-source and sup... article 2025-12-10
@randall_balestr: From world modeling research to vulnerability discovery--OpenApps offers a fully open-source and sup... article 2025-12-10
@randall_balestr: If you are at #NeurIPS2025 and interested in (Le)JEPA: - I will be giving two short talks at the @AI... article 2025-12-02
@randall_balestr: Great questions! all those are different flavors of JEPAs based on your particular use-case. If you ... article 2025-11-21
@randall_balestr: if you have asymmetry (e.g. next frame from current frame) and actions (explaining the transition be... article 2025-11-21