Pith. sign in

REVIEW 4 cited by

Addressing Some Limitations of Transformers with Feedback Memory

Not yet reviewed by Pith; the record is open.

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 2002.09402 v3 pith:VAZB2GET submitted 2020-02-21 cs.LG cs.CLstat.ML

classification cs.LGcs.CLstat.ML
keywords representationrepresentationstransformersfeedbackinputnetworkssequentialwhile
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Transformers have been successfully applied to sequential, auto-regressive tasks despite being feedforward networks. Unlike recurrent neural networks, Transformers use attention to capture temporal relations while processing input tokens in parallel. While this parallelization makes them computationally efficient, it restricts the model from fully exploiting the sequential nature of the input. The representation at a given layer can only access representations from lower layers, rather than the higher level representations already available. In this work, we propose the Feedback Transformer architecture that exposes all previous representations to all future representations, meaning the lowest representation of the current timestep is formed from the highest-level abstract representation of the past. We demonstrate on a variety of benchmarks in language modeling, machine translation, and reinforcement learning that the increased representation capacity can create small, shallow models with much stronger performance than comparable Transformers.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 31 citations worldwide. Full citation record

  1. Full-bandwidth transformer

    cs.AI 2026-08 conditional novelty 6.0 of 10

    Fusing the previous top-layer hidden state into the next input token through a gated linear unit improves transformer pretraining data efficiency and decoding accuracy at 1B scale.

  2. Pretraining Recurrent Networks without Recurrence

    cs.LG 2026-06 unverdicted novelty 6.0 of 10

    SMT trains nonlinear RNNs by imitating one-step memory-transition labels generated by a Transformer, replacing BPTT's unrolled credit assignment with time-parallel supervised learning.

  3. Maglev: Sliding Recurrent Memory

    cs.LG 2026-08 conditional novelty 5.0 of 10

    Using a full-context prefiller to write memory targets, Maglev trains a sliding-window recurrent transformer that keeps bounded memory at inference and improves language-modeling benchmarks.

  4. ContextQFormer: A New Context Modeling Method for Multi-Turn Multi-Modal Conversations

    cs.CL 2025-05 conditional novelty 5.0 of 10

    ContextQFormer adds a queue of [CLS] image and text features to a Q-Former style module and reports a 4.2% available-rate gain over LoRA-only on the new TMDialog benchmark.

Pith tools