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1,420 results for “keyword:"video"” in ICLR 2027. 626 withdrawn or desk rejected listed apart.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]FastEraser: Achieving Efficient and Effect-Aware Video Object Removal via Sparsity-Driven Distillation▲5.4k3.00
[PDF]Auditing the Ground Truth: A Field-Aware Audit of Video Anomaly Understanding Benchmarks▼4.5k2.67
[PDF]Learning Spatiotemporal Sensitivity in Video LLMs via Counterfactual Reinforcement Learning▼4.5k2.67
[PDF]Why Do Video Diffusion Models Violate Physics? Unveiling the Flaws in Attention Mechanisms▼5.8k2.33
[PDF]Long-Horizon Streaming Video Generation via Hybrid Attention with Decoupled Distillation▲5.4k3.00
[PDF]Loc2Drive: Beyond Visual History with Explicit 3D World State for Long-Horizon Driving Video Generation▼5.8k2.33
[PDF]Before the Question Arrives: Causal Evidence Budgeting for Streaming Video Understanding▲3942.67
[PDF]EgoSCOPE: Seeking What Is Missing via Query-Sufficient Evidence Routing for Long-Horizon Video Understanding▼4.5k2.67
[PDF]RoLA: Rotary-Positioned Low-Rank Linear Attention for Efficient Diffusion Transformers▼4.3k2.00
[PDF]CompVID: Which Video Regions Deserve More Tokens? Complexity-Aware Token Compression for Video LLMs▲5.4k3.00
[PDF]Reweighting Framewise Attention in Video Transformers for Facial Expression Understanding▲3942.67
[PDF]Beyond Single Videos: Benchmarking and Active Evidence Seeking for E-Commerce Cross-Video Reasoning▼4.5k2.25
[PDF]Preserve, Reveal, Expand: Towards Faithful 4D Video Editing with Region-Aware Conditioning and Benchmarking▲5103.00
[PDF]PVWander: 3D Memory-guided Panoramic Video Wandering with Path-Facing Canonicalization▼5.8k2.33
[PDF]TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor Reinforcement Learning▲5103.00
[PDF]Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding▲5.4k3.00
[PDF]When Motion Misleads: Causal-Role-Aware Motion-Turbulence Disentanglement for Turbulent Infrared Video Super-Resolution▲143.33
[PDF]VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders▲5103.00
[PDF]Document-Grounded Generation of Verified, Interactive and Photoreal Physics Experiments▲3.0k2.33
[PDF]EcoVideo++: Characterizing and Exploiting Tri-dimensional Capability Boundaries for Collaborative Video Diffusion▼1.2k3.00
[PDF]Exact Where It Matters: Downstream-Guided Attention Refinement for Long-Video Understanding▼4.5k2.67
[PDF]DirectorBench: Diagnosing Long-Form Video Generation with Personalized Multi-Agent Evaluation▲6.1k2.00
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