Copertina

Token Space: A Category Theory Framework for AI Computations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Pan, Wuming
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	General Mathematics Machine Learning I.2.6
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Multiple Token Divergence: Measuring and Steering In-Context Computation Density
di: Herrmann, Vincent, et al.
Pubblicazione: (2025)

Fusing Rewards and Preferences in Reinforcement Learning
di: Khorasani, Sadegh, et al.
Pubblicazione: (2025)

Leap+Verify: Regime-Adaptive Speculative Weight Prediction for Accelerating Neural Network Training
di: McEntire, Jeremy
Pubblicazione: (2026)

AI and Machine Learning Approaches for Predicting Nanoparticles Toxicity The Critical Role of Physiochemical Properties
di: Yousaf, Iqra
Pubblicazione: (2024)

Before the Last Token: Diagnosing Final-Token Safety Probe Failures
di: Doda, Shravan
Pubblicazione: (2026)

Deep Memory Search: A Metaheuristic Approach for Optimizing Heuristic Search
di: Hedar, Abdel-Rahman, et al.
Pubblicazione: (2024)

ArrowFlow: Hierarchical Machine Learning in the Space of Permutations
di: Yilmaz, Ozgur
Pubblicazione: (2026)

Rewarded Region Replay (R3) for Policy Learning with Discrete Action Space
di: Li, Bangzheng, et al.
Pubblicazione: (2024)

Measuring In-Context Computation Complexity via Hidden State Prediction
di: Herrmann, Vincent, et al.
Pubblicazione: (2025)

Explanations Based on Item Response Theory (eXirt): A Model-Specific Method to Explain Tree-Ensemble Model in Trust Perspective
di: Ribeiro, José, et al.
Pubblicazione: (2022)

Beyond Random Sampling: Instance Quality-Based Data Partitioning via Item Response Theory
di: Cardoso, Lucas, et al.
Pubblicazione: (2025)

TimeCatcher: A Variational Framework for Volatility-Aware Forecasting of Non-Stationary Time Series
di: Chen, Zhiyu, et al.
Pubblicazione: (2026)

Future Token Prediction -- Causal Language Modelling with Per-Token Semantic State Vector for Multi-Token Prediction
di: Walker, Nicholas
Pubblicazione: (2024)

Versatile Ordering Network: An Attention-based Neural Network for Ordering Across Scales and Quality Metrics
di: Yu, Zehua, et al.
Pubblicazione: (2024)

Dual VC Dimension Obstructs Sample Compression by Embeddings
di: Chase, Zachary, et al.
Pubblicazione: (2024)

Spherical dimension
di: Chornomaz, Bogdan, et al.
Pubblicazione: (2025)

Why LoRA Resists Label Noise: A Theoretical Framework for Noise-Robust Parameter-Efficient Fine-Tuning
di: Steele, Brady
Pubblicazione: (2026)

Rethinking Thinking Tokens: Understanding Why They Underperform in Practice
di: Vennam, Sreeram, et al.
Pubblicazione: (2024)

ZClassifier: Temperature Tuning and Manifold Approximation via KL Divergence on Logit Space
di: Yong, Shim Soon
Pubblicazione: (2025)

2Mamba2Furious: Linear in Complexity, Competitive in Accuracy
di: Mongaras, Gabriel, et al.
Pubblicazione: (2026)

Loss-Complexity Landscape and Model Structure Functions
di: Kolpakov, Alexander
Pubblicazione: (2025)

A Survey of Reinforcement Learning from Human Feedback
di: Kaufmann, Timo, et al.
Pubblicazione: (2023)

Pre-trained Models Perform the Best When Token Distributions Follow Zipf's Law
di: He, Yanjin, et al.
Pubblicazione: (2025)

Kronecker Embeddings: Byte-Level Structured Token Representations for Parameter-Efficient Language Models
di: Shravan, Rohan
Pubblicazione: (2026)

Securing Reliability: A Brief Overview on Enhancing In-Context Learning for Foundation Models
di: Huang, Yunpeng, et al.
Pubblicazione: (2024)

Enhancing Classifier Evaluation: A Fairer Benchmarking Strategy Based on Ability and Robustness
di: Cardoso, Lucas, et al.
Pubblicazione: (2025)

Towards A Flexible Accuracy-Oriented Deep Learning Module Inference Latency Prediction Framework for Adaptive Optimization Algorithms
di: Shen, Jingran, et al.
Pubblicazione: (2023)

A Comparative Analysis of Reinforcement Learning and Conventional Deep Learning Approaches for Bearing Fault Diagnosis
di: Çakır, Efe, et al.
Pubblicazione: (2025)

HGCN(O): A Self-Tuning GCN HyperModel Toolkit for Outcome Prediction in Event-Sequence Data
di: Wang, Fang, et al.
Pubblicazione: (2025)

FluidWorld: Reaction-Diffusion Dynamics as a Predictive Substrate for World Models
di: Polly, Fabien
Pubblicazione: (2026)

I-GLIDE: Input Groups for Latent Health Indicators in Degradation Estimation
di: Thil, Lucas, et al.
Pubblicazione: (2025)

How Many Ratings per Item are Necessary for Reliable Significance Testing?
di: Homan, Christopher, et al.
Pubblicazione: (2024)

Potential-Based Reward Shaping For Intrinsic Motivation
di: Forbes, Grant C., et al.
Pubblicazione: (2024)

How to Boost Any Loss Function
di: Nock, Richard, et al.
Pubblicazione: (2024)

Interpretable Multi-View Clustering
di: Jiang, Mudi, et al.
Pubblicazione: (2024)

The Bayesian Confidence (BACON) Estimator for Deep Neural Networks
di: Kee, Patrick D., et al.
Pubblicazione: (2024)

Pre-Ictal Seizure Prediction Using Personalized Deep Learning
di: Jaddu, Shriya, et al.
Pubblicazione: (2024)

xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories
di: Kraus, Maurice, et al.
Pubblicazione: (2024)

Representation learning with CGAN for casual inference
di: Weng, Zhaotian, et al.
Pubblicazione: (2024)

Boosting gets full Attention for Relational Learning
di: Guillame-Bert, Mathieu, et al.
Pubblicazione: (2024)