acceptodds: the papers of ICLR 2027
355 results for “area:robotics rating>=3” in ICLR 2027. 11 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]ForeSense: Learning Latent Visual Intuition for Vision-Language-Action Models via Future Experience Distillation▲5.3k3.00
[PDF]TARSphere: A Robot-Oriented Full-Stack Framework for Long-Horizon Embodied Agents in Evolving Physical and Social Environments▲5.3k3.00
[PDF]Beyond the Remembered World: Predictive 4D Belief for Persistent Navigation in Evolving Worlds▲1.7k3.33
[PDF]Learning Repairable Initializations for Multi-Agent Path Finding via Discrete Diffusion▲6.5k3.33
[PDF]AHA-WAM: Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing▲14k3.00
[PDF]DiscoDemo: Discovering Efficient and Diverse Robot Demonstrations for Imitation Learning▲233.33
[PDF]AirGroundVLN: A Large-Scale Benchmark for Goal-Oriented Air-Ground Collaborative Vision-and-Language Navigation▼1.2k3.00
[PDF]Metis: A Generalizable and Efficient 4D World-Action Model for Autonomous Driving and Urban Navigation▲4643.00
[PDF]Exploring What to Preserve for Reasoning and Action in Structured Pruning of Driving VLAs▲233.33
[PDF]CogWAM: Aligning Semantic Cognition with World Action Modeling via Event-Driven Interfaces▲1.7k3.33
[PDF]SceneRig: An Agentic System for Simulation-Ready 3D Scene Reconstruction from Single Images▲5.3k3.00
[PDF]PerturBot: Breaking Shortcut Priors in Vision-Language-Action Models with Perturbative Training▲4643.00
Withdrawn or desk rejected (11)
[PDF]Diagnosing the Structure and Local Behavioral Effects of Viewpoint-Induced Action Distortion in Robot PoliciesWithdrawn3.33
[PDF]Learning from Consequences: Posterior-Transition Reweighting for Behavior CloningDesk rejected3.00
[PDF]BeyondRetarget: Learning Executable Humanoid Motions Directly from Monocular VideoDesk rejected3.33
[PDF]Temporal Ensembling Revisited: Recovering the Stochastic Headroom of Generative Robot PoliciesDesk rejected3.00
[PDF]SmartVLA: A Steerable Action Interface for Fine-Grained, Multimodal, and Corrective InstructionsDesk rejected3.00