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620 results for “keyword:"action model"” in ICLR 2027. 201 withdrawn or desk rejected listed apart.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]AsyncMoT: Interaction-Guided Asynchronous Mixture of Transformers for Generalized and Robust Robotic Manipulation▲5093.00
[PDF]EquiKey: Object-Centric SE(3)-Equivariant Keypose Guidance for One-Shot VLA Adaptation▲5.4k3.00
[PDF]SpanVLA: Learning from Negative-Recovery Samples with Fast Action Bridging for Vision-Language-Action Model▲5093.00
[PDF]Inline Memory Meets Reusable Skills: Memory-centric Framework for Vision-Language-Action Model▼4.3k2.00
[PDF]OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction▲563.60
[PDF]SafeManip: A Property-Driven Benchmark for Temporal Safety Evaluation in Robotic Manipulation▲9.2k2.67
[PDF]Training with Borrowed Eyes: Decentralized Multi-Robot Manipulation via Privileged Information Distillation▲3862.67
[PDF]Dynamic Episode Alignment: Sample-Efficient Reinforcement Learning of Vision-Language-Action Models▲5.4k3.00
[PDF]GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives▲5093.00
[PDF]From Sparse to Dense: Diagnosing Task-Equivalent Language Robustness in Vision-Language-Action Models▲3.0k2.33
[PDF]DualWAM: Dual-System World Action Models for Asynchronous Global Planning and Local Refinement▼4.5k2.67
[PDF]SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation▼1.2k1.67
[PDF]PICA-WAM: Perturbation Invariance via Cross-Appearance Self-Alignment in World Action Models▼4.5k2.67
Withdrawn or desk rejected (201)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