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
11,760 results for “keyword:"models"” in ICLR 2027. 2,911 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Focus When Necessary: Adaptive Routing and Collaborative Grounding for Training-Free Visual Grounding▼4.3k2.00
[PDF]KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization▲5103.00
[PDF]Learning to Verify by Doing: A Self-Renewing Policy–Verifier Loop for Sustained Self-Improvement▼1.2k1.67
[PDF]StructViz-Bench: A Controlled Study of Visualization-Format Dependence in Multimodal LLM Reasoning over Structured Data▼1.2k1.67
[PDF]PerturbBridge: Reference-Process Design for Heterogeneity-Aware Single-Cell Perturbation Prediction▼5.9k2.50
[PDF]CLOVER: Coverage-Led Optimization of Verifiable Evidence Reasoning for AI-Generated Image Detection▲6.1k2.00
[PDF]Attention Sinks as Knowledge-Conflict Arbiters: Training-Free Gating-Preserving Routing for Contextual Faithfulness▲3942.67
[PDF]Learning a Generative Inverse to Adapt the Forward: Source-Free Domain Adaptation for Sequence Regression▲3942.67
[PDF]EvoFG: Decoupling Operator Evolution and Feature Binding for Efficient Feature Generation▼5.3k1.33
[PDF]Verify, Act, Distill: Turning Test-Time Compute into Test-Time Adaptation for Vision-Language-Action Models▼1.2k1.67
[PDF]Activation Diffusion, Revisited: Design Choices for Diffusion-Based Metamodels of LLM Activations▼5.8k2.33
[PDF]Representation, Not Search Strategy: Typed DSL Operators Transfer to Unseen Routing Variants Where Free-Form Code Does Not▼71.25
[PDF]From Natural-Language Propositions to Lean Proofs: Proof-Search Feedback for Source-Grounded Re-Formalization▲9.2k2.67
[PDF]SHADOW ANCHORING: GROUNDING HUMAN- INTERPRETABLE CONCEPTS IN TRANSFORMERS VIA SPARSE AUTOENCODERS▼1361.33
Withdrawn or desk rejected (2,911)
[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