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
427 results for “keyword:"embodied"” in ICLR 2027. 199 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Replan for Error Recovery: Training Embodied VLMs through Verifiable Interaction with Action-Grouped Turn-GSPO▼4.3k2.00
[PDF]When Worlds Outlive Scars: How Persistent Environments Carry History Across Agent Resets▼1.2k1.67
[PDF]CausalScene: Explicit Intervention-Response Structure for Counterfactual Reasoning in Embodied Agents▼1361.33
[PDF]AirGroundVLN: A Large-Scale Benchmark for Goal-Oriented Air-Ground Collaborative Vision-and-Language Navigation▼1.2k3.00
[PDF]PLAN-Bench: Can Existing VLMs Go Well Beyond Perception to Reason and Plan in Embodied Worlds?▼1.2k1.67
[PDF]OpenViTac: Learning and Benchmarking Visuo-Tactile Policies in a Unified Sim-and-Real Framework▲5103.00
[PDF]Learning New Tasks via Reusable Skills: Skill-Compositional Experts for Embodied Continual Learning▼4.5k2.67
[PDF]When Does Negotiation Help? Benchmarking Embodied Multi-Agent Collaboration under Successive Task Revisions▼5.9k2.50
[PDF]The Goal Is Not Enough: Vision-and-Language Navigation under Negative Spatial Constraints▲5.4k3.00
[PDF]FireNav: Decision-Oriented Reconstruction Evidence Routing for Vision-Language Navigation in Indoor Fire Environments▼4.3k2.00
[PDF]Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control▼5.8k2.33
[PDF]Safe in Text, Unsafe in Action: Distinguishing Content and Physical Danger in LLM Hidden States▼4.5k2.67
[PDF]Xperience-0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience▲5103.00
[PDF]Ground3R: Streaming 3D Referring Expression Segmentation with Recurrent Multimodal Memory▼4.5k2.67
[PDF]PRICE the Action Chunks: Physical Relational Credit Assignment for Embodied Reinforcement Learning▼5.8k2.33
[PDF]What to Attend, Where to Act: Referent–Affordance Co-Evolution for Embodied Spatial Grounding▼4.3k2.00
Withdrawn or desk rejected (199)
[PDF]PragyaMD: Parameter-Efficient Adaptation of Humanoid Motion Generators to Indic LanguagesDesk rejected
[PDF]Hybrid Memory-Augmented Vision-Language-Action Models for Long-Horizon ManipulationWithdrawn1.75
[PDF]WorldMirror: Agentic Real-to-Sim Generation of Interactive Worlds from In-the-Wild Robot DemonstrationsWithdrawn1.67
[PDF]SimForge: Agentic Generation of Simulation-Ready Worlds and Demonstrations for Robot LearningWithdrawn2.00
[PDF]AcoustiGym: Physics-Based Acoustic Environment Generation for Robotic Policy EvaluationDesk rejected