arXiv Machine Learning

FORGE: Forward-Only Test-Time Adaptation for Integer-Only Vision Models on Microcontrollers

FORGE is a forward‑only test‑time adaptation technique designed for integer‑only vision models running on microcontrollers. It restores batch‑normalization statistics after BN folding by re‑normalizing each convolution’s per‑channel output using only forward‑pass estimates, enabling adaptation on deployed, folded integer models. The method achieves accuracy gains comparable to gradient‑based TENT, requires adapting only a few layers, works with single‑sample streaming, and has been validated on an ESP32‑S3 with minimal energy and latency overhead.

arXiv AI

2d ago

Adapting Without Gradients: Affine Statistics Transport and What Its Certificate Can Tell You

The paper introduces CASTER, a gradient‑free test‑time adaptation method that keeps the model frozen by storing source class statistics in a discriminative subspace and applying an affine transformation estimated from target‑batch moments. CASTER avoids backward passes, optimizer state, and large feature banks, outperforming k‑NN on frozen features in most backbone‑dataset settings while using far less memory. The authors also propose a residual‑to‑margin transportability certificate that flags when affine transport is unreliable, and demonstrate that gating based on this certificate can recover performance losses.

By Salim Khazem, Ibrahim Mohamed Serouis

safety

arXiv Computer Vision

Aug 25

ZOTTA: Test-Time Adaptation with Gradient-Free Zeroth-Order Optimization

arXiv:2603.14254v2 Announce Type: replace Abstract: Test-time adaptation (TTA) aims to improve model robustness under distribution shifts by adapting to unlabeled test data, but most existing methods...

By Ronghao Zhang, Shuaicheng Niu, Qi Deng, Yanjie Dong, Jian Chen, Runhao Zeng

efficiency safety

Hugging Face Trending Papers

Jul 2

Efficient PEFT Methods with Adaptive Checkpointing for Vision Models and VLMs on Resource Constrained Consumer-GPUs

Modern pretrained vision models achieve strong accuracy but demand substantial GPU memory for fine-tuning, making edge deployment impractical. This paper compares five parameter-efficient fine-tuning (PEFT) methods (Full FT, LoRA, AdaLoRA, QLoRA, BitFit) on Transformers- (ViT-Small, TinyViT) and Mamba-based vision backbones (Vim-Small, MambaVision-T) under an on-device VRAM budget (e.

llms fine-tuning efficiency

arXiv AI

Jul 7

Fusion: A Framework for Unified Sequential Token AdaptatIon in VisiOn TraNsformers

arXiv:2607. 02612v1 Announce Type: cross Abstract: Vision Transformers achieve strong image classification accuracy but process all image regions with nearly the same computation, even when many regions are redundant or uninformative.

By Aravind Pradeep, Samira Nazari, Mahdi Taheri, Christian Herglotz

llms computer-vision efficiency benchmarks

arXiv Machine Learning

Jun 17

From Compression to Deployment: Real-Time and Energy-Efficient FastGRNN on Ultra-Constrained Microcontrollers

arXiv:2606. 17249v1 Announce Type: cross Abstract: The dominant trajectory of modern machine learning has been to scale up: larger models, larger accelerators, larger memory budgets.

By Emre Can Kizilates

efficiency

arXiv AI

Jul 17

A Modern Multimodal Assistant on a 6 GB 2011 GPU: Stage-Validated, All-GPU CUDA Inference for Fermi

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.

By A. C. Opus, J. Q. Lu

rag multimodal benchmarks

arXiv AI

Jul 3

Do Newer Lightweight CNNs Perform Better Under Resource Constraints? A Controlled Multigenerational Study of Architecture, Initialization, Training Budget, and Efficiency

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.

By Tasnim Shahriar

arXiv Machine Learning

Jun 16

CREST: Deployment-Realistic Hardware-in-the-Loop NAS for Embedded Sensing Systems

arXiv:2606. 15004v1 Announce Type: cross Abstract: Deploying neural networks on low-power microcontrollers (MCUs) requires selecting model architectures under tight memory, latency, and energy constraints.

By Joseph Q. Zales, Pragya Sharma, Mani Srivastava

efficiency

arXiv Machine Learning

Jul 31

WIDE: Boosting Adaptive LLM Inference via Token-level Dynamic Width Pruning

arXiv:2607. 28418v1 Announce Type: cross Abstract: Pruning is a promising approach for improving the efficiency of LLMs.

By Haozhe Hu, Hao Wu, Peiran Yin, Chao Han, Yunpu Ma, Xiaoyu Shen

llms nlp efficiency benchmarks

arXiv Machine Learning

Aug 4

AdaDINO: Context-Adaptive DINO-Distilled Vision Foundation Models for Efficient Open-Vocabulary Edge Inference

arXiv:2604. 15622v3 Announce Type: replace-cross Abstract: Always-on contextual AI runs language-aligned vision foundation models (VFMs) on edge devices, where the on-device model is the dominant continuous compute cost under strict latency and power limits.

By Yiwei Zhao, Yi Zheng, Huapeng Su, Jieyu Lin, Stefano Ambrogio, Cijo Jose, Michael Ramamonjisoa, Patrick Labatut, Barbara De Salvo, Chiao Liu, Phillip B. Gibbons, Ziyun Li

llms computer-vision multimodal

arXiv Machine Learning

Jul 8

BitLogic: Training Framework for Gradient-Based FPGA-Native Neural Networks

arXiv:2602. 07400v2 Announce Type: replace Abstract: Gradient-based LUT- and logic-gate-based neural networks (LUTNet, LogicNets, DiffLogic, PolyLUT, NeuraLUT, WARP-LUT, DWN, LILogicNet, LightLUT) replace multiply-accumulate arithmetic with Boolean lookups.

By Simon B\"uhrer, Andreas Plesner, Aczel Till, Roger Wattenhofer

efficiency

arXiv Machine Learning

Jul 10

Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction Tuning

arXiv:2603. 12478v2 Announce Type: replace-cross Abstract: Multimodal instruction tuning is often compute-inefficient because training budgets are spread across large mixed image-video pools whose utility is highly uneven.

By Rujie Wu, Haozhe Zhao, Hai Ci, Yizhou Wang

fine-tuning multimodal benchmarks

Related stories