Copertina

On-Device Training Under 256KB Memory

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lin, Ji, Zhu, Ligeng, Chen, Wei-Ming, Wang, Wei-Chen, Gan, Chuang, Han, Song
Natura:	Preprint
Pubblicazione:	2022
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning
di: Lin, Ji, et al.
Pubblicazione: (2021)

Tiny Machine Learning: Progress and Futures
di: Lin, Ji, et al.
Pubblicazione: (2024)

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
di: Xie, Enze, et al.
Pubblicazione: (2025)

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers
di: Xie, Enze, et al.
Pubblicazione: (2024)

3D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning
di: Yang, Yuncong, et al.
Pubblicazione: (2024)

EfficientViT: Multi-Scale Linear Attention for High-Resolution Dense Prediction
di: Cai, Han, et al.
Pubblicazione: (2022)

DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space
di: He, Wenkun, et al.
Pubblicazione: (2025)

Fast Spatial Memory with Elastic Test-Time Training
di: Ma, Ziqiao, et al.
Pubblicazione: (2026)

EGM: Efficient Visual Grounding Language Models
di: Zhan, Guanqi, et al.
Pubblicazione: (2026)

AMC: AutoML for Model Compression and Acceleration on Mobile Devices
di: He, Yihui, et al.
Pubblicazione: (2018)

FoundationMotion: Auto-Labeling and Reasoning about Spatial Movement in Videos
di: Gan, Yulu, et al.
Pubblicazione: (2025)

Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation
di: Chen, Hanlin, et al.
Pubblicazione: (2026)

HAFormer: Unleashing the Power of Hierarchy-Aware Features for Lightweight Semantic Segmentation
di: Xu, Guoan, et al.
Pubblicazione: (2024)

Graph-Weighted Contrastive Learning for Semi-Supervised Hyperspectral Image Classification
di: Zhang, Yuqing, et al.
Pubblicazione: (2025)

Flow Intelligence: Robust Feature Matching via Temporal Signature Correlation
di: Wang, Jie, et al.
Pubblicazione: (2025)

Ella: Embodied Social Agents with Lifelong Memory
di: Zhang, Hongxin, et al.
Pubblicazione: (2025)

Training-Free Reasoning and Reflection in MLLMs
di: Wei, Hongchen, et al.
Pubblicazione: (2025)

Gaussians on a Diet: High-Quality Memory-Bounded 3D Gaussian Splatting Training
di: Zhang, Yangming, et al.
Pubblicazione: (2026)

LuciBot: Automated Robot Policy Learning from Generated Videos
di: Qiu, Xiaowen, et al.
Pubblicazione: (2025)

Target Recognition Algorithm for Monitoring Images in Electric Power Construction Process
di: Song, Hao, et al.
Pubblicazione: (2024)

TextPSG: Panoptic Scene Graph Generation from Textual Descriptions
di: Zhao, Chengyang, et al.
Pubblicazione: (2023)

SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization
di: Li, Wanhua, et al.
Pubblicazione: (2024)

VILA$^2$: VILA Augmented VILA
di: Fang, Yunhao, et al.
Pubblicazione: (2024)

Memory-Augmented SAM2 for Training-Free Surgical Video Segmentation
di: Yin, Ming, et al.
Pubblicazione: (2025)

MacFormer: Semantic Segmentation with Fine Object Boundaries
di: Xu, Guoan, et al.
Pubblicazione: (2024)

UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection
di: Gu, Zhaopeng, et al.
Pubblicazione: (2024)

OmniVLM: A Token-Compressed, Sub-Billion-Parameter Vision-Language Model for Efficient On-Device Inference
di: Chen, Wei, et al.
Pubblicazione: (2024)

Enhancing Quantization-Aware Training on Edge Devices via Relative Entropy Coreset Selection and Cascaded Layer Correction
di: Tong, Yujia, et al.
Pubblicazione: (2025)

STAMP: Training Explicit Memory for Mobile GUI Agents in Controllable and Scalable Virtual Environments
di: Wang, Junyang, et al.
Pubblicazione: (2026)

Shifting Adaptation from Weight Space to Memory Space: A Memory-Augmented Agent for Medical Image Segmentation
di: Chen, Bowen, et al.
Pubblicazione: (2026)

VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching
di: Ngo, Tuan Duc, et al.
Pubblicazione: (2026)

BachVid: Training-Free Video Generation with Consistent Background and Character
di: Yan, Han, et al.
Pubblicazione: (2025)

A Training-Free Framework for Open-Vocabulary Image Segmentation and Recognition with EfficientNet and CLIP
di: Dai, Ying, et al.
Pubblicazione: (2025)

Zero-Reference Joint Low-Light Enhancement and Deblurring via Visual Autoregressive Modeling with VLM-Derived Modulation
di: Dong, Wei, et al.
Pubblicazione: (2025)

I3DM: Implicit 3D-aware Memory Retrieval and Injection for Consistent Video Scene Generation
di: Li, Jia, et al.
Pubblicazione: (2026)

Context-measure: Contextualizing Metric for Camouflage
di: Wang, Chen-Yang, et al.
Pubblicazione: (2025)

Task-Specific Zero-shot Quantization-Aware Training for Object Detection
di: Li, Changhao, et al.
Pubblicazione: (2025)

Prompt-aware of Frame Sampling for Efficient Text-Video Retrieval
di: Zhang, Deyu, et al.
Pubblicazione: (2025)

FlexAttention for Efficient High-Resolution Vision-Language Models
di: Li, Junyan, et al.
Pubblicazione: (2024)

Face Adapter for Pre-Trained Diffusion Models with Fine-Grained ID and Attribute Control
di: Han, Yue, et al.
Pubblicazione: (2024)