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
248 results for “keyword:"fid"” in ICLR 2027. 75 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]They Know When They're Unsure: Confidence-Gated Acceptance as a Two-Sided Defense against Sycophancy in Video Language Models▼1.2k1.67
[PDF]Knowing When to Abstain: Risk-Aware Criteria for Action-Level Selectivity in Trading Agents▼1.2k1.67
[PDF]StatTS-FM: Statistical Structure as an Inductive Bias for Time-Series Foundation Models▲6.1k2.00
[PDF]The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation▼4.3k2.00
[PDF]Confidence Falls Short: Asymmetric Certainty Gains from Optimization Hinder Multimodal Classification▲2623.67
[PDF]TraceConf: Visually Traceable and Calibrated Confidence in Multimodal Large Language Models▲3952.67
[PDF]Defect-Aware Confidence Routing: Black-Box Confidence Signals Have Regime-Dependent Reliability▼5.3k1.33
[PDF]Decouple to Reconcile: Explicit Inter- and Intra-Exposure Motion Modeling for Night Image Restoration▼4.3k2.00
[PDF]Low-Confidence Remasking Traps Flexibility: Realizing Arbitrary-Order Potential for Diverse Rollouts in Diffusion LLMs▲5103.00
[PDF]What FID Hides: Detecting, Ranking, and Diagnosing Deviations in Generative Evaluation▼4.3k2.00
[PDF]Perturbation Attribution Fragmentation under Alias-Redundant Evidence in Knowledge-Graph RAG▼1361.33
[PDF]FidPoster: End-to-End Product Poster Generation with Fine-grained Product Detail Fidelity▲3.8k2.50
[PDF]AutoLLMResearch: Training Agents for Automating LLM Experiment Configuration — Learn from Cheap, Optimize Expensive▼1361.33
[PDF]When Better Prediction Makes Worse Generation: Teacher-Domain Alignment in Knowledge Distillation▼4.5k2.67
[PDF]Dispersion Is Not Doubt: Rethinking LLM Confidence Estimation When Multiple Answers Are Valid▲3.0k2.33
Withdrawn or desk rejected (75)
[PDF]Attested but Unaccounted: DP-SGD Privacy Accounting as a Precondition of Every StepWithdrawn1.67
[PDF]The Interface Is the Policy: Output Typing, Calibration, and Confidence-Gated Routing in LLM Trading AgentsDesk rejected1.00
[PDF]Commit Order, Not Commit Rate: Answer Availability and Prefix Preservation in Diffusion Language ModelsWithdrawn1.67
[PDF]Beyond a Single Surrogate: Consistency-Weighted Alignment for Instruction-Free Multimodal ExtensionWithdrawn1.00