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533 results for “keyword:"video gen"” in ICLR 2027. 206 withdrawn or desk rejected listed apart.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]World Models Need a Physical Registry: Learning Internal Predictive States for Physically Plausible World Models▲5103.00
[PDF]Beyond Successful Robot Demonstrations: Learning from Human Interactions and Modeling Failure Dynamics▲5.4k3.00
[PDF]ForgeWM: Progressive Causal Training for Few-Step Action-Conditioned Video World Models▲3.0k2.33
[PDF]FrameFold: Response-Guided KV Cache Consolidation for Autoregressive Long Video Generation▲3952.67
[PDF]Omni-Customizer: End-to-End Multimodal Video Generation with Joint Identity and Audio Customization▼4.3k2.00
[PDF]TempoTrack: Temporally Grounded Multi-Track Control for Streaming Joint Audio-Video Generation▲432.75
[PDF]MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers▼4.3k2.00
[PDF]DualWAM: Dual-System World Action Models for Asynchronous Global Planning and Local Refinement▼4.5k2.67
Withdrawn or desk rejected (206)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