Copertina

Continued AI Scaling Requires Repeated Efficiency Doublings

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Lu, Chien-Ping
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

The Race to Efficiency: A New Perspective on AI Scaling Laws
di: Lu, Chien-Ping
Pubblicazione: (2025)

Scaling Context Requires Rethinking Attention
di: Gelada, Carles, et al.
Pubblicazione: (2025)

Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
di: Brown, Bradley, et al.
Pubblicazione: (2024)

When Data Is Scarce: Scaling Sparse Language Models with Repeated Training
di: Wu, Boqian, et al.
Pubblicazione: (2026)

Compute Requirements for Algorithmic Innovation in Frontier AI Models
di: Barnett, Peter
Pubblicazione: (2025)

Distill, Forget, Repeat: A Framework for Continual Unlearning in Text-to-Image Diffusion Models
di: George, Naveen, et al.
Pubblicazione: (2025)

Enhancing Parameter Efficiency and Generalization in Large-Scale Models: A Regularized and Masked Low-Rank Adaptation Approach
di: Mao, Yuzhu, et al.
Pubblicazione: (2024)

Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification
di: Feng, Yunzhen, et al.
Pubblicazione: (2024)

Closed-Form Concept Erasure via Double Projections
di: Zhang, Chi, et al.
Pubblicazione: (2026)

Continual Domain Adversarial Adaptation via Double-Head Discriminators
di: Shen, Yan, et al.
Pubblicazione: (2024)

Improving Continual Learning Performance and Efficiency with Auxiliary Classifiers
di: Szatkowski, Filip, et al.
Pubblicazione: (2024)

Divide and Learn: Multi-Objective Combinatorial Optimization at Scale
di: Singh, Esha, et al.
Pubblicazione: (2026)

The Importance of Being Lazy: Scaling Limits of Continual Learning
di: Graldi, Jacopo, et al.
Pubblicazione: (2025)

The Struggle Between Continuation and Refusal: A Mechanistic Analysis of the Continuation-Triggered Jailbreak in LLMs
di: Deng, Yonghong, et al.
Pubblicazione: (2026)

Revisiting Training Scale: An Empirical Study of Token Count, Power Consumption, and Parameter Efficiency
di: Dwyer, Joe
Pubblicazione: (2026)

Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor
di: Olteanu, Alexandra, et al.
Pubblicazione: (2025)

AI-Slop to AI-Polish? Aligning Language Models through Edit-Based Writing Rewards and Test-time Computation
di: Chakrabarty, Tuhin, et al.
Pubblicazione: (2025)

Scaling Continuous Latent Variable Models as Probabilistic Integral Circuits
di: Gala, Gennaro, et al.
Pubblicazione: (2024)

Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning
di: Liu, Zheyuan, et al.
Pubblicazione: (2023)

Noisy PDE Training Requires Bigger PINNs
di: Andre-Sloan, Sebastien, et al.
Pubblicazione: (2025)

Energy Efficiency in AI for 5G and Beyond: A DeepRx Case Study
di: Lbath, Amine, et al.
Pubblicazione: (2025)

CauScale: Neural Causal Discovery at Scale
di: Peng, Bo, et al.
Pubblicazione: (2026)

Position: AI Scaling: From Up to Down and Out
di: Wang, Yunke, et al.
Pubblicazione: (2025)

Scaling Algorithm Distillation for Continuous Control with Mamba
di: Beaussant, Samuel, et al.
Pubblicazione: (2025)

Optimal Scaling Laws for Efficiency Gains in a Theoretical Transformer-Augmented Sectional MoE Framework
di: Sane, Soham
Pubblicazione: (2025)

Understanding Adam Requires Better Rotation Dependent Assumptions
di: Zhang, Tianyue H., et al.
Pubblicazione: (2024)

Evaluating LLM Safety Under Repeated Inference via Accelerated Prompt Stress Testing
di: Broadwater, Keita
Pubblicazione: (2026)

Counterfactual Explanations for Continuous Action Reinforcement Learning
di: Dong, Shuyang, et al.
Pubblicazione: (2025)

Analysis of the Memorization and Generalization Capabilities of AI Agents: Are Continual Learners Robust?
di: Kim, Minsu, et al.
Pubblicazione: (2023)

Agential AI for Integrated Continual Learning, Deliberative Behavior, and Comprehensible Models
di: Erden, Zeki Doruk, et al.
Pubblicazione: (2025)

ReqBrain: Task-Specific Instruction Tuning of LLMs for AI-Assisted Requirements Generation
di: Habib, Mohammad Kasra, et al.
Pubblicazione: (2025)

Natural Language Requirements Testability Measurement Based on Requirement Smells
di: Zakeri-Nasrabadi, Morteza, et al.
Pubblicazione: (2024)

Integrated Gradient Correlation: a Dataset-wise Attribution Method
di: Lelièvre, Pierre, et al.
Pubblicazione: (2024)

Position: State-of-the-Art Claims Require State-of-the-Art Evidence
di: Oh, YongKyung
Pubblicazione: (2026)

Breaking the Blocks: Continuous Low-Rank Decomposed Scaling for Unified LLM Quantization and Adaptation
di: Tang, Pingzhi, et al.
Pubblicazione: (2026)

Block-Based Double Decoders
di: Labovich, Asher, et al.
Pubblicazione: (2026)

Causal Policy Learning in Reinforcement Learning: Backdoor-Adjusted Soft Actor-Critic
di: Vo, Thanh Vinh, et al.
Pubblicazione: (2025)

Deep Double Q-learning
di: Nagarajan, Prabhat, et al.
Pubblicazione: (2025)

Teaching AI to Remember: Insights from Brain-Inspired Replay in Continual Learning
di: Kim, Jina
Pubblicazione: (2025)

On the Utility of Accounting for Human Beliefs about AI Intention in Human-AI Collaboration
di: Yu, Guanghui, et al.
Pubblicazione: (2024)