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
628 results for “keyword:"understanding"” in ICLR 2027. 278 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]ExamOCRBench: A Multi-Task Benchmark for Real-World Exam Document Understanding and Automated Grading▼1.2k1.67
[PDF]ViCoStream: Streaming VideoLLMs Can Run Beyond 100 FPS with Stage-Wise Coordinated Inference▼4.3k2.00
[PDF]Teaching Video Agents How to Look via Counterfactual Information Gain Policy Optimization▲3.0k2.33
[PDF]RoboStressBench: A Diagnostic Benchmark for Visual Stress in Embodied Scene Understanding▲5103.00
[PDF]mxSRBench: Towards Spatial Understanding and Diagrammatic Reasoning in mxGraph for Large Language Models▲3.0k2.33
[PDF]DashengTokenizer: Acoustically Augmented Semantic Representations for Audio Understanding and Generation▼4.3k2.00
[PDF]Beyond Frame Selection: Decoupled Adaptive Evidence Selection for Video Understanding with MLLMs▼5.8k2.33
[PDF]HEAR 360: Geometry-Aware Panoramic Depth Estimation from Multiple Posed Acoustic Observations▼5.8k2.33
[PDF]Diagnosing Temporal Instance-State Binding and Its Stage-Dependent Repairability in Vision-Language Models: A Controlled Study▼5.8k2.33
[PDF]VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification▲5103.00
[PDF]ForgeLoc-R1: Set-Level Reinforcement Fine-Tuning of Video MLLMs for Temporal Forgery Localization▼1.2k1.67
[PDF]One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding▼4.3k2.00
[PDF]Beyond Multi-modal Alignment: An Information-Preserving Framework for Vision-Language Models▲9.2k2.67
[PDF]Basketball-QA: Diagnosing Perception and Reasoning in Multi-Player Basketball Video Understanding▲5.4k3.00
[PDF]MUUNE: Towards Fine-Grained Full-Song Music Retrieval with Multimodal Large Language Models▲5103.00
[PDF]Broad Coverage, Focused Resolution: Hypothesis-Discriminative Evidence Acquisition for Long Video Question Answering▼5.8k2.33
[PDF]EgoEasy Annotator: Evidence-Governed Task-Navigation Timelines from In-the-Wild Egocentric Video▼5.8k2.33
Withdrawn or desk rejected (278)
[PDF]Beyond Local Cycles: Long-Horizon Repetitive Action Counting via Multi-Scale Temporal Representation LearningDesk rejected
[PDF]Beyond Layers: Position-Resolved Gradient Conflict and Position-Aware Modulation for Unified Multimodal ModelsWithdrawn2.00
[PDF]TFAG-OVD: Training-Free Attribute-Guided Open-Vocabulary Detection via LLM Semantic CompositionWithdrawn1.67
[PDF]Now You See It, Now You Don’t: Rethinking visual token allocation across Vision Language Model layersWithdrawn1.33
[PDF]LongVU-TTT: Causal Test-Time Training for Visual Resampling in Long Video UnderstandingWithdrawn1.75
[PDF]VideoEvoHarness: Self Evolving Agent Harness from Unlabeled Videos for Video UnderstandingWithdrawn1.75