Pith. sign in

REVIEW 10 cited by

Scaling Transformer to 1M tokens and beyond with RMT

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 2304.11062 v2 pith:TAHEU6GA submitted 2023-04-19 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords inputscalingcontextlanguagememorytaskstokenstransformer
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

A major limitation for the broader scope of problems solvable by transformers is the quadratic scaling of computational complexity with input size. In this study, we investigate the recurrent memory augmentation of pre-trained transformer models to extend input context length while linearly scaling compute. Our approach demonstrates the capability to store information in memory for sequences of up to an unprecedented two million tokens while maintaining high retrieval accuracy. Experiments with language modeling tasks show perplexity improvement as the number of processed input segments increases. These results underscore the effectiveness of our method, which has significant potential to enhance long-term dependency handling in natural language understanding and generation tasks, as well as enable large-scale context processing for memory-intensive applications.

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.

  1. RULER: What's the Real Context Size of Your Long-Context Language Models?

    cs.CL 2024-04 accept novelty 8.0 of 10

    RULER shows most long-context LMs drop sharply in performance on complex tasks as length and difficulty increase, with only half maintaining results at 32K tokens.

  2. Mamba: Linear-Time Sequence Modeling with Selective State Spaces

    cs.LG 2023-12 unverdicted novelty 8.0 of 10

    Mamba is a linear-time sequence model using input-dependent selective SSMs that achieves SOTA results across modalities and matches twice-larger Transformers on language modeling with 5x higher inference throughput.

  3. LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding

    cs.CL 2023-08 unverdicted novelty 8.0 of 10

    LongBench is the first bilingual multi-task benchmark for long context understanding in LLMs, containing 21 datasets in 6 categories with average lengths of 6711 words (English) and 13386 characters (Chinese).

  4. RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies

    cs.RO 2026-03 accept novelty 7.0 of 10

    A standardized 16-task memory benchmark and 14 controlled VLA variants show perceptual memory (especially frame sampling + AdaLN modulation) is strongest overall, while symbolic subgoals win on counting and short-hori...

  5. Connecting the Dots: Benchmarking Reflective Memory in Long-Horizon Dialogue

    cs.CL 2026-05 unverdicted novelty 6.0 of 10

    RefMem-Bench benchmarks reflective memory in dialogue with 26K instances across eight dimensions, and REMIND improves model accuracy via hierarchical evidence retrieval, grounding, and abstraction.

  6. AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation Quantization

    cs.AR 2026-04 unverdicted novelty 6.0 of 10

    AQPIM performs in-memory product quantization of activations for LLMs on PIM hardware, reducing GPU-CPU communication by 90-98.5% and delivering 3.4x speedup over prior PIM methods.

  7. RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies

    cs.RO 2026-03 unverdicted novelty 6.0 of 10

    RoboMME is a new benchmark with 16 tasks and 14 memory-augmented VLA variants that shows memory effectiveness is highly task-dependent.

  8. MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent

    cs.CL 2025-07 unverdicted novelty 6.0 of 10

    MemAgent uses multi-conversation RL to train a memory agent that reads text in segments and overwrites memory, extrapolating from 8K training to 3.5M token QA with under 5% loss and 95%+ on 512K RULER.

  9. Titans: Learning to Memorize at Test Time

    cs.LG 2024-12 unverdicted novelty 6.0 of 10

    Titans combine attention for current context with a learnable neural memory for long-term history, achieving better performance and scaling to over 2M-token contexts on language, reasoning, genomics, and time-series tasks.

  10. Language Modeling Is Compression

    cs.LG 2023-09 accept novelty 6.0 of 10

    Large language models serve as strong general-purpose lossless compressors for text, images, and audio, outperforming domain-specific methods and revealing insights into scaling, tokenization, and in-context learning.

Pith tools