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259 results for “keyword:"nki"” in ICLR 2027. 43 withdrawn or desk rejected listed apart.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]Three Steps at a Time: Learning Representations from Action Sequences in Contrastive RL▲1.7k3.33
[PDF]Tailoring the Clustering Objective to the Data: Utility-Guided Validity-Index Selection and Candidate Reranking▲6.1k2.00
[PDF]AUDITING TRAINING–EVALUATION OVERLAP, NEGATIVE SAMPLING, AND RERANKING IN MULTILINGUAL PATENT RETRIEVAL▼4.3k2.00
[PDF]Learning to Decide, Not to Reason: Parameter-Efficient Decision Operators via Low-Rank Activation Steering▼4.5k2.67
[PDF]RazorReward-RL: Capability-Aware Efficiency Optimization for LLM Reasoning via Razor Reward▲9.2k2.67
[PDF]nUniMixer: Breaking the Barrier to a Unified and Scalable Backbone for Recommender Systems▼4.5k2.67
[PDF]ROAST: Reducing Overthinking in Reasoning via Advantage Reshaping and State-aware Termination▼4.3k2.00
[PDF]Pareto-GRPO: Prompt-Local Pareto Credit Assignment for Efficient Search-Augmented Reasoning▼1.2k1.67
[PDF]Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectories▲11.00
[PDF]Is your uncertainty map wrong, or is its target? Exact diagnostics for the Tweedie diagonal, and a gradient-free alternative▼1.2k1.67
[PDF]Beyond Correctness: Benchmarking Response Behaviors and Improving Non-Thinking Outputs in Hybrid-Thinking MLLMs▲1.7k3.33
[PDF]A VC-Dimension View of Capacity and Generalization in Quantum Machine Learning with Classical Data▼1.2k1.67
[PDF]Revisiting Open-Loop Execution in Robotics: Toward Reactive, Higher-Performing Policies▼2443.33
[PDF]Regression Accuracy Is Not Enough: Destination-Agnostic Graph Embeddings for Potential-Field Navigation▼1.2k1.67
[PDF]Leaderboards Display Ranks, Benchmarks Certify Tiers: Simultaneous Inference and a Capacity Law for LLM Evaluation▼1611.50
[PDF]Learning to Rank with Weak Return Signals: Shortcut-Orthogonal Gradient Allocation for Cross-Sectional Stock Ranking▼5.8k2.33
[PDF]QESChunker: A Single Objective Unifies Overlapping and Non-Overlapping Chunking for RAG▲6.1k2.00
Withdrawn or desk rejected (43)
[PDF]When Does an Observable Lose Failure Evidence? Exact Ranking Losses for Runtime Detection in Vision–Language–Action PoliciesWithdrawn1.00
[PDF]When Geometry Flips Architecture Rankings: An Exact Theory of Alignment and ComplexityDesk rejected
[PDF]Beyond Correspondence: Understanding Response Verification in Image–Event RetrievalWithdrawn2.00
[PDF]When to Stop Thinking: Answer-Movement Certificates and Conditional Regret GuaranteesWithdrawn1.33
[PDF]Validating Rankings from Pairwise ComparisonsDesk rejected