Image de couverture de livre

Improving Latent Generalization Using Test-time Compute

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chaudhry, Arslan, Thiagarajan, Sridhar, Lampinen, Andrew
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Finetuning Language Models to Emit Linguistic Expressions of Uncertainty
par: Chaudhry, Arslan, et autres
Publié: (2024)

Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences
par: Lampinen, Andrew Kyle, et autres
Publié: (2025)

Interpretability Illusions in the Generalization of Simplified Models
par: Friedman, Dan, et autres
Publié: (2023)

Distinct Computations Emerge From Compositional Curricula in In-Context Learning
par: Lee, Jin Hwa, et autres
Publié: (2025)

Implicit Statistical Inference in Transformers: Approximating Likelihood-Ratio Tests In-Context
par: Chaudhry, Faris, et autres
Publié: (2026)

On the generalization of language models from in-context learning and finetuning: a controlled study
par: Lampinen, Andrew K., et autres
Publié: (2025)

ExpTest: Automating Learning Rate Searching and Tuning with Insights from Linearized Neural Networks
par: Chaudhry, Zan, et autres
Publié: (2024)

Jensen-Shannon Divergence Based Novel Loss Functions for Bayesian Neural Networks
par: Thiagarajan, Ponkrshnan, et autres
Publié: (2022)

Universal Reinforcement Learning in Coalgebras: Asynchronous Stochastic Computation via Conduction
par: Mahadevan, Sridhar
Publié: (2025)

Improving Routability Prediction via NAS Using a Smooth One-shot Augmented Predictor
par: Sridhar, Arjun, et autres
Publié: (2024)

Latent Regularization in Generative Test Input Generation
par: Merabishvili, Giorgi, et autres
Publié: (2026)

A Comparative Analysis of LLM Adaptation: SFT, LoRA, and ICL in Data-Scarce Scenarios
par: Bohnet, Bernd, et autres
Publié: (2025)

The Geometry of Projection Heads: Conditioning, Invariance, and Collapse
par: Chaudhry, Faris
Publié: (2026)

Non-Interfering Weight Fields: Treating Model Parameters as a Continuously Extensible Function
par: Chaudhry, Sarim
Publié: (2026)

Asymptotic and Finite-Time Guarantees for Langevin-Based Temperature Annealing in InfoNCE
par: Chaudhry, Faris
Publié: (2026)

General Preference Reinforcement Learning
par: Umer, Muhammad, et autres
Publié: (2026)

GAIA: Categorical Foundations of Generative AI
par: Mahadevan, Sridhar
Publié: (2024)

Learned feature representations are biased by complexity, learning order, position, and more
par: Lampinen, Andrew Kyle, et autres
Publié: (2024)

ChronoPlastic Spiking Neural Networks
par: Chaudhry, Sarim
Publié: (2025)

A Simple Sparse Matrix Vector Multiplication Approach to Padded Convolution
par: Chaudhry, Zan
Publié: (2024)

Linear representations in language models can change dramatically over a conversation
par: Lampinen, Andrew Kyle, et autres
Publié: (2026)

Representation biases: will we achieve complete understanding by analyzing representations?
par: Lampinen, Andrew Kyle, et autres
Publié: (2025)

Data Distribution-based Curriculum Learning
par: Chaudhry, Shonal, et autres
Publié: (2024)

GLAD: Improving Latent Graph Generative Modeling with Simple Quantization
par: Nguyen, Van Khoa, et autres
Publié: (2024)

Recursive Concept Evolution for Compositional Reasoning in Large Language Models
par: Chaudhry, Sarim
Publié: (2026)

Scaling Laws and Pathologies of Single-Layer PINNs: Network Width and PDE Nonlinearity
par: Chaudhry, Faris
Publié: (2026)

The in-context inductive biases of vision-language models differ across modalities
par: Allen, Kelsey, et autres
Publié: (2025)

The broader spectrum of in-context learning
par: Lampinen, Andrew Kyle, et autres
Publié: (2024)

How do language models learn facts? Dynamics, curricula and hallucinations
par: Zucchet, Nicolas, et autres
Publié: (2025)

The emergence of sparse attention: impact of data distribution and benefits of repetition
par: Zucchet, Nicolas, et autres
Publié: (2025)

Universal Decision Learners
par: Mahadevan, Sridhar
Publié: (2026)

Kan Extension Transformers: A Categorical Unification of Attention, Diffusion, and Predict-Detach Self-Conditioning
par: Mahadevan, Sridhar
Publié: (2026)

PACEvolve++: Improving Test-time Learning for Evolutionary Search Agents
par: Yan, Minghao, et autres
Publié: (2026)

EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
par: Kouzelis, Theodoros, et autres
Publié: (2025)

Improving the Generation of VAEs with High Dimensional Latent Spaces by the use of Hyperspherical Coordinates
par: Ascarate, Alejandro, et autres
Publié: (2025)

Generative Modeling of Discrete Data Using Geometric Latent Subspaces
par: Gonzalez-Alvarado, Daniel, et autres
Publié: (2026)

Bridging Quantum and Classical Computing in Drug Design: Architecture Principles for Improved Molecule Generation
par: Smith, Andrew, et autres
Publié: (2025)

Deep Learning-Based Visual Fatigue Detection Using Eye Gaze Patterns in VR
par: Zafar, Numan, et autres
Publié: (2025)

Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
par: Geiping, Jonas, et autres
Publié: (2025)

Enhancing Latent Computation in Transformers with Latent Tokens
par: Sun, Yuchang, et autres
Publié: (2025)