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331 results for “keyword:"supervision"” in ICLR 2027. 78 withdrawn or desk rejected listed apart.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]Tracing Error Origins and Propagation: Dependency-Grounded Process Supervision for Mathematics and Physics▲6.1k2.00
[PDF]ReDraft: Your Verifier Is Secretly a Depth Supervisor for Recurrent Speculative Decoding▲5103.00
[PDF]When Passing Checks Are Not Enough: Separating Evidence Reports from Outcome Judgments in Coding Agents▲3.0k2.33
[PDF]Credit Without Ground Truth: Claim-Matched Evaluation of Step-Level Credit with Finite Executed Replay▼1361.33
[PDF]Learning What to Check: Process Supervision with Artifact-Grounded Verification for Scientific Agents▼1361.33
[PDF]Prompt Prototype Learning (PPL): Rethinking Text Supervision for AI-Generated Image Detection▲3952.67
[PDF]Perfect Labels for Free? What Exact Answers and Exact Traces Teach a Small Language Model▼1.2k1.67
[PDF]When Frozen Features Help or Harm: Correspondence and Auxiliary Supervision in Antibody–Antigen Prediction▼1361.33
[PDF]Two Negatives Make a Positive: Dual Negative Learning for Continual Knowledge Graph Embedding▲3.0k2.33
[PDF]AgentLTL: A Trace-Verification Framework for Measuring, Enforcing, and Training Procedural Compliance in Tool-Using LLM Agents▼1.2k1.67
[PDF]Paired Residual Adaptation for Vision-Language-Action Policies under Transient Visual Mislocalization▼5.8k2.33
[PDF]Looped Transformers under the Jacobian Lens: Does the Global Workspace Survive Recurrence?▼4.3k2.00
[PDF]BeamScene: A Physically Consistent Framework with Beam-Footprint Geometry for 3D LiDAR Scene Completion▲5103.00
[PDF]ChronoCheck: Scale Improves Per-Claim Faithfulness but Shifts Time-Series Rationales Toward the Claims Models Get Wrong▼1.2k1.67
[PDF]Reliable Supervision and Semantic Initialization for Noisy Multi-Label Cross-Modal Hashing Retrieval▼1.2k3.00
[PDF]What the Label Admits, the Model Asserts: Evidence-Constrained Supervision of Vision-Language Models from Expert Prose▲11.00
[PDF]Knowing Whom to Erase: Instruction-Routed Audio-Visual Subject Removal for Human-Centric Speech and Music Videos▼5.8k2.33
[PDF]MoldCoder: Automated Construction of Code Instruction Data Using Real Test Execution as Functional Supervision▲3952.67
[PDF]PHYSINET:PHYSICS-GUIDED WEAKLY-SUPERVISED DEEP LEARNING FOR INTERPRETABLE SEISMIC EVENT CLASSIFICATION AND INVERSE PHYSICAL DISCOVERY▼4.3k2.00
[PDF]How to Reduce Localization Ambiguity? Geometry-Semantic Constrained BEV Representation Learning for Satellite-Ground Localization▲3.0k2.33
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