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
71 results for “keyword:"direct preference optimization"” in ICLR 2027. 7 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Extending Controllability from Composition and Topology to Domain Identity in Language-Model Protein Generation▲5103.00
[PDF]VasoDPO: Aligning Treatment Actions with Patient States through State-Fixed Preference Construction▼4.5k2.25
[PDF]ECHO: Emergent Common-Mode Hidden Offsets Drive Vocabulary Collapse in Preference Optimization▲3.0k2.33
[PDF]HDPO: Aligning Large Language Models to Software Architecture via Hierarchical Preference Optimization▼1.2k1.67
[PDF]First-Order In-Context Shapley: Scalable Data Auditing for LLM Alignment and Evaluation▼5.8k2.33
[PDF]When Higher Scores Yield Less Feedback: Score Saturation in Self-Rewarding Language Models▲9.2k2.67
[PDF]Multimodal Bias in AI-Mediated Markets: Benchmarking, Preference Optimization, and Human Valuation▲6.1k2.00
[PDF]Beyond Uniform Forgetting in Alignment: Characterising, Predicting, and Recovering Retention in Sequential Preference Optimisation▼4.3k2.00
[PDF]Sinkhorn-DPO: Distributionally Robust Preference Alignment via Entropic Optimal Transport▼1351.33
[PDF]LEMMA: Learned Model Merging for Text-to-Image Generation via Multi-Objective Optimization▼5.8k2.33
[PDF]Ground the Past to Predict the Future: Optimizing Natural-Language User Representations Without Downstream Supervision▲5.4k3.00
[PDF]The Shape of the DPO Hyperparameter Landscape: What to Measure, How It Moves with Scale, and When Not to Transfer It▼5.8k2.33
[PDF]Not All Preferences Are Strict: Tie-Aware Preference Optimization for Multi-Image MLLMs▼5.8k2.33
[PDF]Not All Tokens Are Equal: Entropy-Guided Credit Assignment for Direct Preference Optimization▼4.3k2.00
[PDF]THE JUDGE LOTTERY: DIAGNOSING WHETHER COMPARISONS BETWEEN STOCHASTIC LLM JUDGES ARE ADEQUATELY SUPPORTED BY RESAMPLING EVIDENCE▼1351.33
[PDF]When Richer Preferences Do Not Help: Rubric Redundancy, Pair Selection, and Training Exposure in Scientific QA▼4.3k2.00
[PDF]Learning What to Reject: Counterfactual Preference Alignment for Emotion–Cause Pair Extraction▼1.3k1.80
[PDF]Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution▲3.0k2.33
Withdrawn or desk rejected (7)
[PDF]FidelityFlow-PO: Bandit-Guided Allocation of Context Fidelity for Long-Context DPODesk rejected
[PDF]Less Drift, Better Alignment: Selecting the Fittest Preference Data for Offline DPOWithdrawn2.00