Dysl-vla：Official code for "DySL-VLA: Efficient Vision-Language-Action Model Inference via Dynamic-Static Layer-Skipping for Robot Manipulation". A framework that dynamically skips VLA layers based on action importance, achieving 3.75× speedup and 85.7× training reduction on robotic manipulation tasks.
☆25Jul 9, 2026Updated 2 months ago
Alternatives and similar repositories for DYSL_VLA
Users that are interested in DYSL_VLA are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- SRSA: Skill Retrieval and Adaptation for Robotic Assembly Tasks☆21Mar 25, 2026Updated 5 months ago
- [ECCV 2026] Official implementation of CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding.☆52Sep 15, 2025Updated last year
- Code release for LightMamba accepted by DATE 2025☆28Oct 18, 2025Updated 11 months ago
- SparAlloc: A Simple and Modular Framework for Decoupled Sparsity Allocation in Layerwise Pruning for LLM☆16Jun 5, 2025Updated last year
- [ICLR 2026] Block-wise Adaptive Caching for Accelerating Diffusion Policy☆18Jan 27, 2026Updated 7 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Source code & scripts for experimental characterization and demonstration of performing NOT and up to 16-input AND, NAND, OR, and NOR ope…☆16Apr 9, 2024Updated 2 years ago
- ☆44Sep 5, 2026Updated 2 weeks ago
- [ICLR 2026] Official implementation of "Enhancing Multi-Image Understanding Through Delimiter Token Scaling"☆17Jul 10, 2026Updated 2 months ago
- [ICLR 2026 Oral] RAIN-Merging☆15Mar 9, 2026Updated 6 months ago
- [ICLR 2026] Offical implementation of "OBS-Diff".☆67Mar 5, 2026Updated 6 months ago
- [arxiv 2025] SparseSSM: Efficient Selective Structured State Space Models Can Be Pruned in One-Shot☆23Oct 8, 2025Updated 11 months ago
- [NeurIPS'25] FreqExit: Enabling Early-Exit Inference for Visual Autoregressive Models via Frequency-Aware Guidance☆21Dec 15, 2025Updated 9 months ago
- ☆16Jan 27, 2026Updated 7 months ago
- ☆19Jan 29, 2026Updated 7 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A toolbox for tracking and visualizing the real-world deployment process of your VLA models.☆25Jun 11, 2026Updated 3 months ago
- [ICLR 2026] MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding☆23Feb 27, 2026Updated 6 months ago
- Official implementation of HEAD CoRL 2025☆18Aug 9, 2025Updated last year
- 同济大学 Slides 模板，适用于 Powerpoint，Google Slides，提供适合工科生的 slides 设计素材与思路☆22Oct 6, 2025Updated 11 months ago
- Action-Guided Knowledge Distillation for VLA Models☆20Dec 16, 2025Updated 9 months ago
- [WIP] Code for LangToMo☆21Mar 19, 2026Updated 6 months ago
- ☆42Jul 28, 2026Updated last month
- Reshaping Action Error Distributions for Reliable Vision-Language-Action Models☆17Feb 5, 2026Updated 7 months ago
- The official implement of VITA, VITA15, LongVITA, VITA-Audio, VITA-VLA, and VITA-E.☆166Oct 28, 2025Updated 10 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- A paper list about Token Merge, Reduce, Resample, Drop for MLLMs.☆90Oct 26, 2025Updated 10 months ago
- High-level Python Particle Sequential Convex Programming Model Predictive Control (SCP PMPC) interface☆16Oct 30, 2023Updated 2 years ago
- [TPAMI 2023] Object Affinity Learning: Towards Annotation-free Instance Segmentation☆14Sep 14, 2023Updated 3 years ago
- Code of paper "HyperVLA: Efficient Inference in Vision-Language-Action Models via Hypernetworks"☆26Oct 8, 2025Updated 11 months ago
- ☆18Sep 7, 2026Updated last week
- [CVPR 2026] EarlyTom: Early Token Compression Completes Fast Video Understanding☆37Jun 22, 2026Updated 2 months ago
- [ICML 2026] This repo is the official implementation of "LangForce : Bayesian Decomposition of Vision Language Action Models via Latent …☆80Jul 29, 2026Updated last month
- ☆51Nov 26, 2025Updated 9 months ago
- [AAAI 2026] Official code for MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Man…☆70Jul 31, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Action aware Dynamic Pruning for Efficient Vision Language Action Manipulation☆28Feb 28, 2026Updated 6 months ago
- ☆43Jun 8, 2026Updated 3 months ago
- [CVPR 2024] DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Model☆19Apr 16, 2024Updated 2 years ago
- [ICML26] Official Repo for WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching☆43Jul 23, 2026Updated last month
- ☆17Aug 13, 2025Updated last year
- Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation (NeurIPS 23)☆12May 7, 2025Updated last year
- Official implementation of HEAD CoRL 2025☆27Aug 22, 2025Updated last year