Cover Image

Geometry Preserving Loss Functions Promote Improved Adaptation of Blackbox Generative Model

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mitra, Sinjini, Kyriakakis, Constantine, Liang, Shenyuan, Srivastava, Anuj, Turaga, Pavan
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

Graph Network Modeling Techniques for Visualizing Human Mobility Patterns
by: Mitra, Sinjini, et al.
Published: (2025)

Gated Adaptation for Continual Learning in Human Activity Recognition
by: Azghan, Reza Rahimi, et al.
Published: (2026)

Role of Mixup in Topological Persistence Based Knowledge Distillation for Wearable Sensor Data
by: Jeon, Eun Som, et al.
Published: (2025)

Structure-Preserving Learning Improves Geometry Generalization in Neural PDEs
by: Shaffer, Benjamin D., et al.
Published: (2026)

Whispering to a Blackbox: Bootstrapping Frozen OCR with Visual Prompts
by: Samandarov, Samandar, et al.
Published: (2026)

Model Merging on Loss Landscape: A Geometry Perspective
by: Lu, Juanwu, et al.
Published: (2026)

XSub: Explanation-Driven Adversarial Attack against Blackbox Classifiers via Feature Substitution
by: Vu, Kiana, et al.
Published: (2024)

Foundation-Preserving Adaptation via Generalized Rayleigh-Quotient Optimization
by: Kim, Dongjun, et al.
Published: (2026)

Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining
by: Sow, Daouda, et al.
Published: (2025)

Field-Theoretic Memory for AI Agents: Continuous Dynamics for Context Preservation
by: Mitra, Subhadip
Published: (2026)

PostMark: A Robust Blackbox Watermark for Large Language Models
by: Chang, Yapei, et al.
Published: (2024)

AttenGluco: Multimodal Transformer-Based Blood Glucose Forecasting on AI-READI Dataset
by: Farahmand, Ebrahim, et al.
Published: (2025)

Preserving Vector Space Properties in Dimensionality Reduction: A Relationship Preserving Loss Framework
by: Weinwurm, Eddi, et al.
Published: (2025)

How Strategic Agents Respond: Comparing Analytical Models with LLM-Generated Responses in Strategic Classification
by: Xie, Tian, et al.
Published: (2025)

The Geometry of Grokking: Norm Minimization on the Zero-Loss Manifold
by: Musat, Tiberiu
Published: (2025)

What Fundamental Structure in Reward Functions Enables Efficient Sparse-Reward Learning?
by: Shihab, Ibne Farabi, et al.
Published: (2025)

Early-Warning Signals of Grokking via Loss-Landscape Geometry
by: Xu, Yongzhong
Published: (2026)

A Principled Loss Function for Direct Language Model Alignment
by: Tan, Yuandong
Published: (2025)

GeoRA: Geometry-Aware Low-Rank Adaptation for RLVR
by: Zhang, Jiaying, et al.
Published: (2026)

MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projection
by: Shen, Yixian, et al.
Published: (2025)

MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projection
by: Shen, Yixian, et al.
Published: (2024)

On Implications of Scaling Laws on Feature Superposition
by: Katta, Pavan
Published: (2024)

Beyond Loss Guidance: Using PDE Residuals as Spectral Attention in Diffusion Neural Operators
by: Sawhney, Medha, et al.
Published: (2025)

Spectral Discovery of Continuous Symmetries via Generalized Fourier Transforms
by: Karjol, Pavan, et al.
Published: (2026)

Improved Constrained Generation by Bridging Pretrained Generative Models
by: Liang, Xiaoxuan, et al.
Published: (2026)

Meta-Learning Adaptive Loss Functions
by: Raymond, Christian, et al.
Published: (2023)

Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
by: Rosset, Corby, et al.
Published: (2024)

Learning Equivariant Functions via Quadratic Forms
by: Karjol, Pavan, et al.
Published: (2025)

Anytime-Valid Answer Sufficiency Certificates for LLM Generation via Sequential Information Lift
by: Akter, Sanjeda, et al.
Published: (2025)

A Note on Loss Functions and Error Compounding in Model-based Reinforcement Learning
by: Jiang, Nan
Published: (2024)

Visualizing Loss Functions as Topological Landscape Profiles
by: Geniesse, Caleb, et al.
Published: (2024)

AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation
by: Du, Weihua, et al.
Published: (2026)

Flow Matching on General Geometries
by: Chen, Ricky T. Q., et al.
Published: (2023)

Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics
by: Pattichis, Andreas, et al.
Published: (2026)

Improving Node Representation by Boosting Target-Aware Contrastive Loss
by: Lin, Ying-Chun, et al.
Published: (2024)

Federated Loss Exploration for Improved Convergence on Non-IID Data
by: Internò, Christian, et al.
Published: (2025)

Improving Epidemic Analyses with Privacy-Preserving Integration of Sensitive Data
by: Guan, Zihan, et al.
Published: (2025)

Forming Auxiliary High-confident Instance-level Loss to Promote Learning from Label Proportions
by: Ma, Tianhao, et al.
Published: (2024)

Generative Urban Flow Modeling: From Geometry to Airflow with Graph Diffusion
by: Giral, Francisco, et al.
Published: (2025)

A Novel Hierarchical Integration Method for Efficient Model Merging in Medical LLMs
by: Timilsina, Prakrit, et al.
Published: (2025)