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591 results for “keyword:"action models"” in ICLR 2027. 192 withdrawn or desk rejected listed apart.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]Do World-Action Models Need Dense World Context? Progressive Sparse Forcing for Action DiTs▲3952.67
[PDF]SACQ: Structure-Aware Codebook Quantization for Ultra-Low-Bit Vision-Language-Action Models▼4.5k2.67
[PDF]Is Test-Time Video Generation Unnecessary? Adaptive Video Reasoning for World Action Models▼1.2k3.00
[PDF]How Deep Should a VLA Think When Thinking Costs Time? Budget-Constrained RL for Early Exit▼1361.33
[PDF]Premover: Fast Vision-Language-Action Control via Early Execution During Instruction Delivery▼4.3k2.00
[PDF]Beyond the Current Observation: History-Informed Adaptation for Vision-Language-Action Models▼1361.33
[PDF]Driving-OPD: Learning Complementary Driving Experts with Reward Variance-Aware RL and On-Policy Distillation▲143.33
[PDF]One from Infinity: Actualizing Futures from Pretrained World Models into Robot Actions▼5.8k2.33
[PDF]RaPhy-AD: Radar-Aware Foundation Model with Explicit Physical Chain-of-Thought for Autonomous Driving▲3952.67
[PDF]DFA-VLA: Dynamic Fine-Grained Alignment for Vision-Language-Action Models in Robotic Manipulation▲11.00
[PDF]Stage-Verifiable Latent Chain-of-Thought with Local Repair for Long-Horizon Robotic Manipulation▼1.2k1.67
[PDF]Rethinking High-Fidelity View Synthesis: Simple Homography Augmentation for Viewpoint-Robust VLAs▼5.8k2.33
[PDF]StairVLA: Stage-Aware Hierarchical Action Generation for Vision-Language-Action Models▼5.8k2.33
[PDF]Learning from Runtime Feedback with Failure-Bank Self-Evolution for Vision-Language-Action Models▼5.8k2.33
[PDF]Hydra: A Navigation World Action Model with Discrete Latent Planning and Continuous Flow-Matching Execution▼5.8k2.33
[PDF]CAPO: Real-World Reinforcement Learning for VLA via Corrective Adjoint Policy Optimization▲5.4k3.00
[PDF]The Repair Must Reach the Backbone: A Controlled Comparison of Instruction-Following Fixes for Vision-Language-Action Policies▼4.3k2.00
[PDF]Faster and Better? Benchmark Bugs and Design Limitations Distort the Evaluation of Vision-Language-Action Acceleration▼5.8k2.33
Withdrawn or desk rejected (192)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