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
2,684 results for “keyword:"vision"” in ICLR 2027. 1,003 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Counterfactual Tests Reveal Limited Depth-Image Use in RGB-D VLMs: A Probing and Causal-Patching Diagnosis on Metric-Distance Queries▲6.1k2.00
[PDF]ASR-VLA: Adaptive Safety Reasoning with Safety-Critical Future Prediction for Vision-Language-Action Models▼1611.50
[PDF]Beyond Multi-modal Alignment: An Information-Preserving Framework for Vision-Language Models▲9.2k2.67
[PDF]Your Filter Picks the Winner: Predictable Selection Bias in Difficulty-Filtered Evaluation of Visual Token Compression▼1361.33
[PDF]Risk-Controlled Post-Compression Verification for Visual Token Reduction with Exact Dense Fallback▼2.0k1.00
[PDF]DUNK: Dual-Space Non-Semantic Knowledge Consolidation for Continual Image Forgery Localization▼4.5k2.25
[PDF]Seeing Action-Critical Evidence: Token Pruning with Internal Action Priors for Vision-Language-Action Models▲133.33
[PDF]Do fMRI Encoding Models Preserve Cross-Subject Transfer? Diagnosing and Reducing the Brain–Model Transfer Gap▲5103.00
[PDF]A failure of Imagination: VLMs fail to use visual representations for text, but self-distillation can help▼4.3k2.00
[PDF]Trigger Appearance Is Not Enough: Evidence Routing for Diverse Backdoor Activation in Large Vision-Language Models▼4.3k2.00
[PDF]Reliability-Aware Self-Distillation for Test-Time Adaptation of Vision-Language Models▼4.3k2.00
[PDF]CHORUS OR ECHO? AN ASSOCIATION-AWARE RANKING LABEL MODEL FOR UNSUPERVISED RETRIEVAL FUSION▲5.4k3.00
[PDF]Train4Merge: A Controlled Single-Teacher Study of RL vs. SFT Teachers for OPD-Based Model Merging▲5.4k3.00
[PDF]FactorizePatch: Factorizing the Printer-Camera Pipeline for Robust Physical Adversarial Patches▲3.0k2.33
[PDF]Same Reward, Different Ability: A Single-Variable Intervention Shows Task Formulation Governs What Spatial RLVR Learns▲3922.67
[PDF]One Man's Cure Is Another's Poison: Turning JPEG Compression Into Backdoor Triggers for Vision-Language (Action) Models▼1.2k1.67
[PDF]FedRALA: Federated Test-Time OOD Detection via Reliable Negative-Label Aggregation and Local Adaptation▲3922.67
[PDF]ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Models▼4.3k2.00
[PDF]Measuring Transformation-Coverage Savings from Geometric Priors: A Fixed-Data Evaluation of Equivariance, Augmentation, and Capacity▲3.0k2.33
[PDF]Self-Evolving Spatial Reasoning in Vision Language Models via Geometric Logic Consistency▲3.0k2.33
[PDF]InteractiveVLN: Proactive Interaction via Uncertainty-Aware Decision for Zero-Shot Vision Language Navigation▼1.2k1.67
[PDF]EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control▲14k3.00
[PDF]CRAFT: Coupled Rotation-Aware Action-Field Caching and Two-Bit Quantization for Vision-Language-Action Models▲9.2k2.67
Withdrawn or desk rejected (1,003)
[PDF]Retrieval-Augmented Anatomy-Aware Reasoning for Interpretable Alzheimer's DiagnosisWithdrawn1.33
[PDF]Beyond the Local View: Predicting Correction Gains for Sparse On-Policy DistillationWithdrawn1.33
[PDF]From Association to Decision Value: Testing Paired Instruction Dependence for VLA Corpus SelectionWithdrawn1.40
[PDF]Counterfactual Auditing of Object Presence and Quantity Judgments in Vision-Language ModelsWithdrawn1.67
[PDF]TFAG-OVD: Training-Free Attribute-Guided Open-Vocabulary Detection via LLM Semantic CompositionWithdrawn1.67
[PDF]Now You See It, Now You Don’t: Rethinking visual token allocation across Vision Language Model layersWithdrawn1.33