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
11,742 results for “keyword:"models"” in ICLR 2027. 2,929 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]TERSE: Trace-Efficiency Reward via Squeezing rEdundancy for Efficient Large Reasoning Models▲5.6k2.00
[PDF]Differentiable Latent-Tree Causal Discovery via Triplet Branch-Point Objectives and Three-Terminal Root Identification▲4743.00
[PDF]Thinking With Tools, Not With Pixels: Tool Calls as Text Scaffolds for Visual Reasoning▼12k1.67
[PDF]Repairable Uncertainty: Selective Temporal Reacquisition for Long-Video Understanding with MLLMs▲293.33
[PDF]TRPQuant: Token Rearrangement and Channel Pruning for Quantizing Large Vision-Language Models▼4.5k2.67
[PDF]Edit Only Where It Fails: Boundary-Guided Editing via Latent Transformations for Vision-Language-Action Models▼5.9k2.33
[PDF]Why MLLMs Struggle to Count: Overcoming Individuation and Aggregation Bottlenecks with ConvStack▼1.2k3.00
[PDF]READ: Query-Relevant Evidence Retrieval for Visual Token Compression in Edge–Cloud VLM Inference▲4743.00
[PDF]ExamInkBench: Benchmarking End-to-End Line-Level Student Answer Reconstruction from Complete Exam Pages▲4743.00
[PDF]Mitigating Over-Optimization in PRM-Guided Search in Mathematical Reasoning by Optimizing the Guide▼5.9k2.33
[PDF]What You Observe Determines How You Identify Causal Effects: Evaluating Causal Models across Observational Views▲4.8k3.25
[PDF]Prune Less, Pay More: Imperceptible Budget Inflation Attacks on Token Pruning in Vision-Language Models▼1.2k1.67
[PDF]Cross-Entropy Loss Falls Short: What Cross-Entropy Loss Reveals about Large-Language-Model Performance?▼1361.33
Withdrawn or desk rejected (2,929)
[PDF]Mind Your Marginals: What Governs Fidelity in Linearized Hierarchical Optimal Transport?Desk rejected1.00
[PDF]A Window Is Not a Door: Mapping the Limits and Conditions of Knowledge Editing in Language ModelsDesk rejected2.33
[PDF]Propagation Is Not Decoration: When Physical Diffraction Carries Generative ComputationWithdrawn1.00
[PDF]When Is a Policy Violation a Model Failure? Policy Observability and Failure Attribution in Agent-Safety EvaluationDesk rejected