NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
91 results for “keyword:"preference learning"” in ICLR 2027. 18 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]ECHO: Emergent Common-Mode Hidden Offsets Drive Vocabulary Collapse in Preference Optimization▲3.0k2.33
[PDF]MetaSteer: Context-Conditioned, Non-linear Steering via Attention-Projection Adaptation▲9.2k2.67
[PDF]TrustRoboReward: Preference-Ordered Isotonic Score Editing for Multi-Paradigm Robot Reward Models▼4.3k2.00
[PDF]Targeted Active Learning for Preference-Based Treatment Effects on Multivariate Outcomes▼5.8k2.33
[PDF]From Task-Oriented Agents to Personalized Teammates: Understanding Continual Adaptation in Cooperative Games▲1.7k3.33
[PDF]When Higher Scores Yield Less Feedback: Score Saturation in Self-Rewarding Language Models▲9.2k2.67
[PDF]AgentJudge:From Real Agent Trajectories to Multi-Granularity Judging and Agent–Judge Co-Evolution▲3.8k2.50
[PDF]Online Preference Learning via Generalized Linear Models: Monotonicity and Convergence of SGD▲3.0k2.33
[PDF]Not All Tokens Are Equal: Entropy-Guided Credit Assignment for Direct Preference Optimization▼4.3k2.00
[PDF]Learning Topology Preferences for Adaptive Communication Topology Generation in Multi-Agent Systems▼5.8k2.33
[PDF]Raising the Floor, Lowering the Ceiling: Adaptive Reward Bounds for Direct Preference Optimization▼4.3k2.00
Withdrawn or desk rejected (18)
[PDF]The Horizon of Reward GuidanceDesk rejected
[PDF]From Soft Targets to Reward Signals: How Assignment and Reward Objectives InteractWithdrawn1.33