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
92 results for “keyword:"clip"” in ICLR 2027. 29 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Batch size is not sample size: near-tie amplification in contrastive membership inference▼1.2k1.67
[PDF]VADAPT: Visual Anchored and Dual-Prompt Tuning for Generalizable Face Attack Detection▼4.3k2.00
[PDF]AGI-TPT: Adaptive Geometry-Informed Test-Time Prompt Tuning for Calibrated Zero-Shot Vision-Language Models▲5103.00
[PDF]When Clipping Becomes a Learning Signal: A Permutation Baseline for Policy Optimization▲3.0k2.33
[PDF]Just Reuse the Rollout Log-Probs: Stable Mixture-of-Experts Reinforcement Learning with a Vocabulary-KL Clip▼5.8k2.33
[PDF]Effects of Pretraining Concept Frequency and Semantic Similarity among Classes on CLIP Generalized Zero-Shot Accuracy▲143.33
[PDF]Clipped or Unclipped? Finite-Sample Trade-offs for Averaged SGD under Heavy-Tailed Noise▼1.2k3.00
[PDF]Same Privacy Guarantee, Different Robustness: How Gradient Clipping Shapes Adversarial Training▲3.0k2.33
[PDF]What makes a good anchor? Offline Anchor Selection for Test-Time Adversarial Robustness of CLIP▼5.8k2.33
[PDF]Domain Generalization in-the-Wild: Disentangling Classification from Domain-Aware Representations▼4.3k2.00
[PDF]XSPA: Crafting Imperceptible X-Shaped Sparse Adversarial Perturbations for Transferable Attacks on VLMs▼4.3k2.00
[PDF]SIA-CT:State-Structured Item Alignment for Open-Vocabulary 3D Chest CT Representation Learning▼5.8k2.33
[PDF]What Do Text Prompts Actually Carry in Zero-Shot Anomaly Detection? Geometry, Not Semantics▼5.8k2.33
[PDF]Mitigating Model Collapse in Latent Diffusion Models using a Lewis Signaling Regulariser▼1361.33
[PDF]WindowFold: Folding Sliding-Window Inference into a Single Forward Pass for Dense CLIP▼4.3k2.00
[PDF]HOW ERASED IS ERASED? QUANTIFYING AND IMPROVING THE RECOVERABILITY OF CONCEPT REMOVAL IN CLIP▼71.25
[PDF]Reliability-Aware Self-Distillation for Test-Time Adaptation of Vision-Language Models▼4.3k2.00
[PDF]Deeper Is Not Better for Quantized CLIP: Early Readout Recovers Accuracy While Cutting Compute▼5.8k2.33
[PDF]IMC-CLINIC: Coupled Loss-Informed Newton Iterations for Clipping in Analog In-Memory Computing▲3952.67
[PDF]Escaping Silent Failure: Auditable Adaptive Clipping under Client-Level Local Differential Privacy▼1.2k1.67
Withdrawn or desk rejected (29)
[PDF]Are We Measuring the Right Angles? Spherical Test-Time Adaptation of Vision-Language ModelsWithdrawn1.67
[PDF]From Global to Local: Rethinking CLIP Feature Aggregation for Person Re-IdentificationWithdrawn1.67
[PDF]Aligned Is Not Supported: Attributing Image–Text Alignment to Caption Phrases for Data SelectionWithdrawn1.67
[PDF]Where Compositionality Hides: Shared-Content Interference in Contrastive Vision-Language RetrievalWithdrawn1.00