- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
This paper argues that autoregressive world models implement retention (KV cache) and protention (action conditioning) but lack recollection: deliberate reactivation of earlier experience on revisit. It proposes Anamnesis, a training-free wrapper for frozen AR world models: store denoised latents with camera poses, detect revisits by pose gating, and reinject memory by re-noising the stored latent for one refinement step (SDEdit-style). A KV-cache override alternative leaves outputs unchanged, suggesting recollection must enter through the generative channel. The authors also introduce a closed-loop revisit benchmark with analytic pose ground truth from the model’s action DSL, plus Excess Revisit Consistency (ERC) against a novel-view control. On LingBot-World-Fast, Anamnesis raises mean ERC-PSNR from about +0.35 dB to +2.24 dB across four loops, with random-anchor and window-widening controls supporting pose-gated generative recollection rather than longer retention.
Critical strengths
- The problem diagnosis is crisp and useful: revisit failure is framed as missing recollection, not merely a short KV window.
- The method is simple, training-free, and scientifically clean as a probe on a frozen checkpoint.
- Evaluation design is thoughtful: exact poses, ERC vs. novel-view control, random-anchor control, KV-null result, and “not just copying / teleport-restart” checks.
- Empirical gains are consistent across loops, with useful ablations.
Critical weaknesses
- Narrow experimental scope. Results are mainly on one open model (LingBot-World-Fast) and a small set of release scenes/seeds. Cross-model transfer and broader scene diversity are needed for stronger claims.
- Exact pose gating limits realism. Detection assumes analytically exact camera poses from the action DSL. Free exploration would need SLAM-quality tracking; gate jitter helps, but is not a full substitute.
- Phenomenology framing is interesting but unevenly necessary. The retention/protention/recollection story is memorable, yet some sections read more philosophical than technical. The core ML contribution stands without heavy Husserlian packaging.
- Recollection is still short-horizon / single-anchor limited. Long excursions and multi-chunk revisits remain weak (semantic ERC mixed; single-anchor coverage issues). The paper acknowledges this, but “world memory” claims should stay bounded.
Questions for authors
Please see weaknesses.