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
1,056 results for “keyword:"alignment"” in ICLR 2027. 253 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]RIVET: Evaluating Retrieval-Induced Value Steering and Retrieval-Stage Mitigation in Search-Augmented LLMs▼1.2k1.67
[PDF]ADAPTRLHF: ADAPTIVE KL-CONSTRAINED REIN FORCEMENT LEARNING FROM HUMAN FEEDBACK WITH GROUP-NORMALIZED AD VANTAGE ESTIMATION▲11.00
[PDF]The Comparison Graph Determines What RLHF Can Learn: Spectral Identifiability, Error Bounds, and a Pre-Training Diagnostic for Preference Data▲3.0k2.33
[PDF]Speaker-dependent Emotional Transition-aware Multimodal Dynamic Anchor Learning for Multimodal Emotion Recognition in Conversations▲3.0k2.33
[PDF]Normalize the Update, Not the Weights: Efficient Loss Weighting for Multi-Objective Pretraining▲3.0k2.33
[PDF]Learning What to Reject: Counterfactual Preference Alignment for Emotion–Cause Pair Extraction▼1.3k1.80
[PDF]No Pain, More Gain: Iterative Merging for Effective Multi-Teacher On-Policy Distillation▲9.7k2.75
[PDF]Beyond lexical alignment: Testing cross-lingual color representations against human naming▲5.4k3.00
[PDF]AudioScape-TTA: A Structured Soundscape Benchmark for Fine-Grained Text-to-Audio Evaluation▲3952.67
[PDF]Blip2Mol: Phenotype–Target Fusion for Molecular Generation via Multimodal Latent Diffusion▼13k2.00
[PDF]Probabilistic Set Representations with Partial Optimal Transport for Image–Text Retrieval▼5.3k1.33
Withdrawn or desk rejected (253)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