SSAD 2026 talk maps the zoo of state representation designs for world models
abursuc · x · 2026-09-17
In a #ssad2026 talk, @abursuc surveyed different ways to craft state representations for world models — focusing on semantics, geometry, task relevance/predictability, or rich features from DINO distillation. He then broke down where methods diverge: what the tokenizer encodes, from frozen visual autoencoders and frozen representation encoders to joint encoder + predictor setups with no decoder.
More from Research
- Asynchronous Flow Map Language Models Generate All Tokens in a Single Forward Pass — kalyan_kpl · 2026-11-02
- NVIDIA's Kumo Is a Family of Four Tabular Foundation Models, Not Just One — pandeyparul · 2026-11-02
- Economist Aaroth: fast agreement dynamics survive without Bayesian updates or accurate priors — Aaroth · 2026-11-02
- ELLIS names 160 new ML Fellows and Scholars for 2025–2026 — JJitsev · 2026-11-02
- Meme turn 50: Aumann's 'Agreeing to Disagree' paper anniversary — Aaroth · 2026-11-02
- Anthropic: analysts unknowingly adopted their agent's secret lean 86% of the time — shoumikgoswami · 2026-11-02