Sanjeda Akter

CoRR, April, 2026

Continual Calibration: Coverage Can Collapse Before Accuracy in Lifelong LLM Fine-Tuning.

[BibT_eX]

[DOI]

CoRR, April, 2026

Why Colors Make Clustering Harder:Global Integrality Gaps, the Price of Fairness, and Color-Coupled Algorithms in Chromatic Correlation Clustering.

[BibT_eX]

[DOI]

CoRR, April, 2026

Minimax Optimality and Spectral Routing for Majority-Vote Ensembles under Markov Dependence.

[BibT_eX]

[DOI]

CoRR, April, 2026

Beyond Accuracy: A Unified Random Matrix Theory Diagnostic Framework for Crash Classification Models.

[BibT_eX]

[DOI]

CoRR, February, 2026

Calibrated Adaptation: Bayesian Stiefel Manifold Priors for Reliable Parameter-Efficient Fine-Tuning.

[BibT_eX]

[DOI]

CoRR, February, 2026

Grassmannian Mixture-of-Experts: Concentration-Controlled Routing on Subspace Manifolds.

[BibT_eX]

[DOI]

CoRR, February, 2026

On the Sparsifiability of Correlation Clustering: Approximation Guarantees under Edge Sampling.

[BibT_eX]

[DOI]

CoRR, February, 2026

Learning to Forget Attention: Memory Consolidation for Adaptive Compute Reduction.

[BibT_eX]

[DOI]

CoRR, February, 2026

Certificate-Guided Pruning for Stochastic Lipschitz Optimization.

[BibT_eX]

[DOI]

CoRR, January, 2026

CalPro: Prior-Aware Evidential-Conformal Prediction with Structure-Aware Guarantees for Protein Structures.

[BibT_eX]

[DOI]

CoRR, January, 2026

Adaptive Constraint Propagation: Scaling Structured Inference for Large Language Models via Meta-Reinforcement Learning.

[BibT_eX]

[DOI]

CoRR, January, 2026

Beyond Variance: Knowledge-Aware LLM Compression via Fisher-Aligned Subspace Diagnostics.

[BibT_eX]

[DOI]

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

Adaptive Constraint Propagation: Scaling Structured Inference for Large Language Models via Meta-Reinforcement Learning.

[BibT_eX]

[DOI]

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025

LLM-Guided Probabilistic Fusion for Label-Efficient Document Layout Analysis.

[BibT_eX]

[DOI]

CoRR, November, 2025

Temporal Zoom Networks: Distance Regression and Continuous Depth for Efficient Action Localization.

[BibT_eX]

[DOI]

CoRR, November, 2025

Valid Stopping for LLM Generation via Empirical Dynamic Formal Lift.

[BibT_eX]

[DOI]

CoRR, October, 2025

Calibrated and Resource-Aware Super-Resolution for Reliable Driver Behavior Analysis.

[BibT_eX]

[DOI]

Senem Velipasalar Gursoy

CoRR, September, 2025

Selective Risk Certification for LLM Outputs via Information-Lift Statistics: PAC-Bayes, Robustness, and Skeleton Design.

[BibT_eX]

[DOI]

CoRR, September, 2025

What Fundamental Structure in Reward Functions Enables Efficient Sparse-Reward Learning?

[BibT_eX]

[DOI]

CoRR, September, 2025

Differentiable Entropy Regularization for Geometry and Neural Networks.

[BibT_eX]

[DOI]

CoRR, September, 2025

Inducing Faithfulness in Structured Reasoning via Counterfactual Sensitivity.

[BibT_eX]

[DOI]

CoRR, September, 2025

Detecting and Mitigating Reward Hacking in Reinforcement Learning Systems: A Comprehensive Empirical Study.

[BibT_eX]

[DOI]

CoRR, July, 2025

Large Language Models for Crash Detection in Video: A Survey of Methods, Datasets, and Challenges.

[BibT_eX]

[DOI]

CoRR, July, 2025

Image Segmentation with Large Language Models: A Survey with Perspectives for Intelligent Transportation Systems.

[BibT_eX]

[DOI]

CoRR, June, 2025

Efficient Unstructured Pruning of Mamba State-Space Models for Resource-Constrained Environments.

[BibT_eX]

[DOI]

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

Cache-Efficient Posterior Sampling for Reinforcement Learning with LLM-Derived Priors Across Discrete and Continuous Domains.

[BibT_eX]

[DOI]

Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

HMAE: Self-Supervised Few-Shot Learning for Quantum Spin Systems.

[BibT_eX]

[DOI]