Image de couverture de livre

Contextual Control without Memory Growth in a Context-Switching Task

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Kim, Song-Ju
Format:	Preprint
Publié:	2026
Sujets:	Artificial Intelligence Information Theory Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Polynomial Context-Truncation Sensitivity in Autoregressive Language Models: Sequential Wyner-Ziv Bounds for KV Cache Compression
par: Kim, Munsik
Publié: (2026)

Contextuality from Single-State Ontological Models: An Information-Theoretic Obstruction
par: Kim, Song-Ju
Publié: (2026)

Contextuality as an External Bookkeeping Cost under Fixed Shared-State Semantics
par: Kim, Song-Ju
Publié: (2026)

Fast Rates for Offline Contextual Bandits with Forward-KL Regularization under Single-Policy Concentrability
par: Zhao, Qingyue, et autres
Publié: (2026)

A Wireless Foundation Model for Multi-Task Prediction
par: Sheng, Yucheng, et autres
Publié: (2025)

Disentangled Structural and Featural Representation for Task-Agnostic Graph Valuation
par: Falahati, Ali, et autres
Publié: (2024)

Context Channel Capacity: An Information-Theoretic Framework for Understanding Catastrophic Forgetting
par: Cheng, Ran
Publié: (2026)

In-Context Learning for MIMO Equalization Using Transformer-Based Sequence Models
par: Zecchin, Matteo, et autres
Publié: (2023)

From Markov to Laplace: How Mamba In-Context Learns Markov Chains
par: Bondaschi, Marco, et autres
Publié: (2025)

Two Birds with One Stone: Multi-Task Semantic Communications Systems over Relay Channel
par: Cao, Yujie, et autres
Publié: (2024)

Estimating Mutual Information between Time Series and Temporal Event Sequences Across Diverse Analysis Tasks
par: Hu, Haoji, et autres
Publié: (2026)

Deep Learning and Matrix Completion-aided IoT Network Localization in the Outlier Scenarios
par: Kim, Sunwoo
Publié: (2025)

Semantic Soft Bootstrapping: Long Context Reasoning in LLMs without Reinforcement Learning
par: Mitra, Purbesh, et autres
Publié: (2025)

Localized Adaptive Risk Control
par: Zecchin, Matteo, et autres
Publié: (2024)

An Information Criterion for Controlled Disentanglement of Multimodal Data
par: Wang, Chenyu, et autres
Publié: (2024)

FibQuant: Universal Vector Quantization for Random-Access KV-Cache Compression
par: Lee, Namyoon, et autres
Publié: (2026)

Remote Action Generation: Remote Control with Minimal Communication
par: Kobus, Szymon, et autres
Publié: (2026)

Generalization and Informativeness of Weighted Conformal Risk Control Under Covariate Shift
par: Zecchin, Matteo, et autres
Publié: (2025)

Energy-Efficient Edge Learning via Joint Data Deepening-and-Prefetching
par: Kook, Sujin, et autres
Publié: (2024)

Universal scaling laws in quantum-probabilistic machine learning by tensor network towards interpreting representation and generalization powers
par: Bai, Sheng-Chen, et autres
Publié: (2024)

Reliability-Optimized User Admission Control for URLLC Traffic: A Neural Contextual Bandit Approach
par: Semiari, Omid, et autres
Publié: (2024)

Long Context Modeling with Ranked Memory-Augmented Retrieval
par: Alselwi, Ghadir, et autres
Publié: (2025)

Knowledge Distillation from Language-Oriented to Emergent Communication for Multi-Agent Remote Control
par: Kim, Yongjun, et autres
Publié: (2024)

Persistent Entropy as a Detector of Phase Transitions
par: Rucco, Matteo
Publié: (2026)

Tackling Federated Unlearning as a Parameter Estimation Problem
par: Balordi, Antonio, et autres
Publié: (2025)

Redundancy as a Structural Information Principle for Learning and Generalization
par: Bi, Yuda, et autres
Publié: (2025)

Laplace Sample Information: Data Informativeness Through a Bayesian Lens
par: Kaiser, Johannes, et autres
Publié: (2025)

Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective
par: Yang, Jiaming, et autres
Publié: (2026)

Flexible Variational Information Bottleneck: Achieving Diverse Compression with a Single Training
par: Kudo, Sota, et autres
Publié: (2024)

Simple Convergence Proof of Adam From a Sign-like Descent Perspective
par: Peng, Hanyang, et autres
Publié: (2025)

AutoBS: Autonomous Base Station Deployment with Reinforcement Learning and Digital Network Twins
par: Lee, Ju-Hyung, et autres
Publié: (2025)

FAdam: Adam is a natural gradient optimizer using diagonal empirical Fisher information
par: Hwang, Dongseong
Publié: (2024)

Multi-Treatment Multi-Task Uplift Modeling for Enhancing User Growth
par: Wei, Yuxiang, et autres
Publié: (2024)

Enhancing User Throughput in Multi-panel mmWave Radio Access Networks for Beam-based MU-MIMO Using a DRL Method
par: Hashemi, Ramin, et autres
Publié: (2026)

Hybrid Federated Learning for Noise-Robust Training
par: Kim, Yongjun, et autres
Publié: (2026)

InfoChess: A Game of Adversarial Inference and a Laboratory for Quantifiable Information Control
par: Murphy, Kieran A.
Publié: (2026)

Context Retrieval via Normalized Contextual Latent Interaction for Conversational Agent
par: Liu, Junfeng, et autres
Publié: (2023)

On the Limits of Self-Improving in Large Language Models: The Singularity Is Not Near Without Symbolic Model Synthesis
par: Zenil, Hector
Publié: (2026)

Deep Randomized Distributed Function Computation (DeepRDFC): Neural Distributed Channel Simulation
par: Bergström, Didrik, et autres
Publié: (2026)

Beyond the Loss Curve: Scaling Laws, Active Learning, and the Limits of Learning from Exact Posteriors
par: Khorasani, Arian, et autres
Publié: (2026)