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
166 results for “keyword:"perturbation"” in ICLR 2027. 62 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]VQIL: Visible Quantum Interference Learning for Perturbation Response Ranking on Graphs▲6.1k2.00
[PDF]ResSub: Dual-Level Backdoor Defense via Residual Alignment and Subspace Perturbation in Vertical Federated Learning▲13k2.33
[PDF]Visual Dependence and Utility in Multimodal Knowledge Graph Completion: A Controlled Pilot Study▼1.2k1.67
[PDF]PerturbBridge: Reference-Process Design for Heterogeneity-Aware Single-Cell Perturbation Prediction▼5.9k2.50
[PDF]Beyond Activity Prediction: Evaluating Compositional Regulatory Generalization in Genomic Foundation Models▲5103.00
[PDF]PerturbSB: Learning Single-Cell Perturbation Dynamics with Control-Informed Schrödinger Bridge▼1.2k1.67
[PDF]Layer-Selective Sharpness-Aware Minimization for Efficient and Accurate Federated Learning▼4.3k2.00
[PDF]Testing Attribution Claims in Diffusion-LM Remasking: A Localized Effect Without a Demonstrated Benefit▼5.3k1.33
[PDF]PopFloor: Split-Half Diagnostics for Finite-Sample Wasserstein Bias in Single-Cell Perturbation Benchmarks▲5103.00
[PDF]BASIL: Batch-Aware Single-Cell Perturbation Response Modeling with Conditional Distribution Alignment▼4.3k2.00
[PDF]Improved Guarantees for Heterogeneous Treatment-Effect Estimation via Matrix Completion▼4.5k2.25
[PDF]BRIDGE: A Multimodal Dataset for Biological Representation Learning across Imaging and Gene Expression▲14k3.00
[PDF]PerturbRx: Learning Treatment-Conditioned Latent Transitions from Single-Cell Perturbations for Patient Drug Response▲3.0k2.33
[PDF]Obscrowd: Joint Face-Localized Identity Protection for Multi-Portrait Images under Generative Editing▲3.8k2.50
[PDF]When Safety Fails Collectively: Robust Alignment Against Harmful Fine-Tuning via Joint Weight Perturbations▲5.4k3.00
[PDF]Measuring the stability of autoregressive generation: Paired latent trajectories under benign input perturbation▼1.2k1.67
[PDF]One Drug, MoRe Views: Response-Directed Multi-Modal Conditioning for Unseen-Drug Perturbation▼4.3k2.00
[PDF]XSPA: Crafting Imperceptible X-Shaped Sparse Adversarial Perturbations for Transferable Attacks on VLMs▼4.3k2.00
[PDF]FalsifyVC: Error-Controlled Reliability Testing of Virtual Cell Models across Comparator Authorities▲5103.00
[PDF]How Should We Describe a Gene? Learning Biological Representations for Perturbation Prediction▲3952.67
[PDF]Equal Path Cost, Unequal Output Effects: Understanding Perturbation Propagation in Diffusion Models▲3952.67
Withdrawn or desk rejected (62)
[PDF]ISCon: A Theoretical Framework for Testing Design Rationales of Personalization ModelsWithdrawn1.50
[PDF]CAPure: Rethinking Purification-Resistant Personalization Defenses via Identity-Aware Diffusion PurificationWithdrawn2.00
[PDF]SMIC: Shared Multiscale Input-Reference Conditioning for Natural Language InferenceWithdrawn1.67
[PDF]Category-Oriented Universal Adversarial Perturbations for Deepfake Video DetectorsWithdrawn2.00