Scaling Laws

Follow this field Ask about this field

Recent momentum

emerging

0 papers in the last 28 days · 0.0% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this field, kept on the site without email delivery.

Period ending 2026-09-21

12 new papers

A weekly snapshot of new work published in Scaling Laws.

Period ending 2026-09-14

8 new papers

A weekly snapshot of new work published in Scaling Laws.

Period ending 2026-09-07

16 new papers

A weekly snapshot of new work published in Scaling Laws.

Inside this field

Focused directions

Focused topic

Neural Scaling Laws

Within Scaling Laws

233 papersExplore

Focused topic

Scaling Laws

Within Scaling Laws

142 papersExplore

Focused topic

Test-Time Scaling

Within Scaling Laws

96 papersExplore

Focused topic

Exponents

Within Scaling Laws

36 papersExplore

Focused topic

Power-Law Distribution

Within Scaling Laws

18 papersExplore

471 papers

Latest in Scaling Laws

Browse all topics →

It Just Takes Two: Scaling Amortized Inference to Large Sets
May 8, 2026Antoine Wehenkel, Michael Kagan, Lukas Heinrich +1Generative Models Neural Scaling Laws
Scaling Categorical Flow Maps
May 8, 2026Oscar Davis, Anastasiia Filippova, Pierre Ablin +4Generative Flow Networks Flow Map
OrScale: Orthogonalised Optimization with Layer-Wise Trust-Ratio Scaling
May 8, 2026Yuxuan Lou, Yang YouMuon Optimizer Model Weights
Tracing Uncertainty in Language Model "Reasoning"
May 8, 2026Nils Grünefeld, Bertram Højer, Philipp Mondorf +5Large Language Model Uncertainty Large Language Model Reasoning
FS-I2P:A Hierarchical Focus-Sweep Registration Network with Dynamically Allocated Depth
May 8, 2026Zhixin Cheng, Yujia Chen, Xujing Tao +4Rgb-Depth Cameras Cross-Modal Learning
A Qualitative Test-Risk Mechanism for Scaling Behavior in Normalized Residual Networks
May 8, 2026Daning Cheng, Zeyu Liu, Jun Sun +4Residual Connections Scaling Laws
On the Invariance and Generality of Neural Scaling Laws
May 8, 2026Xing Han, Ziyin Liu, Suchi Saria +1Scaling Laws Invariance
Limits of Reliability and Scaling in Language Models
May 8, 2026Subhabrata MajumdarNeural Scaling Laws Trade-Off
Knowledge Transfer Scaling Laws for 3D Medical Imaging
May 7, 2026Ho Hin Lee, Dongna Du, Chu Wang +4Transfer Learning Medical Imaging
LLM-Guided Open Hypothesis Learning from Autonomous Scanning Probe Microscopy Experiments
May 7, 2026Boris Slautin, Utkarsh Pratiush, Yu Liu +2Hypothesis Generation Data-Driven Materials Discovery
E = T*H/(O+B): A Dimensionless Control Parameter for Mixture-of-Experts Ecology
May 7, 2026Qingjun ZhangMixture-of-Experts Models Exponents
BitCal-TTS: Bit-Calibrated Test-Time Scaling for Quantized Reasoning Models
May 7, 2026Sai Babu Patarlapalli, Surya Teja AvvaruConfidence Estimation Test-Time Scaling
A renormalization-group inspired lattice-based framework for piecewise generalized linear models
May 6, 2026Joshua C. ChangLogistic Regression Renormalization Group
ViTok-v2: Scaling Native Resolution Auto-Encoders to 5 Billion Parameters
May 6, 2026Philippe Hansen-Estruch, Jiahui Chen, Vivek Ramanujan +9Vision Transformer Autoregressive Image Generation
Sharp Capacity Thresholds in Linear Associative Memory: From Winner-Take-All to Listwise Retrieval
May 6, 2026Nicholas Barnfield, Juno Kim, Eshaan Nichani +2Dense Associative Memory Decision Thresholds
How Long Does Infinite Width Last? Signal Propagation in Long-Range Linear Recurrences
May 6, 2026Mariia SeleznovaInfinite-Width Gaussian Limit Scaling Laws
Gradient Scaling Effects in Adaptive Spectral PINNs for Stiff Nonlinear ODEs
May 6, 2026Isabela M. Yepes, Pavlos ProtopapasConventional Physics-Informed Neural Networks Ordinary Differential Equations
Stream-T1: Test-Time Scaling for Streaming Video Generation
May 6, 2026Yijing Tu, Shaojin Wu, Mengqi Huang +4High-Fidelity Video Generation Few-Step Generation
The Scaling Properties of Implicit Deductive Reasoning in Transformers
May 5, 2026Enrico Vompa, Tanel TammetTransformer Architectures Theorem
Safety and accuracy follow different scaling laws in clinical large language models
May 5, 2026Sebastian Wind, Tri-Thien Nguyen, Jeta Sopa +9Large Language Model Safety Inference-Time
NeurIPS Should Require Reproducibility Standards for Frontier AI Safety Claims
May 5, 2026Varad Vishwarupe, Nigel Shadbolt, Marina Jirotka +1Artificial Intelligence Safety Reproducibility
InfoLaw: Information Scaling Laws for Large Language Models with Quality-Weighted Mixture Data and Repetition
May 4, 2026Fengze Liu, Weidong Zhou, Binbin Liu +7Large Language Model Pretraining Scaling Laws
DP-SfM: Dual-Pixel Structure-from-Motion without Scale Ambiguity
May 3, 2026Lilika Makabe, Kohei Ashida, Hiroaki Santo +2Structure-From-Motion Motion Blur
Prescriptive Scaling Laws for Data Constrained Training
May 2, 2026Justin Lovelace, Christian Belardi, Srivatsa Kundurthy +2Scaling Laws Capacity
Multi-Agent Reasoning Improves Compute Efficiency: Pareto-Optimal Test-Time Scaling
May 2, 2026Florian Valentin Wunderlich, Lars Benedikt Kaesberg, Jan Philip Wahle +2Test-Time Scaling Multi-Agent Reasoning
Visual Implicit Autoregressive Modeling
May 2, 2026Pengfei Jiang, Jixiang Luo, Luxi Lin +2Visual Autoregressive Models Autoregressive Image Generation
Themis: Training Robust Multilingual Code Reward Models for Flexible Multi-Criteria Scoring
May 1, 2026Indraneil Paul, Goran Glavaš, Iryna GurevychProcess Reward Modeling Test-Time Scaling
Stereo Multistage Spatial Attention for Real-Time Mobile Manipulation Under Visual Scale Variation and Disturbances
May 1, 2026Xianbo Cai, Hideyuki Ichiwara, Hyogo Hiruma +3Real-World Manipulation Tasks Spatial Attention
Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning
May 1, 2026Chengshuai Shi, Wenzhe Li, Xinran Liang +10Cross-Domain Generalization Neural Scaling Laws
A unified perspective on fine-tuning and sampling with diffusion and flow models
Apr 30, 2026Carles Domingo-Enrich, Yuanqi Du, Michael S. AlbergoAdjoint Matching Generative Models
Exponential families from a single KL identity
Apr 30, 2026Marc DymetmanKullback-Leibler Divergence Exponents
Dynamic Scaled Gradient Descent for Stable Fine-Tuning for Classifications
Apr 30, 2026Nghia Bui, Lijing WangGradient Descent Class Imbalance
ScaleBox: Enabling High-Fidelity and Scalable Code Verification for Large Language Models
Apr 30, 2026Jiasheng Zheng, Xin Zheng, Boxi Cao +8Large Models Codebooks
Learning Rate Transfer in Normalized Transformers
Apr 29, 2026Boris Shigida, Boris Hanin, Andrey GromovLearning Rates Transfer Learning
Stochastic Scaling Limits and Synchronization by Noise in Deep Transformer Models
Apr 29, 2026Andrea Agazzi, Giuseppe Bruno, Eloy Mosig García +2Transformer Architectures Stochastic Differential Equations
When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling
Apr 29, 2026Zhimin Lin, Yixin Ji, Jinpeng Li +5Test-Time Scaling Reasoning Benchmark
Large-scale semi-supervised learning with online spectral graph sparsification
Apr 29, 2026Daniele Calandriello, Alessandro Lazaric, Michal ValkoSemi-Supervised Learning Sparsity
Do Larger Models Really Win in Drug Discovery? A Benchmark Assessment of Model Scaling in AI-Driven Molecular Property and Activity Prediction
Apr 29, 2026Jinjiang Guo, Sheng DingDrug Discovery Clinical Prediction
Granularity-Regulated Adaptive Computational Efficiency for Optimal Verification in Test-Time Scaling
Apr 28, 2026Ardit Krasniqi, Luan Vejsiu, Elira DervishiTest-Time Scaling Verifier
LatentDiff: Scaling Semantic Dataset Comparison to Millions of Images
Apr 28, 2026James Flora, Kowshik Thopalli, Akshay R. Kulkarni +2Vision Encoders Neural Scaling Laws
Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling
Apr 28, 2026Ocean Monjur, Shahriar Kabir Nahin, Anshuman ChhabraHeterogeneous Pruning Scores Test-Time Scaling
Compute Aligned Training: Optimizing for Test Time Inference
Apr 27, 2026Adam Ousherovitch, Ambuj TewariTest-Time Scaling Large Models
Long-Context Aware Upcycling: A New Frontier for Hybrid LLM Scaling
Apr 27, 2026Parsa Ashrafi Fashi, Utkarsh Saxena, Mehdi Rezagholizadeh +7Efficient Long-Context Inference Neural Scaling Laws
Scaling Properties of Continuous Diffusion Spoken Language Models
Apr 27, 2026Jason Ramapuram, Eeshan Gunesh Dhekane, Amitis Shidani +6Diffusion Language Models Scaling Laws
AmaraSpatial-10K: A Spatially and Semantically Aligned 3D Dataset for Spatial Computing and Embodied AI
Apr 24, 2026Mohammad Sadegh Salehi, Alex Perkins, Igor Maurell +2Real3D-Ad Datasets Spatial Question Answering
The Power of Power Law: Asymmetry Enables Compositional Reasoning
Apr 24, 2026Zixuan Wang, Xingyu Dang, Jason D. Lee +1Power-Law Distribution Distributional Learning
Spend Less, Fit Better: Budget-Efficient Scaling Law Fitting via Active Experiment Selection
Apr 24, 2026Sijie Li, Shanda Li, Haowei Lin +3Bayesian Experimental Design Scaling Laws
A Nationwide Japanese Medical Claims Foundation Model: Balancing Model Scaling and Task-Specific Computational Efficiency
Apr 24, 2026Nanae Aratake, Taisei Tosaki, Yuji Okamoto +5Electronic Health Record Foundation Models Wireless Foundation Models
Beyond N-gram: Data-Aware X-GRAM Extraction for Efficient Embedding Parameter Scaling
Apr 23, 2026Yilong Chen, Yanxi Xie, Zitian Gao +10N$-Grams Features Quadratic Attention
The First Challenge on Remote Sensing Infrared Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview
Apr 23, 2026Kai Liu, Haoyang Yue, Zeli Lin +65Hyperspectral Image Super-Resolution Infrared
CI-Work: Benchmarking Contextual Integrity in Enterprise LLM Agents
Apr 23, 2026Wenjie Fu, Xiaoting Qin, Jue Zhang +5Data Leakage Large Language Model Safety
How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models
Apr 22, 2026Kristian Schwethelm, Daniel Rueckert, Georgios KaissisRecurrence Large Models
FASTER: Value-Guided Sampling for Fast RL
Apr 21, 2026Perry Dong, Alexander Swerdlow, Dorsa Sadigh +1Diffusion Policies Deep Reinforcement Learning
Predicting Scale-Up of Metal-Organic Framework Syntheses with Large Language Models
Apr 21, 2026Peter Walther, Hongrui Sheng, Xinxin Liu +7Automated Synthesis Techniques Neural Scaling Laws
Evaluation-driven Scaling for Scientific Discovery
Apr 21, 2026Haotian Ye, Haowei Lin, Jingyi Tang +22Scientific Discovery Large Models
Nexusformer: Nonlinear Attention Expansion for Stable and Inheritable Transformer Scaling
Apr 21, 2026Weijie Zhao, Mingquan Liu, Bolun Wang +4Mixformer Softmax Attention
Sessa: Selective State Space Attention
Apr 20, 2026Liubomyr HorbatkoEfficient Long-Context Inference Sequence Modeling
Bridging the Reasoning Gap in Vietnamese with Small Language Models via Test-Time Scaling
Apr 20, 2026Bui The Trung, Do Minh Duc, Nguyen Van Vinh +1Small Language Models Large Language Model Reasoning
How Much Data is Enough? The Zeta Law of Discoverability in Biomedical Data, featuring the enigmatic Riemann zeta function
Apr 19, 2026Paul M. ThompsonScaling Laws Sample Size
The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview
Apr 19, 2026Jiatong Li, Zheng Chen, Kai Liu +91Generative Super-Resolution Smartphone Photographs

May 8, 2026 · cs.LGJ/K move · Enter open · S save

It Just Takes Two: Scaling Amortized Inference to Large Sets

Antoine Wehenkel, Michael Kagan, Lukas Heinrich, Chris Pollard

Apple · SLAC National Accelerator Laboratory · TU München · University of Warwick

Neural posterior estimation has emerged as a powerful tool for amortized inference, with growing adoption across scientific and applied domains. In many of these applications, the conditioning variable is a set of observations whose elements depend not only on the target but also on unknown factors shared across the set. Optimal inference therefore requires treating the set jointly, which in turn requires training the estimator at the deployment set size -- a regime where memory and compute quickly become prohibitive. We introduce a simple, theoretically grounded strategy that decouples representation learning from posterior modeling. Our method trains a mean-pool Deep Set on sets of size at most two, producing an encoder that generalizes to arbitrary set sizes. The inference head is then finetuned on pre-aggregated embeddings, making training cost essentially independent of the deployment set size N. Across scalar, image, multi-view 3D, molecular, and high-dimensional conditional generation benchmarks with N in the thousands, our approach matches or outperforms standard baselines at a fraction of the compute.

Generative Models Neural Scaling Laws

Open paper Ask about it PDF