Pith. sign in

REVIEW 9 cited by

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 2405.06640 v1 pith:VTKT73LJ submitted 2024-05-10 cs.CL

Linearizing Large Language Models

classification cs.CL
keywords linearmodelspre-trainingtransformerscomputelargerecurrentalternative
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Linear transformers have emerged as a subquadratic-time alternative to softmax attention and have garnered significant interest due to their fixed-size recurrent state that lowers inference cost. However, their original formulation suffers from poor scaling and underperforms compute-matched transformers. Recent linear models such as RWKV and Mamba have attempted to address these shortcomings by proposing novel time-mixing and gating architectures, but pre-training large language models requires significant data and compute investments. Thus, the search for subquadratic architectures is limited by the availability of compute and quality pre-training datasets. As a cost-effective alternative to pre-training linear transformers, we propose Scalable UPtraining for Recurrent Attention (SUPRA). We present a method to uptrain existing large pre-trained transformers into Recurrent Neural Networks (RNNs) with a modest compute budget. This allows us to leverage the strong pre-training data and performance of existing transformer LLMs, while requiring 5% of the training cost. We find that our linearization technique leads to competitive performance on standard benchmarks, but we identify persistent in-context learning and long-context modeling shortfalls for even the largest linear models. Our code and models can be found at https://github.com/TRI-ML/linear_open_lm.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Morphing into Hybrid Attention Models

    cs.CL 2026-06 unverdicted novelty 7.0

    FlashMorph formulates hybrid layer selection as budget-constrained optimization, trains per-layer gates on synthetic retrieval data with linearization regularization, then discretizes and distills to produce efficient...

  2. The Key to Going Linear: Analysis-Driven Transformer Linearization

    cs.LG 2026-07 conditional novelty 6.0

    Delta-rule linear attention faithfully approximates softmax attention through key-dependent rank-1 projections, enabling efficient post-hoc linearization of LLMs up to 32B parameters.

  3. Llamion Technical Report

    cs.CL 2026-05 unverdicted novelty 6.0

    A new conversion method (KEPT) transforms Orion-14B into Llama-format models while preserving benchmark performance using ~123M tokens of distillation.

  4. Attention to Mamba: A Recipe for Cross-Architecture Distillation

    cs.CL 2026-04 unverdicted novelty 6.0

    A two-stage distillation recipe converts a Pythia-1B Transformer into a Mamba model that preserves performance with perplexity 14.11 versus the teacher's 13.86.

  5. SpikingBrain: Spiking Brain-inspired Large Models

    cs.LG 2025-09 unverdicted novelty 6.0

    SpikingBrain-7B and SpikingBrain-76B achieve Transformer-comparable performance after continual pre-training on 150B tokens, with over 100x TTFT speedup on 4M-token sequences and 69.15% sparsity from event-driven spiking.

  6. Lizard: An Efficient Linearization Framework for Large Language Models

    cs.CL 2025-07 unverdicted novelty 6.0

    Lizard linearizes Transformer LLMs via subquadratic attention and adaptive learnable modules, recovering near-original performance while outperforming prior linearization methods on MMLU and associative recall.

  7. MoBA: Mixture of Block Attention for Long-Context LLMs

    cs.LG 2025-02 unverdicted novelty 6.0

    MoBA routes attention over blocks via MoE-style gating to enable dynamic, bias-light long-context attention that matches full attention performance at lower cost.

  8. LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation

    cs.CL 2024-10 unverdicted novelty 6.0

    LightTransfer identifies lazy layers in LLMs like LLaMA and replaces their attention with streaming attention to form hybrid models, delivering up to 2.17x throughput with under 1.5% drop on LongBench and strong resul...

  9. SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference

    cs.LG 2026-04 unverdicted novelty 5.0

    SpikingBrain2.0 is a 5B hybrid spiking-Transformer that recovers most base model performance while delivering 10x TTFT speedup at 4M context and supporting over 10M tokens on limited GPUs via dual sparse attention and...