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
259 results for “keyword:"nki"” in ICLR 2027. 43 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Winning Without Composing, Losing While Generalizing: Separating Better Scores from Better Choices in Recommendation▼5.8k2.33
[PDF]Constructing Pareto Frontiers of Optimal Reasoning Termination Methods for Overthinking in Reasoning Models▼1.2k1.67
[PDF]Learning Chunk Values from Partial Execution in Offline-to-Online Reinforcement Learning▼5.8k2.33
[PDF]RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction▲5103.00
[PDF]One Step Is Often Enough: Accelerating VLA Action Heads with Training-Free Marginal-Aligned Warm Starts▲3952.67
[PDF]Same Results, Different Rankings: Measuring Evaluation-View Dependence in LLM Agent Benchmarks▼4.3k2.00
[PDF]Visual Dependence and Utility in Multimodal Knowledge Graph Completion: A Controlled Pilot Study▼1.2k1.67
[PDF]On Evaluating the Adversarial Robustness of Foundation Models for Multimodal Entity Linking▼1.2k1.67
[PDF]Relative Temporal Alignment for Real-Time Execution of Vision-Language-Action Policies▼5.8k2.33
[PDF]SWAP: Switched Action Chunking Policies with Massively Parallelized Multi-Task Reinforcement Learning▼1.2k3.00
[PDF]Does Representation Similarity Rank Distillability? A Bounded Audit of Knowledge Distillation▼1361.33
[PDF]Logic Density Pruning: Mitigating Overthinking via Step-Level Chain of Thought Compression▼1.2k1.67
[PDF]A Dynamic Bradley-Terry Approach to Learning Time-Varying Leaderboards from Sparse Comparisons in Sports and LLM Evaluation▼5.8k2.33
[PDF]PersonaBias: Personalized Chain-of-Thought Optimization for Mitigating Personalized Bias in Large Language Models▼5.8k2.33
[PDF]From Ranking Quality to Query Complexity: Exact-AUC Minimax Recovery with Ordinal Predictions▲3952.67
Withdrawn or desk rejected (43)
[PDF]Beyond Aggregate Forgetting: Knowledge Graph Unlearning Can Disagree with RetrainingDesk rejected
[PDF]When Do Independent Scientific Alternatives Emerge? Evaluating LLM Predictions of Waiting TimesWithdrawn1.00
[PDF]Are We Recovering Mechanisms? Objective-Level Recovery Gaps in Mechanistic InterpretabilityWithdrawn1.33
[PDF]SSP-Bench: A Hybrid Data Generation Framework for Safety, Security, and Privacy EvaluationWithdrawn2.00
[PDF]Diagnosing Poisoning Effects in Adapted LLM Guardrails: Beyond Fixed-Threshold EvaluationDesk rejected
[PDF]Lost in Aggregation: A General Perspective on Zero-Cost Neural Architecture SearchWithdrawn1.50