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
402 results for “keyword:"preference"” in ICLR 2027. 80 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Reducing Hallucination in Multimodal Large Language Models through Hard Grounding Preference Supervision▼1.2k1.67
[PDF]FlowForget: Data Unlearning in Flow Matching Models via On-Policy Distillation and Preference Optimization
[PDF]BranchWise: A Path Is Not a Policy — Unfolding Successful Trajectories into Model-Tailored Decision Boundaries▲9.2k2.67
[PDF]Directing Safety Signals to the Appropriate Neurons: Multilingual Safety Alignment through Selective Neuron Masking▲9.2k2.67
[PDF]Can AI Reviewers See Your Efforts to Improve Your Paper? A Large-Scale Study of Paper Revision Trajectories▲9.2k2.67
[PDF]HPOD: Hierarchical Preference Optimization via On-Policy Distillation for LLM Concept Unlearning
[PDF]Task-Aware Configuration Selection for Preference Optimization via Early Training Dynamics▲3.0k2.33
[PDF]CoHabit Arena: Evaluating Personal Preference Realization in Long-Horizon Human-Agent CoHabitation▼1.2k1.67
[PDF]DEFLECT: Temporal Counterfactual Preference Learning for Delay-Robust Asynchronous VLAs▼5.8k2.33
[PDF]Disagreement in, Disagreement Out? Uneven Downstream Effects of Harm Classifier Differences▼5.8k2.33
[PDF]GOT-Align: Learning Generative Operation Tokenizers for Preference-Aligned Image Enhancement▼4.3k2.00
[PDF]Preference-Guided Tree Search for Feasible Solution Generation in Integer Linear Programming▲2843.00
[PDF]Mole-PAIR: Improving Reliability of Molecular Foundation Models with Preference Optimization▼5.8k2.33
Withdrawn or desk rejected (80)
[PDF]Remembering Is Not Navigating: Goal Recurrence and Closed-Loop Success in City-Scale Drone NavigationWithdrawn1.67
[PDF]Same Objective, Different Optimizer: Preference-Flip Noise versus Label Smoothing in DPODesk rejected
[PDF]FidelityFlow-PO: Bandit-Guided Allocation of Context Fidelity for Long-Context DPODesk rejected
[PDF]The Horizon of Reward GuidanceDesk rejected