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427 results for “keyword:"interaction"” in ICLR 2027. 136 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Do LLMs Follow a Behavioral SCRIPT? Measuring Structural Choreography and Rigidity from Positions and Transitions▲3952.67
[PDF]TopoBox: towards Physically Feasible 3D Object Re-Arrangement via Topology-Aware Box Reasoning▼5.8k2.33
[PDF]SVI-Bench: Evaluating Human-Perceived Interaction Trajectories in Streaming Video Systems▼4.5k2.67
[PDF]BiReS: Bidirectional Semantic Recalibration for Text-Guided Multi-Scale Medical Image Segmentation▼4.3k2.00
[PDF]DuplexAct: Benchmarking Natural and Controllable Interaction Behaviors in Real-Time Full-Duplex Speech Systems▼4.3k2.00
[PDF]STANCE: Scene-Consistent Real-Time Motion Estimation from Sparse Wearables via Posterior-Corrected Residual Diffusion▲3.0k2.33
[PDF]TraceForcing: Learning from Persistent Interaction Traces for Fine-Grained Hand-Object Interaction Video Understanding▲5103.00
[PDF]Task-Conditioned Dual-Graph Residual with Marginal Constrained Refinement for circRNA-miRNA Interaction▼5.8k2.33
[PDF]ATLASACT: RETRIEVAL-CONSTRAINED GROUNDING AND STRUCTURE-VALIDATED MEMORY FOR MOBILE GUI AGENTS▲6.1k2.00
[PDF]Know Me To Recommend Me: Personalized Recommendation from Long-Term Human-MLLM Assistant Interactions▲3952.67
[PDF]Human Modeling Meets AI Metacognition: Toward Coupled Cognitive Alignment for Interactive Agents▼1.2k1.67
[PDF]CoHabit Arena: Evaluating Personal Preference Realization in Long-Horizon Human-Agent CoHabitation▼1.2k1.67
[PDF]Phys-WorldBench: A Unified Benchmark for Evaluating Embodied World Models from Passive Prediction to Active Intervention▲5103.00
[PDF]PIPER: Multi-Conformer Reasoning with Physics-Informed Regularization for RNA–Ligand Interaction Prediction▲5103.00
[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]MuscleSight: A Benchmark for Ultrasound Representations of Muscle State in Manual Tasks▼4.5k2.67
[PDF]High-Order Interaction and Modality-Specific Distillation for Unsupervised Cross-Modal Hashing▲1.7k3.33
[PDF]Reconstruct Then Rectify: Information-Conserving Node Interaction Estimation for Graph Unlearning▲9.2k2.67
[PDF]ATMA: Long-Context Language Modeling via Polar Attention and Gated-Delta Compression Memory▼1361.33
[PDF]MindWorld: Iterative Co-Optimization of Mental World Models and Policies for Social Intelligence▲5103.00
[PDF]TARSphere: A Robot-Oriented Full-Stack Framework for Long-Horizon Embodied Agents in Evolving Physical and Social Environments▲5.4k3.00
Withdrawn or desk rejected (136)
[PDF]FairWatch: Interaction Topology as a First-Order Variable Shaping Safety and Fairness in Multi-Agent DeliberationDesk rejected2.00
[PDF]Defect Responses in Visual World Models: Long-Horizon Propagation, Gradient Interaction, and Planning OutcomesWithdrawn1.33
[PDF]-Bench: Benchmarking Proactive Speech Interaction with Full-Duplex Conversational AIDesk rejected
[PDF]Probing Interaction Awareness in Trajectory Prediction with Counterfactual PerturbationsDesk rejected
[PDF]AskInfer-Bench: Profiles Are Evidence, Not Intent Labels, in Personalized Deep ResearchWithdrawn1.00
[PDF]When Does the Move Algebra Guide Search? A Two-Certificate Calculus for Operator Non-Commutativity in Local SearchWithdrawn1.67