pith. sign in

FastVID: Dynamic density pruning for fast video large language models

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CV 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Stage-adaptive Token Selection for Efficient Omni-modal LLMs

cs.CV · 2026-05-19 · unverdicted · novelty 5.0

SEATS adaptively selects and removes non-text tokens before and inside the LLM layers of omni-modal models, yielding 9.3x FLOPs reduction and 4.8x prefill speedup at 10% token retention while keeping 96.3% performance.

citing papers explorer

Showing 1 of 1 citing paper.

  • Stage-adaptive Token Selection for Efficient Omni-modal LLMs cs.CV · 2026-05-19 · unverdicted · none · ref 21

    SEATS adaptively selects and removes non-text tokens before and inside the LLM layers of omni-modal models, yielding 9.3x FLOPs reduction and 4.8x prefill speedup at 10% token retention while keeping 96.3% performance.