Factor

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

2 new papers

A weekly snapshot of new work published in Factor.

Period ending 2026-09-14

2 new papers

A weekly snapshot of new work published in Factor.

Inside this field

Focused directions

Focused topic

Factor

Within Factor

51 papersExplore

Focused topic

Exploratory Factor Analysis

Within Factor

49 papersExplore

Focused topic

Universal Factorization Problem

Within Factor

18 papersExplore

109 papers

Latest in Factor

Browse all topics →

Compositional Generalization in Autoregressive Models via Logit Composition
May 27, 2026Aakash Kumar, Maria Sofia Bucarelli, Emanuele NataleAutoregressive Model Compositionality
On the Detection of Commutative Factors in Factor Graphs: Necessary and Sufficient Conditions
May 26, 2026Malte Luttermann, Ralf Möller, Marcel GehrkeFactor Graphs Factor
BioFact-MoE: Biologically Factorized Mixture of Experts for Vision-Language Prognostic Modeling in Hepatocellular Carcinoma
May 25, 2026Junlin Yang, Tian Yu, Nicha C. Dvornek +6Cholangiocarcinoma Experts
Learning Nonlinear Factor Models with Unknown Monotone Links from Incomplete and Noisy Data
May 25, 2026Yutong Chao, Resat Gökhan, Jalal Etesami +1Exploratory Factor Analysis Low-Rank Factorization
Factorize to Generalize: Retrieval-Guided Invariant-Dynamic Decomposition for Time Series Forecasting
May 24, 2026Jinjin Chi, Lei Feng, Lulu Zhang +6Zero-Shot Forecasting Factor
On the Sample Complexity of Robust Binary Hypothesis Testing
May 23, 2026Shankar Vallinayagam, Ankit Pensia, Varun JogTwo-Sample Testing Sample Complexity
LLMs Show No Signs Of Individuated Metacognition
May 22, 2026M. Moran, Mark WhitingConfidence Calibration Metacognition
A Typed Tensor Language for Federated Learning
May 20, 2026Theofilos Mailis, Kalliopi-Christina Despotidou, Konstantinos Filippopolitis +6Federated Learning Tensor Programs
Factor Augmented High-Dimensional SGD
May 19, 2026Shubo Li, Yuefeng Han, Xiufan YuStochastic Gradient Descent Factor
Beyond Square Roots: Explicit Memory-Efficient Factorization for Multi-Epoch Private Learning
May 18, 2026Nikita P. Kalinin, Aki Rehn, Joel Daniel Andersson +2Differential Privacy Universal Factorization Problem
Dynamic Elliptical Graph Factor Models via Riemannian Optimization with Geodesic Temporal Regularization
May 18, 2026Chuansen Peng, Xiaojing ShenRiemannian Manifolds Factor Graphs
Forward-Learned Discrete Diffusion: Learning how to noise to denoise faster
May 18, 2026Grigory Bartosh, Teodora Pandeva, Sushrut Karmalkar +1Generative Models Factor
Bridging the Gap between Sparse Matrix Reordering and Factorization: A Deep Learning Framework for Fill-in Reduction
May 17, 2026Ziwei Li, Tao Yuan, Shuzi Niu +1Matrix Factorization Factor
From Feedback Loops to Policy Updates: Reinforcement Fine-Tuning for LLM-Based Alpha Factor Discovery
May 14, 2026Lingzhe Zhang, Tong Jia, Yunpeng Zhai +5Exploratory Factor Analysis Reinforcement Fine-Tuning
FactorizedHMR: A Hybrid Framework for Video Human Mesh Recovery
May 14, 2026Patrick Kwon, Chen ChenHuman Mesh Recovery Object Articulation
Factorization-Error-Free Discrete Diffusion Language Model via Speculative Decoding
May 14, 2026Xun Fang, Yunchen Li, Hang Yuan +1Diffusion Language Models Speculative Decoding
Vector-Quantized Discrete Latent Factors Meet Financial Priors: Dynamic Cross-Sectional Stock Ranking Prediction for Portfolio Construction
May 13, 2026Namhyoung Kim, Jae Wook SongPortfolio Optimization Exploratory Factor Analysis
KamonBench: A Grammar-Based Dataset for Evaluating Compositional Factor Recovery in Vision-Language Models
May 13, 2026Richard Sproat, Stefano PeluchettiMultimodal Benchmarks Textual Dataset
Multimodal Hidden Markov Models for Persistent Emotional State Tracking
May 13, 2026Anamika Ragu, Aneesh JonelagaddaEmotion Recognition Valence-Arousal Estimation
Valid Best-Model Identification for LLM Evaluation via Low-Rank Factorization
May 11, 2026Elad Tolochinsky, Yaniv Tenzer, Yaniv RomanoLarge Language Model Evaluation Model Selection
Instruction Adherence in Coding Agent Configuration Files: A Factorial Study of Four File-Structure Variables
May 11, 2026Damon McMillanCoding Agents Adherence
Black-box model classification under the discriminative factorization
May 8, 2026Hayden Helm, Merrick Ohata, Carey PriebeBlack Box Exploratory Factor Analysis
Arrow: A Foundation Model for Causal Discovery
May 8, 2026Ryan Thompson, He Zhao, Daniel M. Steinberg +1Causal Foundation Models Causal Attention
Beyond Factor Aggregation: Gauge-Aware Low-Rank Server Representations for Federated LoRA
May 7, 2026Jinqian Chen, Chang Liu, Jihua ZhuLow-Rank Adaptation Low-Rank Factorization
Fourier Feature Methods for Nonlinear Causal Discovery: FFML Scoring, TRFF Scoring, and FFCI Testing in Mixed Data
May 7, 2026Joseph D. RamseyCausal Foundation Models Conditional Independence
Permutation-preserving Functions and Neural Vecchia Covariance Kernels
May 6, 2026Jian Cao, Nian Liu, Ying LinGaussian Process Covariance Estimation
Improving FMQA via Initial Training Data Design Considering Marginal Bit Coverage in One-Hot Encoding
May 6, 2026Taiga Hayashi, Yuya Seki, Kotaro Terada +3Quantum Approximate Optimization Algorithm Exploratory Factor Analysis
Discovering Sparse Counterfactual Factors via Latent Adjustment for Survey-based Community Intervention
May 6, 2026Fatima Ashraf, Muhammad Ayub Sabir, Junbiao Pang +2Subspace Intervention Framework Propensity
$p$ -adic Manifold Learning and Benchmark Tasks from Impartial Games
May 6, 2026Tomoki MiharaManifold Learning Method Np-Hard
FACTOR: Counterfactual Training-Free Test-Time Adaptation for Open-Vocabulary Object Detection
May 5, 2026Kaixiang Zhao, Mao Ye, Lihua Zhou +4Open-Vocabulary Object Detection Counterfactual Learning
Geometric and Spectral Alignment for Deep Neural Network I
May 4, 2026Ziran Liu, Wei Wang, Jinhao Wang +5Spectral Norm Residual Connections
To Build or Not to Build? Factors that Lead to Non-Development or Abandonment of AI Systems
Apr 30, 2026Shreya Chappidi, Jatinder SinghArtificial Intelligence Governance Artificial Intelligence Systems
Staged Factorial Screening for Budget-Constrained Micro-Pretraining
Apr 27, 2026Felipe Chavarro PolaniaToken Budgets Exploratory Factor Analysis
SNGR: Selective Non-Gaussian Refinement for Ambiguous SLAM Factor Graphs
Apr 23, 2026Anushka Kulkarni, Sarthak DubeySimultaneous Localization And Mapping Diffusion Refinement
QRAFTI: An Agentic Framework for Empirical Research in Quantitative Finance
Apr 20, 2026Terence Lim, Kumar Muthuraman, Michael SuryFactor Autoresearch
Signal or Noise in Multi-Agent LLM-based Stock Recommendations?
Apr 19, 2026George Fatouros, Kostas MetaxasMulti-Agent Large Language Model Market
HopRank: Self-Supervised LLM Preference-Tuning on Graphs for Few-Shot Node Classification
Apr 19, 2026Ziqing Wang, Kaize DingText-Attributed Graph Universal Factorization Problem
The Virtue of Sparsity in Complexity
Apr 18, 2026Nima Afsharhajari, Jonathan Yu-Meng LiPortfolio Optimization Sparsity
Factor Graph-Based Shape Estimation for Continuum Robots via Magnus Expansion
Apr 17, 2026Lorenzo Ticozzi, Patricio A. Vela, Panagiotis TsiotrasSoft Robots Statistical Shape Model
Understanding Tool-Augmented Agents for Lean Formalization: A Factorial Analysis
Apr 16, 2026Ke Zhang, Patricio Gallardo, Maziar Raissi +1Multi-Turn Tool-Use Agent Formalization
CoPA: Benchmarking Personalized Question Answering with Data-Informed Cognitive Factors
Apr 16, 2026Hang Su, Zequn Liu, Chen Hu +3Multi-Hop Question Answering Benchmarks Model Preference
MeDUET: Disentangled Unified Pretraining for 3D Medical Image Synthesis and Analysis
Feb 19, 2026Junkai Liu, Ling Shao, Le ZhangMedical Image Generation 3D Latent Diffusion Model
BALF: Budgeted Activation-Aware Low-Rank Factorization for Fine-Tuning-Free Model Compression
Sep 29, 2025David González-MartínezLow-Rank Factorization Sparse Expert Activation
Probabilistic Analysis of Least Squares, Orthogonal Projection, and QR Factorization Algorithms Subject to Gaussian Noise
Sep 27, 2024Ali Lotfi, Julien Langou, Mohammad MeysamiSingular Value Decomposition Orthogonality
Beyond Spectral Decomposition: Bayesian Contrastive Learning and its Non-negative Formulation via Factor Analysis
Jul 31, 2024Zhibin Duan, Tiansheng Wen, Yifei Wang +3Exploratory Factor Analysis Contrastive Learning
Large and Deep Factor Models
Jan 20, 2024Bryan Kelly, Boris Kuznetsov, Semyon Malamud +1Neural Tangent Kernel Exploratory Factor Analysis
Interpretable factorization of clinical questionnaires to identify latent factors of psychopathology
Dec 12, 2023Ka Chun Lam, Francisco Pereira, Bridget W Mahony +1Exploratory Factor Analysis Psychometrics
Analytical Standard Errors for Exploratory Factor Solutions
Nov 12, 2018Xingwei Hu, Caihong Hu, Cheng-Kuang WuExploratory Factor Analysis Heteroskedasticity
A Factorial Study of Synthetic Data Generation for Low-Resource Machine Translation using Grammar Books
Date pendingVarun Ghat Ravikumar, Sina Ahmadi, Lena Jäger +1Machine Translation Low-Resource Languages

May 27, 2026 · cs.LGJ/K move · Enter open · S save

Compositional Generalization in Autoregressive Models via Logit Composition

Aakash Kumar, Maria Sofia Bucarelli, Emanuele Natale

COATI, CNRS, Inria, I3S, Université Coté d’Azur, France

Composing autoregressive models remains a core challenge in understanding how large language models can combine behaviors or skills learned across tasks. We introduce a new and principled composition strategy for autoregressive systems, inspired by composition methods developed for diffusion models. Under a factorized-conditionals assumption, we show that the resulting composition is projective: each component model preserves control over its own designated subspace of the output distribution avoiding interference between models. This property is further preserved under smooth reparameterizations of the output space, yielding a feature-space theorem. Finally, we show that composition preserves length-generalizing behavior when the factorization assumptions and component guarantees hold uniformly at the target length. These results provide a principled understanding of when model composition and merging succeed in autoregressive systems and identify conditions under which their interactions remain stable.

Autoregressive Model Compositionality Logit Lens Factor

Open paper Ask about it PDF