Copertina

Physics in Next-token Prediction

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	An, Hongjun, Song, Yiliang, Li, Xuelong
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

CreditAudit: 2$^\text{nd}$ Dimension for LLM Evaluation and Selection
di: Song, Yiliang, et al.
Pubblicazione: (2026)

Next-token pretraining implies in-context learning
di: Riechers, Paul M., et al.
Pubblicazione: (2025)

Interpretable Next-token Prediction via the Generalized Induction Head
di: Kim, Eunji, et al.
Pubblicazione: (2024)

SUN: Shared Use of Next-token Prediction for Efficient Multi-LLM Disaggregated Serving
di: Woo, Sunghyeon, et al.
Pubblicazione: (2026)

Not all tokens are needed(NAT): token efficient reinforcement learning
di: Sang, Hejian, et al.
Pubblicazione: (2026)

All or None: Identifiable Linear Properties of Next-token Predictors in Language Modeling
di: Marconato, Emanuele, et al.
Pubblicazione: (2024)

Theoretical Foundations of Scaling Law in Familial Models
di: Song, Huan, et al.
Pubblicazione: (2025)

Single-Pixel Vision-Language Model for Intrinsic Privacy-Preserving Behavioral Intelligence
di: An, Hongjun, et al.
Pubblicazione: (2026)

Scaling FP8 training to trillion-token LLMs
di: Fishman, Maxim, et al.
Pubblicazione: (2024)

An attempt to generate new bridge types from latent space of energy-based model
di: Zhang, Hongjun
Pubblicazione: (2024)

The pitfalls of next-token prediction
di: Bachmann, Gregor, et al.
Pubblicazione: (2024)

Looking beyond the next token
di: Thankaraj, Abitha, et al.
Pubblicazione: (2025)

Demonstration of DB-GPT: Next Generation Data Interaction System Empowered by Large Language Models
di: Xue, Siqiao, et al.
Pubblicazione: (2024)

Are LLMs Vulnerable to Preference-Undermining Attacks (PUA)? A Factorial Analysis Methodology for Diagnosing the Trade-off between Preference Alignment and Real-World Validity
di: An, Hongjun, et al.
Pubblicazione: (2026)

SentenceVAE: Enable Next-sentence Prediction for Large Language Models with Faster Speed, Higher Accuracy and Longer Context
di: An, Hongjun, et al.
Pubblicazione: (2024)

GReF: A Unified Generative Framework for Efficient Reranking via Ordered Multi-token Prediction
di: Lin, Zhijie, et al.
Pubblicazione: (2025)

Deep Contrastive Graph Learning with Clustering-Oriented Guidance
di: Chen, Mulin, et al.
Pubblicazione: (2024)

Decouple Graph Neural Networks: Train Multiple Simple GNNs Simultaneously Instead of One
di: Zhang, Hongyuan, et al.
Pubblicazione: (2023)

Resilience Inference for Supply Chains with Hypergraph Neural Network
di: Shen, Zetian, et al.
Pubblicazione: (2025)

Bio2Token: All-atom tokenization of any biomolecular structure with Mamba
di: Liu, Andrew, et al.
Pubblicazione: (2024)

Shaping capabilities with token-level data filtering
di: Rathi, Neil, et al.
Pubblicazione: (2026)

Provable Long-Range Benefits of Next-Token Prediction
di: Cao, Xinyuan, et al.
Pubblicazione: (2025)

Next Embedding Prediction Makes World Models Stronger
di: Bredis, George, et al.
Pubblicazione: (2026)

Don't flatten, tokenize! Unlocking the key to SoftMoE's efficacy in deep RL
di: Sokar, Ghada, et al.
Pubblicazione: (2024)

Silicon Bureaucracy and AI Test-Oriented Education: Contamination Sensitivity and Score Confidence in LLM Benchmarks
di: Song, Yiliang, et al.
Pubblicazione: (2026)

Leveraging Taxonomy Similarity for Next Activity Prediction in Patient Treatment
di: Kuhn, Martin, et al.
Pubblicazione: (2025)

Scaling Transformer to 1M tokens and beyond with RMT
di: Bulatov, Aydar, et al.
Pubblicazione: (2023)

Towards Learnable Anchor for Deep Multi-View Clustering
di: Wang, Bocheng, et al.
Pubblicazione: (2025)

Unveiling the Inflexibility of Adaptive Embedding in Traffic Forecasting
di: Wang, Hongjun, et al.
Pubblicazione: (2024)

Cautious Next Token Prediction
di: Wang, Yizhou, et al.
Pubblicazione: (2025)

An Accurate and Low-Parameter Machine Learning Architecture for Next Location Prediction
di: Jary, Calvin, et al.
Pubblicazione: (2024)

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

Can We Predict Your Next Move Without Breaking Your Privacy?
di: Soni, Arpita, et al.
Pubblicazione: (2025)

Next-Token Prediction Should be Ambiguity-Sensitive: A Meta-Learning Perspective
di: Gagnon, Leo, et al.
Pubblicazione: (2025)

D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation
di: Li, Junlin, et al.
Pubblicazione: (2026)

You only need 4 extra tokens: Synergistic Test-time Adaptation for LLMs
di: Xu, Yijie, et al.
Pubblicazione: (2025)

COMPACT: Common-token Optimized Model Pruning Across Channels and Tokens
di: Kwek, Eugene, et al.
Pubblicazione: (2025)

An Innovative Next Activity Prediction Using Process Entropy and Dynamic Attribute-Wise-Transformer in Predictive Business Process Monitoring
di: Zare, Hadi, et al.
Pubblicazione: (2025)

Controllable Exploration in Hybrid-Policy RLVR for Multi-Modal Reasoning
di: Huang, Zhuoxu, et al.
Pubblicazione: (2026)

CoVeR: Conformal Calibration for Versatile and Reliable Autoregressive Next-Token Prediction
di: Chen, Yuzhu, et al.
Pubblicazione: (2025)