Copertina

Excess Description Length of Learning Generalizable Predictors

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Donoway, Elizabeth, Joren, Hailey, Roger, Fabien, Leike, Jan
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

Technical Report: Evaluating Goal Drift in Language Model Agents
di: Arike, Rauno, et al.
Pubblicazione: (2025)

Towards Understanding Link Predictor Generalizability Under Distribution Shifts
di: Revolinsky, Jay, et al.
Pubblicazione: (2024)

TG-NAS: Generalizable Zero-Cost Proxies with Operator Description Embedding and Graph Learning for Efficient Neural Architecture Search
di: Qiao, Ye, et al.
Pubblicazione: (2024)

Learning Universal Predictors
di: Grau-Moya, Jordi, et al.
Pubblicazione: (2024)

Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers
di: Shaw, Peter, et al.
Pubblicazione: (2025)

Self-Attribution Bias: When AI Monitors Go Easy on Themselves
di: Khullar, Dipika, et al.
Pubblicazione: (2026)

Reasoning Models Don't Always Say What They Think
di: Chen, Yanda, et al.
Pubblicazione: (2025)

Scaling and evaluating sparse autoencoders
di: Gao, Leo, et al.
Pubblicazione: (2024)

All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language
di: Guo, Shiyuan, et al.
Pubblicazione: (2025)

Classification with Conceptual Safeguards
di: Joren, Hailey, et al.
Pubblicazione: (2024)

Three Concrete Challenges and Two Hopes for the Safety of Unsupervised Elicitation
di: Canavan, Callum, et al.
Pubblicazione: (2026)

PAC-Bayesian Reinforcement Learning Trains Generalizable Policies
di: Zitouni, Abdelkrim, et al.
Pubblicazione: (2025)

Decision from Suboptimal Classifiers: Excess Risk Pre- and Post-Calibration
di: Perez-Lebel, Alexandre, et al.
Pubblicazione: (2025)

Fine-tuning Timeseries Predictors Using Reinforcement Learning
di: Cazaux, Hugo, et al.
Pubblicazione: (2026)

LLM Pretraining Shapes a Generalizable Manifold: Insights into Cross-Modal Transfer to Time Series
di: Roger, Alexis, et al.
Pubblicazione: (2026)

ELIS: Efficient LLM Iterative Scheduling System with Response Length Predictor
di: Choi, Seungbeom, et al.
Pubblicazione: (2025)

Learning Discriminative and Generalizable Anomaly Detector for Dynamic Graph with Limited Supervision
di: Tian, Yuxing, et al.
Pubblicazione: (2026)

Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate
di: Jin, Can, et al.
Pubblicazione: (2024)

Arithmetic Transformers Can Length-Generalize in Both Operand Length and Count
di: Cho, Hanseul, et al.
Pubblicazione: (2024)

Mining Generalizable Activation Functions
di: Vitvitskyi, Alex, et al.
Pubblicazione: (2026)

Generalizability of Memorization Neural Networks
di: Yu, Lijia, et al.
Pubblicazione: (2024)

DIGIC: Domain Generalizable Imitation Learning by Causal Discovery
di: Chen, Yang, et al.
Pubblicazione: (2024)

Generalizable Multimodal Large Language Model Editing via Invariant Trajectory Learning
di: Su, Jiajie, et al.
Pubblicazione: (2026)

Schema-Adaptive Tabular Representation Learning with LLMs for Generalizable Multimodal Clinical Reasoning
di: Mao, Hongxi, et al.
Pubblicazione: (2026)

Towards Generalizable PDE Dynamics Forecasting via Physics-Guided Invariant Learning
di: Li, Siyang, et al.
Pubblicazione: (2025)

BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning
di: Lin, Haohong, et al.
Pubblicazione: (2024)

Generalizable Trajectory Prediction via Inverse Reinforcement Learning with Mamba-Graph Architecture
di: Li, Wenyun, et al.
Pubblicazione: (2025)

Learning Stable Predictors from Weak Supervision under Distribution Shift
di: Shoeibi, Mehrdad, et al.
Pubblicazione: (2026)

CARL: Causality-guided Architecture Representation Learning for an Interpretable Performance Predictor
di: Ji, Han, et al.
Pubblicazione: (2025)

SCL-GNN: Towards Generalizable Graph Neural Networks via Spurious Correlation Learning
di: Zhang, Yuxiang, et al.
Pubblicazione: (2026)

MeshONet: A Generalizable and Efficient Operator Learning Method for Structured Mesh Generation
di: Xiao, Jing, et al.
Pubblicazione: (2025)

Causally-informed Deep Learning towards Explainable and Generalizable Outcomes Prediction in Critical Care
di: Cheng, Yuxiao, et al.
Pubblicazione: (2025)

Just Enough Thinking: Efficient Reasoning with Adaptive Length Penalties Reinforcement Learning
di: Xiang, Violet, et al.
Pubblicazione: (2025)

MEP: Multiple Kernel Learning Enhancing Relative Positional Encoding Length Extrapolation
di: Gao, Weiguo
Pubblicazione: (2024)

Language models are better than humans at next-token prediction
di: Shlegeris, Buck, et al.
Pubblicazione: (2022)

Length-Aware Adversarial Training for Variable-Length Trajectories: Digital Twins for Mall Shopper Paths
di: Sun, He, et al.
Pubblicazione: (2026)

Protein-Conditioned Multi-Objective Reinforcement Learning for Full-Length mRNA Design
di: Shao, Zixi, et al.
Pubblicazione: (2026)

Memory Sequence Length of Data Sampling Impacts the Adaptation of Meta-Reinforcement Learning Agents
di: Zhang, Menglong, et al.
Pubblicazione: (2024)

TPTT: Transforming Pretrained Transformers into Titans
di: Furfaro, Fabien
Pubblicazione: (2025)

Generalizable Reasoning through Compositional Energy Minimization
di: Oarga, Alexandru, et al.
Pubblicazione: (2025)