CHASE-VLA: チャンク認識型スケール推定による視覚-言語-行動モデルの訓練後量子化フレームワーク
CHASE-VLA: Post-Training Quantization Framework for Vision-Language-Action Models with Chunk-Aware Scale Estimation
VLAモデルの拡散ベース行動エキスパートをW4A4に量子化する際、生成済み行動チャンクとノイズ除去ステップ情報を活用して活性化スケールを適応させ、精度を維持しつつメモリを大幅削減する手法を提案。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Jin Hyun, Jung Gyu Min, Gyuhyun Jung, Youngjoo Lee
分類: cs.CV
原文アブストラクト
Vision-Language-Action (VLA) models map visual observations and language instructions to continuous robot actions, but a diffusion-based action expert (AE) poses a key challenge for low-bit post-training quantization (PTQ). The AE is repeatedly invoked across denoising steps and policy queries, where fixed calibration scales can be mismatched with activation ranges that vary with denoising progress and intended motion. We propose CHASE-VLA, a chunk-aware PTQ method that exploits a VLA-specific signal readily available from the policy: the generated action chunk, including its unexecuted future suffix. Rather than relying only on static scale matching for AE layers, CHASE-VLA combines the previously generated chunk as causal action context with denoising step group information to adapt AE activation scales. This enables W4A4 quantization of both MLP and attention projections in the repeated AE without modifying the pretrained policy. On LIBERO, CHASE-VLA achieves 97.3% average success rate on $π_{0.5}$ when both MLP and attention projections in the AE are quantized to W4A4, restoring FP16-level performance. CHASE-VLA also reduces the weight storage of the quantized AE linear layers by 73.4% and their single-chunk memory traffic by 70.9% and 71.2% on $π_{0.5}$ and GR00T N1.6, respectively, with a predictor overhead of at most 1.26% of the saved storage.