[NeurIPS'25] FreqExit: Enabling Early-Exit Inference for Visual Autoregressive Models via Frequency-Aware Guidance
-
Updated
Dec 15, 2025 - Python
#
dynamic-inference
Here are 13 public repositories matching this topic...
Code for paper "TLEE: Temporal-wise and Layer-wise Early Exiting Network for Efficient Video Recognition on Edge Devices"
inference dnn deep-learning-algorithms resnet action-recognition content-analysis video-recognition video-analytics frame-analysis on-device-ai early-exiting inference-acceleration dynamic-inference dnn-inference
-
Updated
Jul 22, 2026 - Python
[IROS 2021] ADD: A Fine-grained Dynamic Inference Architecture for Semantic Image Segmentation
pytorch densenet darts deeplab neural-architecture-search msdnet auto-deeplab semantic-image-segmentation dynamic-inference
-
Updated
May 3, 2022 - Python
Code for paper "Joint Adaptive Resolution Selection and Conditional Early Exiting for Efficient Video Recognition on Edge Devices"
bigdata inference dnn deep-learning-algorithms resnet action-recognition content-analysis video-recognition video-analytics ucf101 hmdb51 frame-analysis resolution-cnn early-exiting inference-acceleration dynamic-inference dnn-inference
-
Updated
Jul 22, 2026 - Python
A collection of awesome papers in Deep Learning, with a one sentence summary.
machine-learning computer-vision deep-learning ml cnn style-transfer transfer-learning papers gans data-augmentation robustness styletransfer continual-learning papers-with-code dynamic-inference sentence-summaries
-
Updated
Mar 4, 2021
Convenient Convert CRAFT Text detection pretrain Pytorch model into TensorRT engine directly, without ONNX step between
-
Updated
Aug 18, 2021 - Python
Adaptive model-capacity orchestration — dynamically select, load, cache, and budget adapters, experts, models, and future model blocks.
machine-learning research inference model-selection lora peft mixture-of-experts conditional-computation dynamic-inference ml-systems llm llm-inference semantic-routing adaptive-compute model-routing capacity-routing
-
Updated
Sep 28, 2026 - Python
NSGA-II search framework for CIFAR-10 big/little dynamic inference cascades under embedded memory constraints.
-
Updated
May 28, 2026 - Python
Pre-to-Post Prediction Refinement (P2PR) for efficient multimodal inference with sample-wise routing.
-
Updated
Sep 15, 2026
This work unifies 150+ studies on early-exit and dynamic inference models, analyzing their architectures, training strategies, exit policies, application domain, and open challenges and future directions.
-
Updated
Nov 3, 2025
Dynamic Activation of Neural Network Blocks Based on Graph Representation for Energy-Efficient Inference
machine-learning deep-learning pytorch neural-networks resnet pruning cifar research-paper cifar10 resnet-50 cifar100 cifar-10 cifar-100 paper-implementation dynamic-inference restnet50 restnet18 restnet-18
-
Updated
Jul 3, 2026 - Python
Recurrent sparse vision on SparseFormer: latent tokens gather evidence over rounds, with a memory between rounds and early exit
computer-vision pytorch early-exit dynamic-inference efficient-deep-learning vision-transformer sparseformer
-
Updated
Sep 30, 2026 - Python
Object A: MoE orbit prefetch — source+math+215KB trajectories+plots+sparse DeepSeek runtime (Apache-2.0). Analyze without weights; credit on substantial use.
pytorch moe memory-efficient mixture-of-experts huggingface dynamic-inference safetensors llm-inference deepseek sparse-moe expert-prefetch expert-offload
-
Updated
Jul 29, 2026 - Python
Add this topic to your repo
To associate your repository with the dynamic-inference topic, visit your repo's landing page and select "manage topics."