The Flow has not summarised this story yet — read it at arXiv Machine Learning.
The paper introduces VLA-ULAP, a lightweight local action predictor that interleaves remote vision–language–action (VLA) calls with on‑edge inference. ULAP, with only 7.4 M parameters, predicts action chunks in a single pass using current views, proprioception, and action history, eliminating the need for VLA hidden states or server round‑trips. Experiments on Jetson Orin Nano and simulated benchmarks show that VLA-ULAP can remove 48.8–76.7 % of VLA calls while preserving 95–97.5 % of baseline success, and it outperforms local VLA‑acceleration alternatives in both inference time and energy consumption.
arXiv:2606. 09682v1 Announce Type: new Abstract: AutoMegaKernel (AMK) compiles a HuggingFace Llama-family model into a single persistent cooperative CUDA kernel that runs the whole forward pass in one launch, with no per-model hand-written CUDA.
arXiv:2607. 14568v1 Announce Type: cross Abstract: A companion study ran a 35B mixture-of-experts model on a 2011 NVIDIA Tesla C2075 (Fermi, sm_20, 6GB) as a GPU-prefill/CPU-decode hybrid, because the 4-bit model did not fit in device memory (arXiv:2606.
arXiv:2606. 08094v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) policies are typically shipped as Python/PyTorch stacks that assume a workstation-class GPU, a mismatch for the hardware on which robots actually run.
arXiv:2607. 01984v1 Announce Type: cross Abstract: Newer lightweight convolutional neural networks are often presented as improving predictive performance and deployment efficiency, but such claims require controlled evaluation.
arXiv:2604. 23466v2 Announce Type: replace Abstract: NVIDIA's CUDA Tile (CuTile) introduces a Python-based, tile-centric abstraction for GPU kernel development that aims to simplify programming while retaining Tensor Core and Tensor Memory Accelerator (TMA) efficiency on modern GPUs.