Copertina

Don't Run with Scissors: Pruning Breaks VLA Models but They Can Be Recovered

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Jabbour, Jason, Kim, Dong-Ki, Smith, Max, Patrikar, Jay, Ghosal, Radhika, Wang, Youhui, Agha, Ali, Reddi, Vijay Janapa, Omidshafiei, Shayegan
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Robotics Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Generative AI Agents in Autonomous Machines: A Safety Perspective
di: Jabbour, Jason, et al.
Pubblicazione: (2024)

Multi-Agent Reinforcement Learning for Sample-Efficient Deep Neural Network Mapping
di: Krishnan, Srivatsan, et al.
Pubblicazione: (2025)

GrndCtrl: Grounding World Models via Self-Supervised Reward Alignment
di: He, Haoyang, et al.
Pubblicazione: (2025)

Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers
di: Chen, Yutian, et al.
Pubblicazione: (2025)

TinyTorch: Building Machine Learning Systems from First Principles
di: Reddi, Vijay Janapa
Pubblicazione: (2026)

Delay-Aware Diffusion Policy: Bridging the Observation-Execution Gap in Dynamic Tasks
di: Liao, Aileen, et al.
Pubblicazione: (2025)

SocratiQ: A Generative AI-Powered Learning Companion for Personalized Education and Broader Accessibility
di: Jabbour, Jason, et al.
Pubblicazione: (2025)

StageACT: Stage-Conditioned Imitation for Robust Humanoid Door Opening
di: Lee, Moonyoung, et al.
Pubblicazione: (2025)

The Magnificent Seven Challenges and Opportunities in Domain-Specific Accelerator Design for Autonomous Systems
di: Neuman, Sabrina M., et al.
Pubblicazione: (2024)

Collision Avoidance Verification of Multiagent Systems with Learned Policies
di: Dong, Zihao, et al.
Pubblicazione: (2024)

VENTURA: Adapting Image Diffusion Models for Unified Task Conditioned Navigation
di: Zhang, Arthur, et al.
Pubblicazione: (2025)

FedStaleWeight: Buffered Asynchronous Federated Learning with Fair Aggregation via Staleness Reweighting
di: Ma, Jeffrey, et al.
Pubblicazione: (2024)

How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perf
di: Jiang, Wenqi, et al.
Pubblicazione: (2026)

Generative AI in Embodied Systems: System-Level Analysis of Performance, Efficiency and Scalability
di: Wan, Zishen, et al.
Pubblicazione: (2025)

Don't Be Greedy, Just Relax! Pruning LLMs via Frank-Wolfe
di: Roux, Christophe, et al.
Pubblicazione: (2025)

SayComply: Grounding Field Robotic Tasks in Operational Compliance through Retrieval-Based Language Models
di: Ginting, Muhammad Fadhil, et al.
Pubblicazione: (2024)

Tabula: Efficiently Computing Nonlinear Activation Functions for Secure Neural Network Inference
di: Lam, Maximilian, et al.
Pubblicazione: (2022)

SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?
di: Ma, Jeffrey Jian, et al.
Pubblicazione: (2025)

Don't Blind Your VLA: Aligning Visual Representations for OOD Generalization
di: Kachaev, Nikita, et al.
Pubblicazione: (2025)

Don’t Burn it Here
di: Walsh, Ed, et al.
Pubblicazione: (2026)

Don't Look Twice: Faster Video Transformers with Run-Length Tokenization
di: Choudhury, Rohan, et al.
Pubblicazione: (2024)

World Model Failure Classification and Anomaly Detection for Autonomous Inspection
di: Ho, Michelle, et al.
Pubblicazione: (2026)

Condense, Don't Just Prune: Enhancing Efficiency and Performance in MoE Layer Pruning
di: Cao, Mingyu, et al.
Pubblicazione: (2024)

TinyML Security: Exploring Vulnerabilities in Resource-Constrained Machine Learning Systems
di: Huckelberry, Jacob, et al.
Pubblicazione: (2024)

What Papers Don't Tell You: Recovering Tacit Knowledge for Automated Paper Reproduction
di: Li, Lehui, et al.
Pubblicazione: (2026)

Planning with Sketch-Guided Verification for Physics-Aware Video Generation
di: Huang, Yidong, et al.
Pubblicazione: (2025)

Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural Networks
di: Berghe, Korneel Van den, et al.
Pubblicazione: (2025)

From Seed to Harvest: Augmenting Human Creativity with AI for Red-teaming Text-to-Image Models
di: Quaye, Jessica, et al.
Pubblicazione: (2025)

Materiality and Risk in the Age of Pervasive AI Sensors
di: Sloane, Mona, et al.
Pubblicazione: (2024)

Can AI Assistants Know What They Don't Know?
di: Cheng, Qinyuan, et al.
Pubblicazione: (2024)

Fine-Tuned LLMs Know They Don't Know: A Parameter-Efficient Approach to Recovering Honesty
di: Shi, Zeyu, et al.
Pubblicazione: (2025)

World2Rules: A Neuro-Symbolic Framework for Learning World-Governing Safety Rules for Aviation
di: Wang, Haichuan, et al.
Pubblicazione: (2026)

AutoODD: Agentic Audits via Bayesian Red Teaming in Black-Box Models
di: Martin, Rebecca, et al.
Pubblicazione: (2025)

Frictional Agent Alignment Framework: Slow Down and Don't Break Things
di: Nath, Abhijnan, et al.
Pubblicazione: (2025)

QuArch: A Question-Answering Dataset for AI Agents in Computer Architecture
di: Prakash, Shvetank, et al.
Pubblicazione: (2025)

When Respondents Don't Care Anymore: Identifying the Onset of Careless Responding
di: Welz, Max, et al.
Pubblicazione: (2023)

Don't be salesmen
Pubblicazione: (1997)

Don't Retrain, Just Reuse: Recovering Dual-Target Molecules from Single-Target Diffusion Models
di: Zeng, Qingyuan, et al.
Pubblicazione: (2026)

Don't Break the Cache: An Evaluation of Prompt Caching for Long-Horizon Agentic Tasks
di: Lumer, Elias, et al.
Pubblicazione: (2026)

On Minimization and Learning of Deterministic $ω$-Automata in the Presence of Don't Care Words
di: Löding, Christof, et al.
Pubblicazione: (2022)