Papers › Scalable Adaptive Computation for Iterative Generation

Scalable Adaptive Computation for Iterative Generation

22 Dec 2022arXiv:2212.11972archive 2025-07-28

Allan Jabri, David Fleet, Ting Chen

Natural data is redundant yet predominant architectures tile computation uniformly across their input and output space. We propose the Recurrent Interface Networks (RINs), an attention-based architecture that decouples its core computation from the dimensionality of the data, enabling adaptive computation for more scalable generation of high-dimensional data. RINs focus the bulk of computation (i.e. global self-attention) on a set of latent tokens, using cross-attention to read and write (i.e. route) information between latent and data tokens. Stacking RIN blocks allows bottom-up (data to latent) and top-down (latent to data) feedback, leading to deeper and more expressive routing. While this routing introduces challenges, this is less problematic in recurrent computation settings where the task (and routing problem) changes gradually, such as iterative generation with diffusion models. We show how to leverage recurrence by conditioning the latent tokens at each forward pass of the reverse diffusion process with those from prior computation, i.e. latent self-conditioning. RINs yield state-of-the-art pixel diffusion models for image and video generation, scaling to 1024X1024 images without cascades or guidance, while being domain-agnostic and up to 10X more efficient than 2D and 3D U-Nets.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2212.11972")

Code

Syntology Ran 21 of 29 code samples harvested from 2 repositories linked to this paper; 8 have no recorded run. Of those that ran: 8 ran · honoured contract; 2 ran · our draft was wrong; 1 ran · fixture could not drive it; 10 ran with no contract checked.

By repository: official repository: 17 samples from 1 repository, 12 ran; community (archive-listed): 11 samples from 1 repository, 8 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

google-research/pix2seq officialmentioned in papermentioned on GitHubtf report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

29 samples harvested; 21 ran; 8 honoured the contract we drafted; 8 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

8ran · honoured contract
2ran · our draft was wrong
1ran · fixture could not drive it
10ran
8unverified

Licence: 1 of the 29 samples is pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

DropPath google-research/pix2seq/architectures/transformers.py official repository ran Apache-2.0 (permissive) · 80161ca59f374d2a · report
FeedForwardLayer google-research/pix2seq/architectures/transformers.py official repository ran Apache-2.0 (permissive) · b9ad5f9347bcd710 · report
add_vis_pos_emb google-research/pix2seq/architectures/transformers.py official repository ran · honoured contract Apache-2.0 (permissive) · fbc958c1295b5f01 · report
get_1d_position_codes google-research/pix2seq/architectures/transformers.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · cbbd048907025ae1 · report
get_2d_position_codes google-research/pix2seq/architectures/transformers.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · 554d30594bb18ba4 · report
get_angles google-research/pix2seq/architectures/transformers.py official repository ran · honoured contract Apache-2.0 (permissive) · c1a5330036a08dfa · report
get_ar_mask google-research/pix2seq/architectures/transformers.py official repository ran · honoured contract Apache-2.0 (permissive) · 508ee551fb33fedc · report
get_chunk_ar_mask google-research/pix2seq/architectures/transformers.py official repository ran · honoured contract Apache-2.0 (permissive) · 3e4ac71a6f12be9d · report
get_layer_config google-research/pix2seq/architectures/transformers.py official repository ran · honoured contract Apache-2.0 (permissive) · 90a86ebf31046958 · report
get_variable_initializer google-research/pix2seq/architectures/transformers.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 37888d00e9d8c4ab · report
kronecker_product google-research/pix2seq/architectures/transformers.py official repository ran · honoured contract fingerprinted Apache-2.0 (permissive) · e37890b1d73b280c · report
positional_encoding google-research/pix2seq/architectures/transformers.py official repository ran · fixture could not drive it fingerprinted Apache-2.0 (permissive) · 7a5b750c9c8d5e81 · report
FIT google-research/pix2seq/architectures/transformers.py official repository unverified Apache-2.0 (permissive) · e147f983e472692f · report
MLP google-research/pix2seq/architectures/transformers.py official repository unverified Apache-2.0 (permissive) · e2256176baee1426 · report
TransformerDecoderLayer google-research/pix2seq/architectures/transformers.py official repository unverified Apache-2.0 (permissive) · f14aac70f9859dd8 · report
TransformerEncoder google-research/pix2seq/architectures/transformers.py official repository unverified Apache-2.0 (permissive) · b019a0895599116d · report
TransformerEncoderLayer google-research/pix2seq/architectures/transformers.py official repository unverified Apache-2.0 (permissive) · e730a175de3303f8 · report
Attend lucidrains/recurrent-interface-network-pytorch/rin_pytorch/rin_pytorch.py community (archive-listed) ran MIT (permissive) · df4d0ae2244e374f · report
Attention lucidrains/recurrent-interface-network-pytorch/rin_pytorch/rin_pytorch.py community (archive-listed) ran MIT (permissive) · 305ed1d536ee99b2 · report
FeedForward lucidrains/recurrent-interface-network-pytorch/rin_pytorch/rin_pytorch.py community (archive-listed) ran MIT (permissive) · 1e9eca95c178f7c9 · report
LayerNorm lucidrains/recurrent-interface-network-pytorch/rin_pytorch/rin_pytorch.py community (archive-listed) ran MIT (permissive) · d070db73849f9743 · report
LearnedSinusoidalPosEmb lucidrains/recurrent-interface-network-pytorch/rin_pytorch/rin_pytorch.py community (archive-listed) ran · metamorphic tier: invariant fingerprinted MIT (permissive) · e4a1970252d572fd · report
LinearAttention lucidrains/recurrent-interface-network-pytorch/rin_pytorch/rin_pytorch.py community (archive-listed) ran MIT (permissive) · f8753f538bdf8090 · report
MultiHeadedRMSNorm lucidrains/recurrent-interface-network-pytorch/rin_pytorch/rin_pytorch.py community (archive-listed) ran MIT (permissive) · 8535fbe5734cf1d3 · report
PEG lucidrains/recurrent-interface-network-pytorch/rin_pytorch/rin_pytorch.py community (archive-listed) ran MIT (permissive) · 2090cfddb3b4ea08 · report
RIN lucidrains/recurrent-interface-network-pytorch/rin_pytorch/rin_pytorch.py community (archive-listed) unverified MIT (permissive) · 5fdaf6caf1863ed1 · report
RINBlock lucidrains/recurrent-interface-network-pytorch/rin_pytorch/rin_pytorch.py community (archive-listed) unverified MIT (permissive) · 89c11df753e06cb9 · report
Sequential lucidrains/recurrent-interface-network-pytorch/rin_pytorch/rin_pytorch.py community (archive-listed) unverified MIT (permissive) · d6fde31f78c4502f · report
suffix_id identical code first harvested elsewhere ran · our draft was wrong fingerprinted licence of this copy not recorded · d1c561539ef11926 · report

Tasks

Image GenerationVideo GenerationVideo Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation ImageNet 128x128 RIN FID 2.75 #8 of 23 Archive leaderboard report
Image Generation ImageNet 128x128 RIN IS 144.1 #8 of 23 Archive leaderboard report
Image Generation ImageNet 256x256 RIN FID 4.51 #85 of 94 Archive leaderboard report
Image Generation ImageNet 64x64 RIN FID 1.23 #8 of 65 Archive leaderboard report
Video Prediction Kinetics-600 12 frames, 64x64 RIN (1000 steps) FVD 10.8 #6 of 16 Archive leaderboard report
Video Prediction Kinetics-600 12 frames, 64x64 RIN (1000 steps) IS 17.7 #6 of 16 Archive leaderboard report
Video Prediction Kinetics-600 12 frames, 64x64 RIN (400 steps) FVD 11.5 #7 of 16 Archive leaderboard report
Video Prediction Kinetics-600 12 frames, 64x64 RIN (400 steps) IS 17.7 #7 of 16 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Diffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections