Pith. sign in

REVIEW 10 cited by

Perceiver: General Perception with Iterative Attention

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2103.03206 v2 pith:VSE46BWS submitted 2021-03-04 cs.CV cs.AIcs.LGcs.SDeess.AS

Andrew Jaegle , Felix Gimeno , Andrew Brock , Andrew Zisserman , Oriol Vinyals , Joao Carreira This is my paper
classification cs.CVcs.AIcs.LGcs.SDeess.AS
keywords inputsmodalitiesmodelsperceiverassumptionsattentionaudiocompetitive
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Biological systems perceive the world by simultaneously processing high-dimensional inputs from modalities as diverse as vision, audition, touch, proprioception, etc. The perception models used in deep learning on the other hand are designed for individual modalities, often relying on domain-specific assumptions such as the local grid structures exploited by virtually all existing vision models. These priors introduce helpful inductive biases, but also lock models to individual modalities. In this paper we introduce the Perceiver - a model that builds upon Transformers and hence makes few architectural assumptions about the relationship between its inputs, but that also scales to hundreds of thousands of inputs, like ConvNets. The model leverages an asymmetric attention mechanism to iteratively distill inputs into a tight latent bottleneck, allowing it to scale to handle very large inputs. We show that this architecture is competitive with or outperforms strong, specialized models on classification tasks across various modalities: images, point clouds, audio, video, and video+audio. The Perceiver obtains performance comparable to ResNet-50 and ViT on ImageNet without 2D convolutions by directly attending to 50,000 pixels. It is also competitive in all modalities in AudioSet.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 128 citations worldwide. Full citation record

  1. RoboTTT: Context Scaling for Robot Policies

    cs.RO 2026-07 conditional novelty 7.0 of 10

    A robot policy that updates its own weights during deployment can use 8,000 steps of history, steadily improving as context grows and enabling one-shot imitation from human videos.

  2. Rethinking Incompleteness: Formalizing Protocol Divergence and Train-Once Learning for Robust IMVC

    cs.LG 2026-06 unverdicted novelty 7.0 of 10

    Reconstruction-based IMVC is structurally untrainable when complete-sample proportion falls near zero; CRAFT escapes that bound via per-sample attention-masked fusion trained once on complete data.

  3. Patch Policy: Efficient Embodied Control via Dense Visual Representations

    cs.RO 2026-07 conditional novelty 6.0 of 10

    Patch Policy shows that frozen dense ViT patch tokens, consumed through a block-causal attention mask, let lightweight robot policies beat pooled-feature policies and even a fine-tuned 7B vision-language-action model.

  4. Distributed Cross-Channel Hierarchical Aggregation for Foundation Models

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Distributed Cross-Channel Hierarchical Aggregation (D-CHAG) reduces memory and boosts throughput for multi-channel vision foundation models by spreading tokenization and channel fusion across GPUs with only a small qu...

  5. AMPLIFY: Actionless Motion Priors for Robot Learning from Videos

    cs.RO 2025-06 conditional novelty 6.0 of 10

    A three-stage pipeline that turns keypoint tracks into discrete motion tokens, predicts them from action-free video, and decodes them into actions yields large few-shot and zero-shot policy improvements in robot manipulation.

  6. Turbocharging Web Automation: The Impact of Compressed History States

    cs.CL 2025-07 conditional novelty 5.0 of 10

    A Perceiver-style history compressor that summarizes past web states into 256-token representations improves Mind2Web and WebLINX web-automation accuracy by 1.2-5.4% over a no-history baseline.

  7. TransZero: Parallel Tree Expansion in MuZero using Transformer Networks

    cs.LG 2025-09 conditional novelty 4.0 of 10

    TransZero parallelizes Monte Carlo tree search expansion using a transformer dynamics network and a variance-based evaluator, achieving up to an 11x wall-clock speedup over MuZero without sacrificing final reward.

  8. DesignCLIP: Multimodal Learning with CLIP for Design Patent Understanding

    cs.CV 2025-08 unverdicted novelty 4.0 of 10

    The submitted package describes DesignCLIP in metadata, but the full text is a different paper, so the central results cannot be verified.

  9. Visual Language Models as Zero-Shot Deepfake Detectors

    cs.CV 2025-07 conditional novelty 4.0 of 10

    Zero-shot VLMs scored by normalized yes/no token probabilities beat most trained deepfake detectors on a new SimSwap dataset, and a lightly fine-tuned InstructBLIP is near-perfect on DFDC-P.

  10. A Vision Toward Energy-Efficient Domain-Specific Artificial Intelligence Models and Agents

    cs.AI 2025-10 unverdicted novelty 2.0 of 10

    A position paper proposing compact, domain-specific AI agents as the path to ≥1000× energy efficiency, without demonstrating the claim.

Pith tools