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
904 results for “keyword:"ema"” in ICLR 2027. 260 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]HAIR: Fine-Strand Hidden-State Anchored Implicit Reasoning with Single-Prefill Inference▲3.0k2.40
[PDF]VocabAudit: Auditing Inference-Vocabulary Sensitivity in Training-Free Open-Vocabulary Segmentation▼5.8k2.33
[PDF]Predicting Reasoning Errors Before They Occur: A Prompt-Side Activation Direction Anticipates Correctness in a Large Language Model▼1361.33
[PDF]ORBIT: EFFICIENT VERIFICATION OF EDITED LLM OUTPUTS WITH COMPACT ROUTING HINTS AND LOCAL SEMANTIC ASSESSMENT▼1.3k1.75
[PDF]Same Knowledge, Different Graph: Knowledge-Graph Foundation Models Are Not Schema-Invariant▼4.5k2.67
[PDF]DriftBench: An Execution-Based Benchmark for LLM SQL Query Repair Under Schema Evolution▲3952.67
[PDF]Beyond Semantic Similarity: Abstraction-Based Demonstration Retrieval for Mathematical Reasoning▼5.8k2.33
[PDF]Bidirectional Transfer, Asymmetric Expression: Math Fine-Tuning Conceals the Code Gains It Carries▲13k2.33
[PDF]What Does It Mean to Remove an Edge? Intervention-Aware Fidelity for Graph Neural Network Explanations▲3.9k1.75
[PDF]VulnDG: Diagnosing and Calibrating Shift-Induced Semantic Vulnerabilities for Domain Generalization Semantic Segmentation▲3.0k2.33
[PDF]When Semantics Stay the Same but Predictions Change: Auditing Checkpoint Portability under Local Nominal Re-serialization▼1.2k1.67
[PDF]Mitigating Catastrophic Forgetting in LLM Continual Learning through Attractor-Informed Latent Transition Alignment▲3952.67
[PDF]VPBRANDLOOP: AIGC ADVERTISING IMAGE GENERATION WITH CROSS-SCENE VANISHING-POINT CONSTRAINTS▼1.2k1.67
[PDF]Unsure What Exists, Not Missing Physics: Intermediate Denoising Estimates Violate Support Constraints in 3D Scene Diffusion▼3.7k2.25
[PDF]Why and When Deep is Better than Shallow: Implementation-Agnostic State-Transition Model of Deep Learning▲3.7k2.60
[PDF]Shapley-Calibrated Semantic Routing for Black-Box LLM Guardrails: What a Fixed Route Retains▲3.0k2.33
[PDF]Learning to Repair the Learner: Evaluating Recursive Improvement in Neuro-Symbolic World Models▼4.5k2.67
[PDF]Vision-Language Models on Specification-Governed Instrument Approach Charts: Which Failures, and Which Supplied Information Changes Them▲11.00
[PDF]Same Target, Different Paths: Learning from Multiple Reasoning Trajectories for Generative Recommendation▼1.2k1.67
[PDF]SG-MoE: Shared Multi-Granularity MoE with MLLM-Assisted Semantic Router Learning for Cross-Modal Representation Learning and Zero-Shot Retrieval▼1.2k1.67
[PDF]When Do Cross-Modal Gains Warrant a Semantic Role? A Role-Conditioned Audit of Derived Pairing Rules▼4.3k2.00
[PDF]Four-Certificate Minimax Rates over Public Class Pairs for Bounded Partially Linear Models▼1.2k1.67
[PDF]SD-LLaVA: Dual-Stream Vision-Language Reasoning with Structured Semantic Priors for BEV Understanding▲11.00
Withdrawn or desk rejected (260)
[PDF]Balancing Cross-Modal Class Alignment and Local Separation for Zero-Shot Skeleton Action RecognitionWithdrawn1.67
[PDF]Knowing Where to Look Next: Adaptive Regional Indexing and Evidence-Guided Search for Multimodal Lifelong NavigationWithdrawn2.00
[PDF]Multi-Agent-Inspired Reward Channels for Mathematical Reasoning: A Diagnostic Case StudyDesk rejected
[PDF]Who Bears How Much Blame? Semantic Cooperative Games for Behavioral Accountability and Incentive Alignment in Agentic AI SystemsWithdrawn1.00
[PDF]ACCOUNTING FOR THE UNSEEN: FRAGILITY-AWARE RECALIBRATION OF SEMANTIC UNCERTAINTY FOR HALLUCINATION DETECTIONWithdrawn1.33