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
1,057 results for “keyword:"alignmen"” in ICLR 2027. 253 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]When Do Models Admit They Are Wrong? Failure Disclosure Is Unstable Under Reinforcement Learning▼1.2k1.67
[PDF]Visual Representations in the Human Medial Temporal Lobe During Naturalistic Movie Viewing▼4.5k2.67
[PDF]Comparable Outcome, Different Execution: How Should We Measure Evaluation Awareness in Coding Agents?▼12k1.67
[PDF]Sinkhorn-DPO: Distributionally Robust Preference Alignment via Entropic Optimal Transport▼1361.33
[PDF]One Self, Many Masks: Language Models Have a Self That Persists Beneath Their Personas▼1.2k1.67
[PDF]Alignment and Convergence Analyses of Gradient Flow in Two-Layer Convolutional Neural Networks▲6.6k3.33
[PDF]Does Register-Length Flexibility Help Peptide–MHC-II Classification? A Controlled Ablation on the Chicken Allele BLB2▼1361.33
[PDF]The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology▼4.3k2.00
[PDF]Graph-Parameterized Capacity for Latent Multi-Hop Recall: Usage, Compression, and Composition▼13k2.00
[PDF]Encoding Without Alignment: Analyzing The Correspondence Between LLMs And The Visual Cortex▼1.2k1.67
[PDF]The Strong, weak and benign Goodhart's law: An independence-free and paradigm-agnostic formalisation▲5.4k3.00
[PDF]Generalizable RNA 3D Structure Prediction with RNA-Adapted Protenix and Agentic Tree Search▼1.2k1.67
[PDF]Serialization Is Not Enough: From Presentation to Utilization in LLM-Based Graph Prediction▲3952.67
Withdrawn or desk rejected (253)
[PDF]Everything in Moderation: Interior Per-Domain Coverage Optima and Gap-Preserving Fixed-Budget Alignment in Multi-Domain Mid-TrainingDesk rejected
[PDF]Machine Love: Emergent Bonding Behavior in Large Language Models and Its Implications for AI SafetyDesk rejected
[PDF]Why Benign Post-Training Induces Safety Gate Collapse: Changes in Harmful Activation Geometry Relative to the Inherited Refusal GateWithdrawn1.67
[PDF]dREPA: Difficulty-Aware Representation Alignment Accelerates Diffusion TrainingDesk rejected2.00
[PDF]Cross-Domain Micro-Action Learning via Inter-Space Alignment and Prototype CalibrationWithdrawn1.67
[PDF]Beyond Domain Alignment: Anatomically Constrained Unsupervised Adaptation for Optic Nerve Head SegmentationWithdrawn1.00