Copertina

Learning What Matters Now: Dynamic Preference Inference under Contextual Shifts

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Cao, Xianwei, Quan, Dou, Zhang, Zhenliang, Wang, Shuang
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

CLNet: Cross-View Correspondence Makes a Stronger Geo-Localizationer
di: Cao, Xianwei, et al.
Pubblicazione: (2025)

Dynamics-Aligned Shared Hypernetworks for Contextual RL under Discontinuous Shifts
di: Benad, Jan, et al.
Pubblicazione: (2026)

Learning What Matters Now: A Dual-Critic Context-Aware RL Framework for Priority-Driven Information Gain
di: Panagopoulos, Dimitris, et al.
Pubblicazione: (2025)

Time-Scaling Is What Agents Need Now
di: Liu, Zhi, et al.
Pubblicazione: (2026)

Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts
di: Zhang, Zeyang, et al.
Pubblicazione: (2024)

Exploring Human-Machine Coexistence in Symmetrical Reality
di: Zhang, Zhenliang
Pubblicazione: (2026)

Contrastive Learning of Preferences with a Contextual InfoNCE Loss
di: Bertram, Timo, et al.
Pubblicazione: (2024)

Silencing the Guardrails: Inference-Time Jailbreaking via Dynamic Contextual Representation Ablation
di: Xing, Wenpeng, et al.
Pubblicazione: (2026)

Human-in-the-Loop Multi-Agent Ventilator Decision Support with Contextual Bandit Preference Learning
di: Li, Sijia, et al.
Pubblicazione: (2026)

Where and What: Reasoning Dynamic and Implicit Preferences in Situated Conversational Recommendation
di: Lin, Dongding, et al.
Pubblicazione: (2026)

Contextual Position Encoding: Learning to Count What's Important
di: Golovneva, Olga, et al.
Pubblicazione: (2024)

Understand What LLM Needs: Dual Preference Alignment for Retrieval-Augmented Generation
di: Dong, Guanting, et al.
Pubblicazione: (2024)

Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learning
di: Chen, Yifei, et al.
Pubblicazione: (2025)

Reinforcement Learning-based Sequential Route Recommendation for System-Optimal Traffic Assignment
di: Wang, Leizhen, et al.
Pubblicazione: (2025)

From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics
di: Cao, Bowen, et al.
Pubblicazione: (2026)

ATIR: Towards Audio-Text Interleaved Contextual Retrieval
di: Zhao, Tong, et al.
Pubblicazione: (2026)

ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs
di: Zhang, Zhenliang, et al.
Pubblicazione: (2025)

Adaptive Shielding for Safe Reinforcement Learning under Hidden-Parameter Dynamics Shifts
di: Kwon, Minjae, et al.
Pubblicazione: (2025)

Small-Margin Preferences Still Matter-If You Train Them Right
di: Pang, Jinlong, et al.
Pubblicazione: (2026)

Via Negativa for AI Alignment: Why Negative Constraints Are Structurally Superior to Positive Preferences
di: Cheng, Quan
Pubblicazione: (2026)

Lightweight Adapter Learning for More Generalized Remote Sensing Change Detection
di: Quan, Dou, et al.
Pubblicazione: (2025)

Graphs Generalization under Distribution Shifts
di: Tian, Qin, et al.
Pubblicazione: (2024)

Attention Basin: Why Contextual Position Matters in Large Language Models
di: Yi, Zihao, et al.
Pubblicazione: (2025)

Rule Learning for Knowledge Graph Reasoning under Agnostic Distribution Shift
di: Liu, Shixuan, et al.
Pubblicazione: (2025)

Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue
di: Du, Huifang, et al.
Pubblicazione: (2024)

OMPO: A Unified Framework for RL under Policy and Dynamics Shifts
di: Luo, Yu, et al.
Pubblicazione: (2024)

Domain-Contextualized Inference: A Computable Graph Architecture for Explicit-Domain Reasoning
di: Li, Chao, et al.
Pubblicazione: (2026)

Statistical Inference for Misspecified Contextual Bandits
di: Guo, Yongyi, et al.
Pubblicazione: (2025)

DynamicPO: Dynamic Preference Optimization for Recommendation
di: Hu, Xingyu, et al.
Pubblicazione: (2026)

TeachAnything: A Multimodal Crowdsourcing Platform for Training Embodied AI Agents in Symmetrical Reality
di: Liu, Zidong, et al.
Pubblicazione: (2026)

What Matters for Batch Online Reinforcement Learning in Robotics?
di: Dong, Perry, et al.
Pubblicazione: (2025)

An Enhanced Federated Prototype Learning Method under Domain Shift
di: Kuang, Liang, et al.
Pubblicazione: (2024)

SPPD: Self-training with Process Preference Learning Using Dynamic Value Margin
di: Yi, Hao, et al.
Pubblicazione: (2025)

Focus on What Matters: Fisher-Guided Adaptive Multimodal Fusion for Vulnerability Detection
di: Bian, Yun, et al.
Pubblicazione: (2026)

Now It Sounds Like You: Learning Personalized Vocabulary On Device
di: Wang, Sid, et al.
Pubblicazione: (2023)

Preference Consistency Matters: Enhancing Preference Learning in Language Models with Automated Self-Curation of Training Corpora
di: Lee, JoonHo, et al.
Pubblicazione: (2024)

What Matters in Data for DPO?
di: Pan, Yu, et al.
Pubblicazione: (2025)

Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio Regularization
di: Joshi, Sunay, et al.
Pubblicazione: (2025)

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited
di: Agrawal, Rishabh, et al.
Pubblicazione: (2026)

Contextual Preference Collaborative Measure Framework Based on Belief System
di: Yu, Hang, et al.
Pubblicazione: (2025)