Copertina

History-Aware Cross-Attention Reinforcement: Self-Supervised Multi Turn and Chain-of-Thought Fine-Tuning with vLLM

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Kiruluta, Andrew, Lemos, Andreas, Burity, Priscilla
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

A Self-Supervised Reinforcement Learning Approach for Fine-Tuning Large Language Models Using Cross-Attention Signals
di: Kiruluta, Andrew, et al.
Pubblicazione: (2025)

Learnable Multi-Scale Wavelet Transformer: A Novel Alternative to Self-Attention
di: Kiruluta, Andrew, et al.
Pubblicazione: (2025)

Breaking Quadratic Barriers: A Non-Attention LLM for Ultra-Long Context Horizons
di: Kiruluta, Andrew, et al.
Pubblicazione: (2025)

Spectral Neuro-Symbolic Reasoning II: Semantic Node Merging, Entailment Filtering, and Knowledge Graph Alignment
di: Kiruluta, Andrew, et al.
Pubblicazione: (2025)

From Eigenmodes to Proofs: Integrating Graph Spectral Operators with Symbolic Interpretable Reasoning
di: Kiruluta, Andrew, et al.
Pubblicazione: (2025)

Graph Laplacian Wavelet Transformer via Learnable Spectral Decomposition
di: Kiruluta, Andrew, et al.
Pubblicazione: (2025)

From Pixels and Words to Waves: A Unified Framework for Spectral Dictionary vLLMs
di: Kiruluta, Andrew, et al.
Pubblicazione: (2025)

Beyond Self Attention: A Subquadratic Fourier Wavelet Transformer with Multi Modal Fusion
di: Kiruluta, Andrew, et al.
Pubblicazione: (2021)

Beyond Neural Networks: Symbolic Reasoning over Wavelet Logic Graph Signals
di: Kiruluta, Andrew, et al.
Pubblicazione: (2025)

Operator-Based Machine Intelligence: A Hilbert Space Framework for Spectral Learning and Symbolic Reasoning
di: Kiruluta, Andrew, et al.
Pubblicazione: (2025)

vLLM Hook v0: A Plug-in for Programming Model Internals on vLLM
di: Ko, Ching-Yun, et al.
Pubblicazione: (2026)

CS-VLM: Compressed Sensing Attention for Efficient Vision-Language Representation Learning
di: Kiruluta, Andrew, et al.
Pubblicazione: (2025)

State Fourier Diffusion Language Model (SFDLM): A Scalable, Novel Iterative Approach to Language Modeling
di: Kiruluta, Andrew, et al.
Pubblicazione: (2025)

Filtering Beats Fine Tuning: A Bayesian Kalman View of In Context Learning in LLMs
di: Kiruluta, Andrew
Pubblicazione: (2026)

Entropic-Time Inference: Self-Organizing Large Language Model Decoding Beyond Attention
di: Kiruluta, Andrew
Pubblicazione: (2026)

Adaptive Two Sided Laplace Transforms: A Learnable, Interpretable, and Scalable Replacement for Self-Attention
di: Kiruluta, Andrew
Pubblicazione: (2025)

From Attention to Atoms: Spectral Dictionary Learning for Fast, Interpretable Language Models
di: Kiruluta, Andrew
Pubblicazione: (2025)

Compressed-Sensing-Guided, Inference-Aware Structured Reduction for Large Language Models
di: Kiruluta, Andrew
Pubblicazione: (2026)

FourierNAT: A Fourier-Mixing-Based Non-Autoregressive Transformer for Parallel Sequence Generation
di: Kiruluta, Andrew, et al.
Pubblicazione: (2025)

When to Reason: Semantic Router for vLLM
di: Wang, Chen, et al.
Pubblicazione: (2025)

A Novel Architecture for Symbolic Reasoning with Decision Trees and LLM Agents
di: Kiruluta, Andrew
Pubblicazione: (2025)

ARES: Alternating Reinforcement Learning and Supervised Fine-Tuning for Enhanced Multi-Modal Chain-of-Thought Reasoning Through Diverse AI Feedback
di: Byun, Ju-Seung, et al.
Pubblicazione: (2024)

On the Role of Reasoning Patterns in the Generalization Discrepancy of Long Chain-of-Thought Supervised Fine-Tuning
di: Li, Zhaoyi, et al.
Pubblicazione: (2026)

On the Impact of Fine-Tuning on Chain-of-Thought Reasoning
di: Lobo, Elita, et al.
Pubblicazione: (2024)

98$\times$ Faster LLM Routing Without a Dedicated GPU: Flash Attention, Prompt Compression, and Near-Streaming for the vLLM Semantic Router
di: Liu, Xunzhuo, et al.
Pubblicazione: (2026)

Cause-Aware Empathetic Response Generation via Chain-of-Thought Fine-Tuning
di: Chen, Xinhao, et al.
Pubblicazione: (2024)

CARFT: Boosting LLM Reasoning via Contrastive Learning with Annotated Chain-of-Thought-based Reinforced Fine-Tuning
di: Zhu, Wenqiao, et al.
Pubblicazione: (2025)

Data-Driven Variational Basis Learning Beyond Neural Networks: A Non-Neural Framework for Adaptive Basis Discovery
di: Kiruluta, Andrew
Pubblicazione: (2026)

Spectral Generative Flow Models: A Physics-Inspired Replacement for Vectorized Large Language Models
di: Kiruluta, Andrew
Pubblicazione: (2026)

From Gradients to Riccati Geometry: Kalman World Models for Single-Pass Learning
di: Kiruluta, Andrew
Pubblicazione: (2026)

Long-Short Chain-of-Thought Mixture Supervised Fine-Tuning Eliciting Efficient Reasoning in Large Language Models
di: Yu, Bin, et al.
Pubblicazione: (2025)

TRACT: Regression-Aware Fine-tuning Meets Chain-of-Thought Reasoning for LLM-as-a-Judge
di: Chiang, Cheng-Han, et al.
Pubblicazione: (2025)

Fine-Tuned Thoughts: Leveraging Chain-of-Thought Reasoning for Industrial Asset Health Monitoring
di: Lin, Shuxin, et al.
Pubblicazione: (2025)

Supervised Chain of Thought
di: Zhang, Xiang, et al.
Pubblicazione: (2024)

The Impact of Hyperparameters on Large Language Model Inference Performance: An Evaluation of vLLM and HuggingFace Pipelines
di: Martinez, Matias
Pubblicazione: (2024)

Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning
di: Chen, Yiqun, et al.
Pubblicazione: (2026)

Beyond Fine-Tuning: In-Context Learning and Chain-of-Thought for Reasoned Distractor Generation
di: Alhazmi, Elaf, et al.
Pubblicazione: (2026)

Hierarchical Attention Diffusion Networks with Object Priors for Video Change Detection
di: Kiruluta, Andrew, et al.
Pubblicazione: (2024)

Not All Thoughts are Generated Equal: Efficient LLM Reasoning via Multi-Turn Reinforcement Learning
di: Ning, Yansong, et al.
Pubblicazione: (2025)

Learning When to Sample: Confidence-Aware Self-Consistency for Efficient LLM Chain-of-Thought Reasoning
di: Xiong, Juming, et al.
Pubblicazione: (2026)