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
533 results for “keyword:"video gen"” in ICLR 2027. 206 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]ReelOnce: Adaptive Reference Policy and Evaluation-Driven Hierarchical Refinement for Agentic Multi-Shot Story Video Generation▲3.0k2.33
[PDF]Structura: Intrinsic Scoring and Inference-Time Refinement against Structural Hallucinations in Video Generation▼5.8k2.33
[PDF]LongWM-Bench: Benchmarking Persistent and Navigable Worlds over Long-Horizon Interaction▼4.5k2.67
[PDF]Adaptive Reward Routing: Dynamic Multi-Reward Optimization for Joint Audio-Video Diffusion via Forward-Process RL▲4.6k3.00
[PDF]Hear the World in Stereo: Learning Dynamic Spatial Correspondence for Immersive Joint Video-Audio Generation▲5103.00
[PDF]CineMem: Attention-Aligned Fine-grained Memory Retrieval for Multi-Shot Long Video Generation▲9.2k2.67
[PDF]On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators▲6.6k3.33
[PDF]FastInteract: Few-Step Human-Object Interaction Video Generation via Attention Perturbation▼4.5k2.67
[PDF]Geometry as Address: Routing Attention to Visual Memory for Long-Horizon Camera-Controlled Video Generation▲6.6k3.33
[PDF]RECAP: Reciprocal Sparse Attention and Hierarchical Caching for Efficient Video Diffusion▲2843.00
[PDF]OmniVBench: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generation▼4.5k2.67
[PDF]Xperience-0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience▲5103.00
Withdrawn or desk rejected (206)
[PDF]Trace Forcing: Anchor Tokens in the KV Cache for Training-Free Long Video GenerationWithdrawn2.00
[PDF]ECGEchoDiag: A Benchmark for ECG-Conditioned Multi-View Echocardiography Generation and Cardiac Disease RecognitionWithdrawn1.33
[PDF]Injected but Not Accumulated: Measuring and Stabilizing Synchronization in Training-Free Streaming Audio-Video GenerationWithdrawn2.00
[PDF]VeloCache: Frequency-Decoupled Velocity Caching for Training-Free Video Diffusion AccelerationWithdrawn2.00