Pith. sign in

Scan and snap: Understanding training dynamics and token composition in 1-layer transformer

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CL 1 cs.LG 1

years

2026 1 2024 1

representative citing papers

Tight Sample Complexity of Transformers

cs.LG · 2026-06-08 · accept · novelty 8.0

Hard-attention Transformers with W parameters and depth L have VC dimension Θ(WL log(TW)); teacher forcing is sample-optimal for chain-of-thought learning.

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

cs.CL · 2024-02-05 · conditional · novelty 6.0

KIVI applies asymmetric 2-bit quantization to KV cache with per-channel keys and per-token values, reducing memory 2.6x and boosting throughput up to 3.47x with near-identical quality on Llama, Falcon, and Mistral.

citing papers explorer

Showing 2 of 2 citing papers.

  • Tight Sample Complexity of Transformers cs.LG · 2026-06-08 · accept · none · ref 38

    Hard-attention Transformers with W parameters and depth L have VC dimension Θ(WL log(TW)); teacher forcing is sample-optimal for chain-of-thought learning.

  • KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache cs.CL · 2024-02-05 · conditional · none · ref 17

    KIVI applies asymmetric 2-bit quantization to KV cache with per-channel keys and per-token values, reducing memory 2.6x and boosting throughput up to 3.47x with near-identical quality on Llama, Falcon, and Mistral.