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
591 results for “keyword:"action models"” in ICLR 2027. 192 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]VLMs are Native Action Models: Unleashing the manipulation capabilities of VLMs with Explicit Action-Space Grounding▲3952.67
[PDF]TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on a Consumer-Grade GPU with <1 GB VRAM▲2843.00
[PDF]WAVE-VLA: A Whole-Body Humanoid VLA with Executable Vision–Motion Codes Learned from Heterogeneous Human and Robot Data▼1.2k1.67
[PDF]PrimitiveVLA: Learning Reusable Motion Primitives for Efficient and Generalizable Robotic Manipulation▼4.5k2.67
[PDF]AnyStep-WAM: Budget-Aligned Distillation and Adaptive Inference for World Action Models▲3.8k2.50
[PDF]GTPO: Group Teaching Policy Optimization via Temporal Optimal Transport in VLA Reinforcement Learning▼1.2k3.00
[PDF]LPA-CACHE: Latency-Plateau Aware KV Cache Reuse for Efficient Vision-Language-Action Model Inference on GPUs▼1.2k1.67
[PDF]Not Every Action Needs Every Token: Dynamic Visual Token Allocation for Vision-Language-Action Models▲8.9k2.75
[PDF]PF-RL: Progress Field Reinforcement Learning via Goal-Conditioned Value Geometry for Vision-Language-Action Models▲5103.00
[PDF]PolicyGround: Recovering from High-Level Failures by Probing Frozen Hierarchical Vision-Language-Action Models▼1361.33
[PDF]Scenarist: Reshaping the Driving Data Distribution through Open-Ended Failure Scenarios, from Language to Policy▲3.0k2.33
[PDF]Edit Only Where It Fails: Boundary-Guided Editing via Latent Transformations for Vision-Language-Action Models▼5.8k2.33
[PDF]Task Conditions Tell More Than the Task: Dataset-Property Leakage and Private Release in World Action Models▲143.33
[PDF]ReWAM: A Unified Framework for Representation-Centric Analysis of World-Action Modeling▲5.4k3.00
[PDF]TrajScale-VLA:Trajectory Aligned Scale Autoregressive Action Generation for Vision-Language-Action Models▲5.4k3.00
[PDF]Rolebind: training vision-language-action policies with task-conditioned role–instance supervision▼1361.33
[PDF]Triage Before Fine-Tuning: Feasibility-Gated Selection and Monitored Adaptation of Embodied Foundation Models for a Fixed Physical Platform▲3952.67
[PDF]Towards a General Humanoid Loco-Manipulation Model via Egocentric Whole-Body Human Data Pretraining▼1.2k3.00
[PDF]BioLab: Benchmarking Robotic Manipulation in Biology Laboratory from Individual Skills to Experiment SOPs▼4.5k2.67
Withdrawn or desk rejected (192)
[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
[PDF]Beyond In-Distribution Preservation: Recovering Generalization in Quantized VLAs via Vulnerability-Oriented TuningWithdrawn2.00