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
620 results for “keyword:"action model"” in ICLR 2027. 201 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Readable Factors, Unresolved Combinations: Support-Aware Correction for Warm-Start Recommendation▼4.3k2.00
[PDF]Paired Residual Adaptation for Vision-Language-Action Policies under Transient Visual Mislocalization▼5.8k2.33
[PDF]Grounding Attention in Motion: Proprioception-Guided Visual Token Pruning with Adaptive Layer Selection for Vision-Language-Action Models▲3.0k2.33
[PDF]Brain alignment of reasoning and action representations from vision–language and action models during naturalistic gameplay▲3952.67
[PDF]VLA-Duo: Periodic Cross-Inference Scheduling for Mobile Vision-Language-Action Inference▼5.9k2.50
[PDF]GeoLACE: Geometric Layerwise Action-Conditioned Enhancement for Vision-Language-Action Models▼4.5k2.67
[PDF]ViDAL: A Visual Dynamics-Grounded Action Latent Space for Vision-Language-Action Models▼4.5k2.67
[PDF]ChainVLA: Chaining Vision-Language-Action Queries through a Unified Execution State for Long-Horizon Manipulation▲3952.67
[PDF]What Success Rate Hides: Mapping Disturbance Tolerance in Vision-Language-Action Policies▼4.3k2.00
[PDF]RAAG: Training-Free Retrieval-Augmented Action Generation Guided by Gripper–Object Geometry from Successful Experience▲5.4k3.00
[PDF]ManipScope: A Diagnostic Benchmark for Instruction Following and Generalization in Robotic Manipulation▲3952.67
[PDF]CAFE-VLA: Controllable Avoidance with Field Encoding for Compact Vision-Language-Action Models▼4.3k2.00
[PDF]PRESERVE WHAT MATTERS: COUNTERFACTUAL TASK-VECTOR DECOMPOSITION FOR REPLAY-FREE CONTINUAL VISION-LANGUAGE-ACTION LEARNING▲3952.67
[PDF]Grounding Is Inherited, Action Is Concentrated: What VLA Finetuning Adds to a Web-Pretrained VLM▼71.25
[PDF]Knowing Where to Go: Generalizing Mobile Manipulation to Unseen Environments from a Single Video▲5103.00
[PDF]EMAG: Event Memory Retrieval and Spatial Affordance Grounding for Non-Markovian Robot Manipulation▼4.3k2.00
[PDF]World–Action Coupling and Collection-Matched Optimization for Online Multi-Task Reinforcement Learning▲9.2k2.67
[PDF]TrajPoison: Trajectory-Aware Clean-Label Poisoning of Vision-Language-Action Models via Robotic Demonstrations▼4.3k2.00
Withdrawn or desk rejected (201)
[PDF]From Association to Decision Value: Testing Paired Instruction Dependence for VLA Corpus SelectionWithdrawn1.40
[PDF]Hybrid Memory-Augmented Vision-Language-Action Models for Long-Horizon ManipulationWithdrawn1.75
[PDF]When Does an Observable Lose Failure Evidence? Exact Ranking Losses for Runtime Detection in Vision–Language–Action PoliciesWithdrawn1.00
[PDF]Separate Adaptation, Unidirectional Coordination: Learning Bimanual Manipulation with a Shared VLA BackboneDesk rejected
[PDF]Revision, Not Restart: Revisable Visual Plans for Closed-Loop World-Action ModelsDesk rejected2.00
[PDF]Rethinking Vision-Language-Action Model Scaling: Alignment, Mixture, and RegularizationDesk rejected2.33