Cover Image

MIC: Maximizing Informational Capacity in Adaptive Representations via Isotropic Subspace Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hong, Dang Nguyen, Nguyen, Nhi Ngoc-Yen, Pham, Huy-Hieu
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

EVL-ECG: Efficient ECG Interpretation With Multi-Aspect Heterogeneous Knowledge Distillation
by: Hong, Dang Nguyen, et al.
Published: (2026)

End-to-End Chatbot Evaluation with Adaptive Reasoning and Uncertainty Filtering
by: Dang, Nhi, et al.
Published: (2026)

Lean and Mean Adaptive Optimization via Subset-Norm and Subspace-Momentum with Convergence Guarantees
by: Nguyen, Thien Hang, et al.
Published: (2024)

Structured Pruning for Diverse Best-of-N Reasoning Optimization
by: Nguyen, Hieu Trung, et al.
Published: (2025)

Task-driven Layerwise Additive Activation Intervention
by: Nguyen, Hieu Trung, et al.
Published: (2025)

On the Effectiveness and Generalization of Race Representations for Debiasing High-Stakes Decisions
by: Nguyen, Dang, et al.
Published: (2025)

Explainable Disentangled Representation Learning for Generalizable Authorship Attribution in the Era of Generative AI
by: Man, Hieu, et al.
Published: (2026)

Nested Named-Entity Recognition on Vietnamese COVID-19: Dataset and Experiments
by: Lê, Ngoc C., et al.
Published: (2025)

Adaptive Rollout Allocation for Online Reinforcement Learning with Verifiable Rewards
by: Nguyen, Hieu Trung, et al.
Published: (2026)

Mixture-of-Personas Language Models for Population Simulation
by: Bui, Ngoc, et al.
Published: (2025)

Adaptive Prompting for Continual Relation Extraction: A Within-Task Variance Perspective
by: Le, Minh, et al.
Published: (2024)

Phrase-Instance Alignment for Generalized Referring Segmentation
by: Nguyen, E-Ro, et al.
Published: (2024)

VietMix: A Naturally-Occurring Parallel Corpus and Augmentation Framework for Vietnamese-English Code-Mixed Machine Translation
by: Tran, Hieu, et al.
Published: (2025)

Linguistically Informed Multimodal Fusion for Vietnamese Scene-Text Image Captioning: Dataset, Graph Framework, and Phonological Attention
by: Nguyen, Nhi Ngoc-Yen, et al.
Published: (2026)

OWLViz: An Open-World Benchmark for Visual Question Answering
by: Nguyen, Thuy, et al.
Published: (2025)

Representation Learning with Conditional Information Flow Maximization
by: Hu, Dou, et al.
Published: (2024)

Multimodal Contrastive Representation Learning in Augmented Biomedical Knowledge Graphs
by: Dang, Tien, et al.
Published: (2025)

ViQA-COVID: COVID-19 Machine Reading Comprehension Dataset for Vietnamese
by: Nguyen-Phung, Hai-Chung, et al.
Published: (2025)

Reasoning Planning for Language Models
by: Nguyen, Bao, et al.
Published: (2025)

Adaptive Two-Phase Finetuning LLMs for Japanese Legal Text Retrieval
by: Trung, Quang Hoang, et al.
Published: (2024)

Beyond Semantic Entropy: Boosting LLM Uncertainty Quantification with Pairwise Semantic Similarity
by: Nguyen, Dang, et al.
Published: (2025)

Leveraging Large Language Models for Suicide Detection on Social Media with Limited Labels
by: Nguyen, Vy, et al.
Published: (2024)

ToVo: Toxicity Taxonomy via Voting
by: Luong, Tinh Son, et al.
Published: (2024)

A Comparative Analysis of Contextual Representation Flow in State-Space and Transformer Architectures
by: Hoang, Nhat M., et al.
Published: (2025)

Subspace Representations for Soft Set Operations and Sentence Similarities
by: Ishibashi, Yoichi, et al.
Published: (2022)

Toward a Flexible Framework for Linear Representation Hypothesis Using Maximum Likelihood Estimation
by: Nguyen, Trung, et al.
Published: (2025)

ATLAS: Adaptive Test-Time Latent Steering with External Verifiers for Enhancing LLMs Reasoning
by: Nguyen, Tuc, et al.
Published: (2026)

Detecting and Rectifying Noisy Labels: A Similarity-based Approach
by: Huu-Tien, Dang, et al.
Published: (2025)

LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models
by: Shojaee, Parshin, et al.
Published: (2025)

Discovering Low-rank Subspaces for Language-agnostic Multilingual Representations
by: Xie, Zhihui, et al.
Published: (2024)

Synthetic Text Generation for Training Large Language Models via Gradient Matching
by: Nguyen, Dang, et al.
Published: (2025)

Interpretable Safety Alignment via SAE-Constructed Low-Rank Subspace Adaptation
by: Wang, Dianyun, et al.
Published: (2025)

OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment
by: Lin, Liang, et al.
Published: (2025)

Predict, Don't React: Value-Based Safety Forecasting for LLM Streaming
by: Kavumba, Pride, et al.
Published: (2026)

Beyond Forgetting: Machine Unlearning Elicits Controllable Side Behaviors and Capabilities
by: Dang, Tien, et al.
Published: (2026)

Few-shot Continual Relation Extraction via Open Information Extraction
by: Nguyen, Thiem, et al.
Published: (2025)

Defect Prediction with Content-based Features
by: Pham, Hung Viet, et al.
Published: (2024)

On the Representational Capacity of Recurrent Neural Language Models
by: Nowak, Franz, et al.
Published: (2023)

VITRO: Vocabulary Inversion for Time-series Representation Optimization
by: Bellos, Filippos, et al.
Published: (2024)

Training-Free Cross-Lingual Dysarthria Severity Assessment via Phonological Subspace Analysis in Self-Supervised Speech Representations
by: Muller, Bernard, et al.
Published: (2026)