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2,994 results for “keyword:"generation"” in ICLR 2027. 878 withdrawn or desk rejected listed apart.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]ProSearch: Teaching LLMs When (Not) to Search over Streaming Inputs via Reinforcement Learning▼5.8k2.33
[PDF]MemActive: Training-Free Memory Activation for Consistent Interactive Streaming Video Generation▼4.5k2.67
[PDF]Aligning the Clocks: Alignment-Aware Causal Distillation for Streaming Audio-Driven Avatars▲11.00
[PDF]TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation▼4.3k2.00
[PDF]Modality-decoupled Distribution Matching Distillation for Few-step Audio-visual Generation▼1.2k1.67
[PDF]GrowFlow: Unified 3D Structure and Feature Generation via Expanding Structural Flow Matching▼4.5k2.67
[PDF]CogExtract: Test-Time Search with Execution-Grounded Verification for Web Information Extraction on Dynamic Pages▼1361.33
[PDF]ZeroMAG: Zero-Shot Multimodal Adapter Generation for Plug-and-Play EEG Foundation Models▼1.2k1.67
[PDF]Structural Extrapolative Data Generation: Hardness, Feasibility, and Formal Conditions▲9.2k2.67
[PDF]Mirrorrefine: Mirror Reflection Generation via Multi-agent Refinement with Spatial Priors▼5.8k2.33
[PDF]CROWN: Conversion to Routed Experts with Output-Aware Width Narrowing for Audio-Video Diffusion▼4.3k2.00
[PDF]DitronGen: Compiler–LLM Coordination for Adaptive Kernel Generation and Computation–Communication Overlap▼4.3k2.00
[PDF]Retrieved but not ranked: surface-form bias in structural retrieval, from mathematics to agent trajectories▲11.00
[PDF]EntroKine3D: Shared Kinetic-Profile Supervision for Single-Reference 3D Dance Camera Synthesis▼1.2k3.00
[PDF]BudgetCMT: Joint Allocation of Teacher Compute and Student Supervision Budgets in Consistency Mid-Training▼4.3k2.00
[PDF]OmniShowcase: Omnidirectional Subject-Consistent Video Generation From Multi-View Images▲3912.67
[PDF]Simple Links, Strong Retrieval: Local Entity Expansion for Multi-Hop Evidence Retrieval▼1.2k1.67
[PDF]PulseQuant: Propagation-Guided Subspace Correction for 4-Bit Video Diffusion Transformers▲5103.00
Withdrawn or desk rejected (878)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