Cover Image

Towards Effective Theory of LLMs: A Representation Learning Approach

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ustaomeroglu, Muhammed, Qu, Guannan
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

BLOCK-EM: Preventing Emergent Misalignment via Latent Blocking
by: Ustaomeroglu, Muhammed, et al.
Published: (2026)

A Theoretical Study of (Hyper) Self-Attention through the Lens of Interactions: Representation, Training, Generalization
by: Ustaomeroglu, Muhammed, et al.
Published: (2025)

Internal Planning in Language Models: Characterizing Horizon and Branch Awareness
by: Ustaomeroglu, Muhammed, et al.
Published: (2025)

Emergent and Subliminal Misalignment Through the Lens of Data-Mediated Transfer
by: Askin, Baris, et al.
Published: (2026)

Transformer-Based Scalable Multi-Agent Reinforcement Learning for Networked Systems with Long-Range Interactions
by: Sinha, Vidur, et al.
Published: (2025)

Towards a Learning Theory of Representation Alignment
by: Insulla, Francesco, et al.
Published: (2025)

Bayesian Kolmogorov Arnold Networks (Bayesian_KANs): A Probabilistic Approach to Enhance Accuracy and Interpretability
by: Hassan, Masoud Muhammed
Published: (2024)

Towards a Generic Representation of Combinatorial Problems for Learning-Based Approaches
by: Boisvert, Léo, et al.
Published: (2024)

Thinking Beyond Visibility: A Near-Optimal Policy Framework for Locally Interdependent Multi-Agent MDPs
by: DeWeese, Alex, et al.
Published: (2025)

Toward Effective Digraph Representation Learning: A Magnetic Adaptive Propagation based Approach
by: Li, Xunkai, et al.
Published: (2025)

Locally Interdependent Multi-Agent MDP: Theoretical Framework for Decentralized Agents with Dynamic Dependencies
by: DeWeese, Alex, et al.
Published: (2024)

RED: Effective Trajectory Representation Learning with Comprehensive Information
by: Zhou, Silin, et al.
Published: (2024)

The Effectiveness of LLMs as Annotators: A Comparative Overview and Empirical Analysis of Direct Representation
by: Pavlovic, Maja, et al.
Published: (2024)

any4: Learned 4-bit Numeric Representation for LLMs
by: Elhoushi, Mostafa, et al.
Published: (2025)

MolMix: A Simple Yet Effective Baseline for Multimodal Molecular Representation Learning
by: Manolache, Andrei, et al.
Published: (2024)

Toward Temporal Causal Representation Learning with Tensor Decomposition
by: Chen, Jianhong, et al.
Published: (2025)

Exploiting Latent Linearity in LLMs Improves Explainable Molecular Representation Learning
by: Li, Zhuoran, et al.
Published: (2024)

MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs
by: Zhao, Guojiang, et al.
Published: (2025)

Towards Effective Experiential Learning: Dual Guidance for Utilization and Internalization
by: Bai, Fei, et al.
Published: (2026)

Merge then Realign: Simple and Effective Modality-Incremental Continual Learning for Multimodal LLMs
by: Zhang, Dingkun, et al.
Published: (2025)

Predictive Modeling of Homeless Service Assignment: A Representation Learning Approach
by: Rahman, Khandker Sadia, et al.
Published: (2024)

A Theory of Training Profit-Optimal LLMs
by: Hao, Sophie, et al.
Published: (2026)

Toward Enhancing Representation Learning in Federated Multi-Task Settings
by: Setayesh, Mehdi, et al.
Published: (2026)

DeepGate3: Towards Scalable Circuit Representation Learning
by: Shi, Zhengyuan, et al.
Published: (2024)

Schema-Adaptive Tabular Representation Learning with LLMs for Generalizable Multimodal Clinical Reasoning
by: Mao, Hongxi, et al.
Published: (2026)

Refining Latent Representations: A Generative SSL Approach for Heterogeneous Graph Learning
by: Hu, Yulan, et al.
Published: (2023)

TSI: A Multi-View Representation Learning Approach for Time Series Forecasting
by: Gao, Wentao, et al.
Published: (2024)

FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning
by: Zhou, Yanbing, et al.
Published: (2025)

COSMOS: Predictable and Cost-Effective Adaptation of LLMs
by: Wang, Jiayu, et al.
Published: (2025)

Simple and Effective Specialized Representations for Fair Classifiers
by: Sinigaglia, Alberto, et al.
Published: (2025)

When LLMs Learn to Be Consistently Wrong: A Multi-Model Study of Linear Representations of Synthetic Deception
by: Zolfaghari, Vahideh
Published: (2026)

Towards Robust Trajectory Representations: Isolating Environmental Confounders with Causal Learning
by: Luo, Kang, et al.
Published: (2024)

Exploring Open-world Continual Learning with Knowns-Unknowns Knowledge Transfer
by: Li, Yujie, et al.
Published: (2025)

A2PO: Towards Effective Offline Reinforcement Learning from an Advantage-aware Perspective
by: Qing, Yunpeng, et al.
Published: (2024)

LightDiC: A Simple yet Effective Approach for Large-scale Digraph Representation Learning
by: Li, Xunkai, et al.
Published: (2024)

A Self-guided Multimodal Approach to Enhancing Graph Representation Learning for Alzheimer's Diseases
by: Wang, Zhepeng, et al.
Published: (2024)

Exploring Task Unification in Graph Representation Learning via Generative Approach
by: Hu, Yulan, et al.
Published: (2024)

EMP: Effective Multidimensional Persistence for Graph Representation Learning
by: Segovia-Dominguez, Ignacio, et al.
Published: (2024)

DECRL: A Deep Evolutionary Clustering Jointed Temporal Knowledge Graph Representation Learning Approach
by: Chen, Qian, et al.
Published: (2024)

Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation Learning
by: Fu, En, et al.
Published: (2024)