Image de couverture de livre

Learning Where It Matters: Geometric Anchoring for Robust Preference Alignment

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Cho, Youngjae, Kim, Jongsuk, Kim, Ji-Hoon
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

AVCap: Leveraging Audio-Visual Features as Text Tokens for Captioning
par: Kim, Jongsuk, et autres
Publié: (2024)

EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning
par: Kim, Jongsuk, et autres
Publié: (2024)

Adversarial Preference Learning for Robust LLM Alignment
par: Wang, Yuanfu, et autres
Publié: (2025)

Cost-Efficient LLM Serving in the Cloud: VM Selection with KV Cache Offloading
par: Kim, Kihyun, et autres
Publié: (2025)

Spread Preference Annotation: Direct Preference Judgment for Efficient LLM Alignment
par: Kim, Dongyoung, et autres
Publié: (2024)

Preference Alignment with Flow Matching
par: Kim, Minu, et autres
Publié: (2024)

Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment
par: D'Oosterlinck, Karel, et autres
Publié: (2024)

Expert with Clustering: Hierarchical Online Preference Learning Framework
par: Zhou, Tianyue, et autres
Publié: (2024)

Synergy-CLIP: Extending CLIP with Multi-modal Integration for Robust Representation Learning
par: Cho, Sangyeon, et autres
Publié: (2025)

Policy-labeled Preference Learning: Is Preference Enough for RLHF?
par: Cho, Taehyun, et autres
Publié: (2025)

Self-Abstraction Learning for Effective and Stable Training of Deep Neural Networks
par: Cho, Wonyong, et autres
Publié: (2026)

ORFit: One-Pass Learning via Bridging Orthogonal Gradient Descent and Recursive Least-Squares
par: Min, Youngjae, et autres
Publié: (2022)

ASAP: Attention Sink Anchored Pruning
par: Lee, Jaehyuk, et autres
Publié: (2026)

Coupling-Robust Accuracy in Multiphysics Physics Informed Neural Networks via Kronecker-Preconditioned Optimization
par: Park, Youngjae, et autres
Publié: (2026)

BAPO: Base-Anchored Preference Optimization for Overcoming Forgetting in Large Language Models Personalization
par: Lee, Gihun, et autres
Publié: (2024)

Hardware-Efficient Softmax and Layer Normalization with Guaranteed Normalization for Edge Devices
par: Choi, Dawon, et autres
Publié: (2026)

Lightweight Robust Direct Preference Optimization
par: Kim, Cheol Woo, et autres
Publié: (2025)

Task Addition in Multi-Task Learning by Geometrical Alignment
par: Yim, Soorin, et autres
Publié: (2024)

Debiasing Online Preference Learning via Preference Feature Preservation
par: Kim, Dongyoung, et autres
Publié: (2025)

Preference Robustness for DPO with Applications to Public Health
par: Kim, Cheol Woo, et autres
Publié: (2025)

TRACE: Distilling Where It Matters via Token-Routed Self On-Policy Alignment
par: Wang, Jiaxuan, et autres
Publié: (2026)

Similarity as Reward Alignment: Robust and Versatile Preference-based Reinforcement Learning
par: Rajaram, Sara, et autres
Publié: (2025)

Swap-guided Preference Learning for Personalized Reinforcement Learning from Human Feedback
par: Kim, Gihoon, et autres
Publié: (2026)

SCRec: A Scalable Computational Storage System with Statistical Sharding and Tensor-train Decomposition for Recommendation Models
par: Yang, Jinho, et autres
Publié: (2025)

Feature Structure Distillation with Centered Kernel Alignment in BERT Transferring
par: Jung, Hee-Jun, et autres
Publié: (2022)

ADPO: Anchored Direct Preference Optimization
par: Zixian, Wang
Publié: (2025)

Personalized Federated Learning for Gradient Alignment
par: Kim, Dongwon, et autres
Publié: (2026)

PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation
par: Liu, Runze, et autres
Publié: (2023)

References Indeed Matter? Reference-Free Preference Optimization for Conversational Query Reformulation
par: Kim, Doyoung, et autres
Publié: (2025)

Robust LLM Alignment via Distributionally Robust Direct Preference Optimization
par: Xu, Zaiyan, et autres
Publié: (2025)

Robust Multi-Objective Preference Alignment with Online DPO
par: Gupta, Raghav, et autres
Publié: (2025)

Learning Generalizable Visuomotor Policy through Dynamics-Alignment
par: Lee, Dohyeok, et autres
Publié: (2025)

Compare Where It Matters: Using Layer-Wise Regularization To Improve Federated Learning on Heterogeneous Data
par: Son, Ha Min, et autres
Publié: (2021)

PrefPoE: Advantage-Guided Preference Fusion for Learning Where to Explore
par: Lin, Zhihao, et autres
Publié: (2025)

Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomy
par: Cho, Jung-Hoon, et autres
Publié: (2023)

Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment
par: Kim, Bryan Sangwoo, et autres
Publié: (2025)

Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User Preferences
par: Koo, Jabin, et autres
Publié: (2026)

Beyond RLHF: A Unified Theoretical Framework of Alignment
par: Yun, Jihun, et autres
Publié: (2025)

CompassDPO: Dynamics-Controlled Direct Preference Optimization for Robust Safety Alignment
par: Liu, Jilong, et autres
Publié: (2026)

Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning
par: Pranger, Stefan, et autres
Publié: (2024)