Copertina

What If We Allocate Test-Time Compute Adaptively?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Bilal, Ahsan, Mohsin, Ahmed, Umer, Muhammad, Subhan, Ali, Rizwan, Hassan, Mohsin, Ayesha, Hougen, Dean
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Epistemic Uncertainty for Test-Time Discovery
di: Riaz, Kainat, et al.
Pubblicazione: (2026)

6G Twin: Hybrid Gaussian Radio Fields for Channel Estimation and Non-Linear Precoder Design for Radio Access Networks
di: Mohsin, Muhammad Ahmed, et al.
Pubblicazione: (2025)

Meta-Thinking in LLMs via Multi-Agent Reinforcement Learning: A Survey
di: Bilal, Ahsan, et al.
Pubblicazione: (2025)

Conditional Prior-based Non-stationary Channel Estimation Using Accelerated Diffusion Models
di: Mohsin, Muhammad Ahmed, et al.
Pubblicazione: (2025)

Channel Prediction under Network Distribution Shift Using Continual Learning-based Loss Regularization
di: Mohsin, Muhammad Ahmed, et al.
Pubblicazione: (2025)

Pressure, What Pressure? Sycophancy Disentanglement in Language Models via Reward Decomposition
di: Mohsin, Muhammad Ahmed, et al.
Pubblicazione: (2026)

Transformer-Based Sparse CSI Estimation for Non-Stationary Channels
di: Mohsin, Muhammad Ahmed, et al.
Pubblicazione: (2025)

Hierarchical Deep Reinforcement Learning for Adaptive Resource Management in Integrated Terrestrial and Non-Terrestrial Networks
di: Mohsin, Muhammad Ahmed, et al.
Pubblicazione: (2025)

$S^3$: Stratified Scaling Search for Test-Time in Diffusion Language Models
di: Bilal, Ahsan, et al.
Pubblicazione: (2026)

General Preference Reinforcement Learning
di: Umer, Muhammad, et al.
Pubblicazione: (2026)

Resource Allocation for RIS-Assisted CoMP-NOMA Networks using Reinforcement Learning
di: Umer, Muhammad, et al.
Pubblicazione: (2025)

Canonical Optimization for MIMO MAC Design
di: Umer, Muhammad, et al.
Pubblicazione: (2026)

Neural Gaussian Radio Fields for Channel Estimation
di: Umer, Muhammad, et al.
Pubblicazione: (2025)

Computation Offloading Strategies in Integrated Terrestrial and Non-Terrestrial Networks
di: Mohsin, Muhammad Ahmed, et al.
Pubblicazione: (2025)

Continual Learning for Wireless Channel Prediction
di: Mohsin, Muhammad Ahmed, et al.
Pubblicazione: (2025)

Meta-Reinforcement Learning for Fast and Data-Efficient Spectrum Allocation in Dynamic Wireless Networks
di: Giwa, Oluwaseyi, et al.
Pubblicazione: (2025)

Single layer tiny Co$^4$ outpaces GPT-2 and GPT-BERT
di: Zain, Noor Ul, et al.
Pubblicazione: (2025)

Towards Green Connectivity: An AI-Driven Mesh Architecture for Sustainable and Scalable Wireless Networks
di: Mohsin, Muhammad Ahmed, et al.
Pubblicazione: (2026)

BanglaNirTox: A Large-scale Parallel Corpus for Explainable AI in Bengali Text Detoxification
di: Mohsin, Ayesha Afroza, et al.
Pubblicazione: (2025)

Evaluating Large Language Models (LLMs) in Financial NLP: A Comparative Study on Financial Report Analysis
di: Mohsin, Md Talha
Pubblicazione: (2025)

OnRL-RAG: Real-Time Personalized Mental Health Dialogue System
di: Bilal, Ahsan, et al.
Pubblicazione: (2025)

On the Fundamental Limits of LLMs at Scale
di: Mohsin, Muhammad Ahmed, et al.
Pubblicazione: (2025)

Deep Reinforcement Learning Optimized Intelligent Resource Allocation in Active RIS-Integrated TN-NTN Networks
di: Mohsin, Muhammad Ahmed, et al.
Pubblicazione: (2025)

When to Ponder: Adaptive Compute Allocation for Code Generation via Test-Time Training
di: Sim, Gihyeon
Pubblicazione: (2025)

Uncertainty-Aware Budget Allocation for Adaptive Test-Time Reasoning
di: Nguyen, Manh, et al.
Pubblicazione: (2026)

Do LLMs Know They Are Being Tested? Evaluation Awareness and Incentive-Sensitive Failures in GPT-OSS-20B
di: Ahmed, Nisar, et al.
Pubblicazione: (2025)

Task and Perception-aware Distributed Source Coding for Correlated Speech under Bandwidth-constrained Channels
di: Bhattacharya, Sagnik, et al.
Pubblicazione: (2025)

Retrieval Augmented Generation with Multi-Modal LLM Framework for Wireless Environments
di: Mohsin, Muhammad Ahmed, et al.
Pubblicazione: (2025)

Assessment of reliability and availability of a system by using a bivariate stochastic model
di: Muhammad Mohsin, et al.
Pubblicazione: (2024)

Context-sensitive neocortical neurons transform the effectiveness and efficiency of neural information processing
di: Ahmed, Khubaib, et al.
Pubblicazione: (2022)

Mitigating Hallucinations Using Ensemble of Knowledge Graph and Vector Store in Large Language Models to Enhance Mental Health Support
di: Muqtadir, Abdul, et al.
Pubblicazione: (2024)

CODA: Difficulty-Aware Compute Allocation for Adaptive Reasoning
di: Wu, Siye, et al.
Pubblicazione: (2026)

Intelligent Spectrum Sharing in Integrated TN-NTNs: A Hierarchical Deep Reinforcement Learning Approach
di: Umer, Muhammad, et al.
Pubblicazione: (2025)

Adaptive Rectification Sampling for Test-Time Compute Scaling
di: Tan, Zhendong, et al.
Pubblicazione: (2025)

Neural Optimizer Equation, Decay Function, and Learning Rate Schedule Joint Evolution
di: Morgan, Brandon, et al.
Pubblicazione: (2024)

Evolving Loss Functions for Specific Image Augmentation Techniques
di: Morgan, Brandon, et al.
Pubblicazione: (2024)

LLMs for Explainable AI: A Comprehensive Survey
di: Bilal, Ahsan, et al.
Pubblicazione: (2025)

Neural Loss Function Evolution for Large-Scale Image Classifier Convolutional Neural Networks
di: Morgan, Brandon, et al.
Pubblicazione: (2024)

Collective Narrative Grounding: Community-Coordinated Data Contributions to Improve Local AI Systems
di: Gao, Zihan, et al.
Pubblicazione: (2025)

TCAR-Gen: Temporal Graph Retrieval with Evidence Fusion for Knowledge-Grounded Generation
di: Nasir, Sidra, et al.
Pubblicazione: (2026)