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
2,994 results for “keyword:"generation"” in ICLR 2027. 878 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]PlanTalk: MLLM-Based Motion Planning with Hierarchical Audio Guidance for Talking Head Generation▼4.3k2.00
[PDF]Mambura: a Mamba-Transformer Hybrid for Unified Multimodal Understanding and Generation▼5.8k2.33
[PDF]RS-Gen: A Multi-Stage Agentic Framework for Reasoning and Search-Augmented Image Generation▼4.3k2.00
[PDF]Early Warning of Personalization Model Degradation from User Histories and Hidden States▼5.8k2.33
[PDF]Cache Homeostasis: Diagnosing and Controlling Feature Drift in Autoregressive Video Diffusion▼4.3k2.00
[PDF]Representations from Pretrained Machine-Learning Interatomic Potentials as Coarse Coordinates for Material Generation and Evaluation▼3.7k2.25
[PDF]SPOON: Towards Coherent Compositional 3D Scene Generation from Uncalibrated Multi-view Images▲5.4k3.00
[PDF]Learning to Forget Together: Prompt-Conditioned Adapter Generation for Multi-Domain LLM Unlearning▼1.2k1.67
[PDF]UMI3D: Robust 3D Generation on Unconstrained Multi-Image Inputs via Simultaneous Focusing Cross-Attention Routing▲3.0k2.33
[PDF]Sweeping Promptable Spoofs under the DirtyRAG: A Practical, Query-Blind RAG Attack Done Right▼4.3k2.00
[PDF]AW3D: Action Prototype Learning with World Modelling for Text-Driven 3D Human-Object Interaction Generation▼1.2k3.00
[PDF]TOSCA: Transport Operators with Set-valued Certified Assembly for Scene-Graph-to-3D Generation▼5.8k2.33
[PDF]FieldForge: A Pretraining and Post-Training Framework for Flow-Based Crystal Generation▼4.3k2.00
[PDF]Carrying a Length and Counting It Are Different Abilities: A Double Dissociation between Recurrence and Attention in Code-Fence Generation▲6.6k3.33
[PDF]CausalMotion: Structured Physical Reasoning as Keyframe and Trajectory Guidance for Training-Free Video Generation▲3.0k2.50
[PDF]Scenarist: Reshaping the Driving Data Distribution through Open-Ended Failure Scenarios, from Language to Policy▲3.0k2.33
[PDF]ReelBench: Towards Systematic Evaluation of Multi-Shot Narrative Video Generation under Image Reference▲412.75
Withdrawn or desk rejected (878)
[PDF]PragyaMD: Parameter-Efficient Adaptation of Humanoid Motion Generators to Indic LanguagesDesk rejected
[PDF]Beyond Layers: Position-Resolved Gradient Conflict and Position-Aware Modulation for Unified Multimodal ModelsWithdrawn2.00
[PDF]Beyond Hypothesis Recovery: Evaluating Scientific Hypothesis Generation through Evidence-Hypothesis TransitionsWithdrawn1.33