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
1,801 results for “keyword:"vision language"” in ICLR 2027. 696 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Gains Stay Where the Loss Went: A Channel-by-Condition Map of Physical-Plausibility Training in Vision-Language Models▲3942.67
[PDF]HOI-UP: Adapting Human-Object Interaction Motion to Unseen Object Properties without Property-Labeled Motion Data▲5103.00
[PDF]PGOT: Physically Grounded Optimal Transport for Distilling Vision-Language-Action Models▼5.8k2.33
[PDF]From Clues to Causes: Teacher-Guided Reasoning and Analysis through Cascaded Evidence for Wafer Defect Map Diagnosis▲3942.67
[PDF]Planning Takes More Than Token Prediction: Causal Plan for Benchmarking and Building Physically Grounded Embodied Reasoners▲3.0k2.33
[PDF]UVA: A UNIFIED VISION-LANGUAGE ALIGNMENT FRAMEWORK FOR FINE-GRAINED ZERO-SHOT AND FEW-SHOT CLASSIFICATION▼12k1.67
[PDF]COMPACT: A UNIFIED FRAMEWORK FOR MULTIMODAL SPLIT LEARNING WITH COMPRESSED ACTIVATIONS▲3.0k2.33
[PDF]CausalWAM: Learning Action-Conditioned Visual Dynamics for Efficient World Action Models▼4.3k2.00
[PDF]WHEN SELF-PREFERENCE IS A VERIFICATION FAILURE: CAUSAL EVIDENCE FROM VISION-LANGUAGE JUDGES▼5.8k2.33
[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]Your Filter Picks the Winner: Predictable Selection Bias in Difficulty-Filtered Evaluation of Visual Token Compression▼1361.33
[PDF]Seeing Action-Critical Evidence: Token Pruning with Internal Action Priors for Vision-Language-Action Models▲143.33
[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]Train4Merge: A Controlled Single-Teacher Study of RL vs. SFT Teachers for OPD-Based Model Merging▲5.4k3.00
[PDF]Same Reward, Different Ability: A Single-Variable Intervention Shows Task Formulation Governs What Spatial RLVR Learns▲3942.67
[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▲3942.67
[PDF]ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Models▼4.3k2.00
Withdrawn or desk rejected (696)
[PDF]Retrieval-Augmented Anatomy-Aware Reasoning for Interpretable Alzheimer's DiagnosisWithdrawn1.33
[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
[PDF]Hybrid Memory-Augmented Vision-Language-Action Models for Long-Horizon ManipulationWithdrawn1.75
[PDF]Most of the Gain Is Not Video: Taking Apart a Fine-Tuned Video Question-Answering ScoreWithdrawn1.67