Pith. sign in

REVIEW 2 cited by

Rethinking Token Reduction for State Space Models

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 2410.14725 v1 pith:Q2NTALLW submitted 2024-10-16 cs.LG cs.CL

classification cs.LGcs.CL
keywords tokenreductionmodelsssmsexistingmambamethodmethods
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent advancements in State Space Models (SSMs) have attracted significant interest, particularly in models optimized for parallel training and handling long-range dependencies. Architectures like Mamba have scaled to billions of parameters with selective SSM. To facilitate broader applications using Mamba, exploring its efficiency is crucial. While token reduction techniques offer a straightforward post-training strategy, we find that applying existing methods directly to SSMs leads to substantial performance drops. Through insightful analysis, we identify the reasons for this failure and the limitations of current techniques. In response, we propose a tailored, unified post-training token reduction method for SSMs. Our approach integrates token importance and similarity, thus taking advantage of both pruning and merging, to devise a fine-grained intra-layer token reduction strategy. Extensive experiments show that our method improves the average accuracy by 5.7% to 13.1% on six benchmarks with Mamba-2 compared to existing methods, while significantly reducing computational demands and memory requirements.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Training-free Token Reduction for Vision Mamba

    cs.CV 2025-07 conditional novelty 6.0 of 10

    MTR uses Mamba's timescale parameter Δ as a token importance score to merge unimportant tokens, giving training-free inference speedups with small accuracy loss.

  2. Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation

    cs.CL 2025-05 conditional novelty 5.0 of 10

    Adaptive selection and dynamic weighted fusion of source LLMs reduces knowledge interference and improves target model accuracy compared to FuseLLM.

Pith tools