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
331 results for “keyword:"supervision"” in ICLR 2027. 78 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]The Same-Family Halo: A Gold-Free Audit of Source-Dependent Agreement in LLM Silver Labeling▼1361.33
[PDF]CROSS-TASK GAINS WITHOUT AUXILIARY LABELS: ARCHITECTURE-PRESERVING ABLATIONS UNDER DISJOINT SUPERVISION▼1.2k1.67
[PDF]ORION: EXACT CANONICAL-STATE SUPERVISION FOR SYSTEMATIC GENERALIZATION IN TRANSFORMERS▼1.2k1.67
[PDF]Conservation-Aware Fine-Tuning: Injecting Physical Laws into LLM Reasoning via Preference Optimization▼1361.33
[PDF]ProCrit: Self-Elicited Multi-Perspective Reasoning with Critic-Guided Revision for Multimodal Sarcasm Detection▼5.8k2.33
[PDF]What Does a Failed Rollout Supervise? Separating Policy Failure from Recoverability in Tool Agents▼4.3k2.00
[PDF]Prediction Can Benefit Understanding: Visual Prediction as Complementary Supervision for Video LLMs▲9.2k2.67
[PDF]EviSR-GS:Evidence-Guided Supervision and Refinement for Sparse-View Gaussian Splatting▼4.3k2.00
[PDF]Rationale Content Shapes What a Detector Learns: Controlled Supervision for Person-Centric AI-Image Forensics▲3.0k2.33
[PDF]MedPreceptor: Decoupled Process Supervision for Active Clinical Inquiry in Multi-Turn Medical Consultations▲432.75
[PDF]Visitation Is Not Supervision: D-Optimality-Guided Allocation for On-Policy Distillation▼5.8k2.33
[PDF]Executable Gold Semantics: Compiling Gold Labels for Auditing Memory Transitions in Language Agents▼4.3k2.00
[PDF]Is Dense Supervision Worth Its Cost? A Budget-Controlled Study of Supervision Allocation in MAML▼4.3k2.00
[PDF]Learning from Partially Corrected Labels: A Framework for Human-in-the-Loop Data Curation with Statistical Guarantees▲3.0k2.33
[PDF]Beyond a Single Sparse Solution: Certifying Feature Necessity under Inexact Multi-Label Supervision▼5.8k2.33
[PDF]Staged Latent Chain-of-Thought for Sequential Counterfactual Prediction with Universal Holdout Calibration▼4.3k2.00
[PDF]Consensus Is Not Correctness: Reliability-Aware Self-Teaching for Unsupervised Self-Distillation▲11.20
[PDF]Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL▲6.1k2.00
Withdrawn or desk rejected (78)
[PDF]Beyond the Local View: Predicting Correction Gains for Sparse On-Policy DistillationWithdrawn1.33
[PDF]When Should the Count Change? Learning State Maintenance for Causal Video CountingDesk rejected2.00