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
1,420 results for “keyword:"video"” in ICLR 2027. 626 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Past- and Future-Informed KV Cache Policy with Salience Estimation in Autoregressive Video Diffusion▲3942.67
[PDF]AskStream: When and What to Ask Proactively under Uncertainty in Streaming Video Understanding▲5.4k3.00
[PDF]RISE: Recurrent Evidence Consolidation with Kernelized Selection for Efficient Long-Video Understanding▼4.5k2.25
[PDF]CinePersona: Camera-Aware Dynamic Persona Encoding for Identity-Preserving Human Video Generation▲3942.67
[PDF]Efficient Video Super-Resolution via Hybrid Attention and Reward-Yield Distribution Matching▲5103.00
[PDF]CoverVTG: Coverage-Constrained Sparse Observation for Universal Video Temporal Grounding▲5103.00
[PDF]End-to-end Full Video-level Supervision for Facial Depression Assessment Model Training▲3942.67
[PDF]Toward Physically Consistent Driving Video World Models under Challenging Trajectories▼4.5k2.67
[PDF]EndoTME: Physics-Inspired Degradation-Aware Trajectory Memory for Endoscopic Video Enhancement▲5103.00
[PDF]Learning Memory Update Policies for Streaming Video Understanding through Reinforcement Learning▲3.0k2.33
[PDF]WorldPortal: Recast Residual Correction for Instruction-Guided Video Background Replacement and Relighting▲5103.00
[PDF]Stop Early, Spend Less: Equal-Accuracy Frame-Budget Saving via Agreement-Gated Adaptive Sampling in Video Language Models▲11.00
[PDF]CORAL-KV: Compact Cross-Layer Prediction and Residual Coding for Autoregressive Video KV Caches▲5103.00
Withdrawn or desk rejected (626)
[PDF]Matched Counterfactual Attribution: A Controlled Evaluation of Data Selection for Video Instruction TuningDesk rejected2.00
[PDF]Beyond Local Cycles: Long-Horizon Repetitive Action Counting via Multi-Scale Temporal Representation LearningDesk rejected
[PDF]Most of the Gain Is Not Video: Taking Apart a Fine-Tuned Video Question-Answering ScoreWithdrawn1.67
[PDF]Decoupling Temporal Action Ownership and Actor Geometry for Spatio-Temporal Action LocalizationWithdrawn1.33
[PDF]LongVU-TTT: Causal Test-Time Training for Visual Resampling in Long Video UnderstandingWithdrawn1.75