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
581 results for “keyword:"human"” in ICLR 2027. 197 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Interactive Visual Gym: Evaluating visual assistants with simulated human users in interactive worlds▲143.33
[PDF]Gaze2Act: Gaze-Guided Vision-Language-Action Policies for Interactive Robot Manipulation▲3952.67
[PDF]Reversible Hierarchical Active Correction under Imperfect Human Feedback for MLLM-human Hybrid Annotation▼1.2k1.67
[PDF]Expert-Grounded Synthetic Data for Cognitive Biases: Controlled Generation and Blind Evaluation of Construct Fidelity▼71.25
[PDF]RePO: Reference-Relative Policy Optimization for High-Fidelity Humanoid Motion Imitation▼5.8k2.33
[PDF]SetMimic: Policy-in-the-Loop Interpretation of Motion Intent for Humanoid Imitation from Imperfect Motion References▲25k3.00
[PDF]PT: Prototype-Guided Self-Supervised Pretraining for Generalizable mmWave Human Point Cloud Representations▼4.5k2.67
[PDF]When Decision Theories Empower AI Agents: Learning and Orchestrating Theory–Agent Alignment for Personalized Decision-Making▲5.4k3.00
[PDF]TARSphere: A Robot-Oriented Full-Stack Framework for Long-Horizon Embodied Agents in Evolving Physical and Social Environments▲5.4k3.00
[PDF]IteraFigure: Editable Structured Scientific Diagram Generation with Atomic Local Editing▲9.2k2.67
[PDF]CoSTA4D: Consistent Spatio-Temporal Aggregation for Streaming 4D Human Reconstruction from Uncalibrated Sparse-View Videos▲3952.67
[PDF]LLMDT: LLM-Based Dual-Transformer for Scene-Aware Text-Driven 3D Human Motion Generation▼4.3k2.00
Withdrawn or desk rejected (197)
[PDF]Machine Love: Emergent Bonding Behavior in Large Language Models and Its Implications for AI SafetyDesk rejected
[PDF]AskInfer-Bench: Profiles Are Evidence, Not Intent Labels, in Personalized Deep ResearchWithdrawn1.00
[PDF]Beyond Prediction: Structural Transfer and Partial Identification in Symbolic Domain GeneralizationDesk rejected
[PDF]CasePath: An Agentic, Process-First Architecture for Determining Evidence RequirementsWithdrawn1.00