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628 results for “keyword:"understanding"” in ICLR 2027. 278 withdrawn or desk rejected listed apart.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]OphMem: Leveraging Cross-Case Experience to Mitigate Visual Ambiguity in Ophthalmic Surgical Video Understanding▼4.3k2.00
[PDF]EOR: Evidence-Obligation Reasoning for Verification-Driven Long-Video Question Answering▼4.3k2.00
[PDF]Analytic Dynamics: Learning Physics-Grounded Representation for Fast Intrinsic Dynamics Inference from Monocular Videos▲3952.67
[PDF]Mambura: a Mamba-Transformer Hybrid for Unified Multimodal Understanding and Generation▼5.8k2.33
[PDF]VideoSeeker: Empowering Cross-Video Understanding via Multi-Turn Evidence-Seeking Agentic Reasoning▲4.6k3.00
[PDF]The Perception-Override Reflex: When Speech Language Models Follow Perception Over Instructions▲6.1k2.00
[PDF]Repairable Uncertainty: Selective Temporal Reacquisition for Long-Video Understanding with MLLMs▲143.33
[PDF]Why MLLMs Struggle to Count: Overcoming Individuation and Aggregation Bottlenecks with ConvStack▼1.2k3.00
[PDF]IVU-Bench: Benchmarking Multimodal Large Language Models for Video Understanding under Incomplete Observations▼4.3k2.00
[PDF]DriveTok: 3D Driving Scene Tokenization for Unified Multi-View Reconstruction and Understanding▲3.0k2.33
[PDF]Atomic Physical Transitions: A Structured Representation for Physical Dynamics in Video▲5103.00
[PDF]Towards Biological Intelligence:Evaluating and Aligning MLLMs for Taxonomic Perception and Knowledge Reasoning▼4.3k2.00
[PDF]BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender▼4.5k2.67
[PDF]AutoClAM: End-to-End Differentiable Deep Clustering for Unsupervised Action Localization▲6.1k2.00
[PDF]SpatialRoute-Bench: Benchmarking Long-Horizon Spatial Intelligence of Vision-Language Models in Outdoor Videos▲3952.67
Withdrawn or desk rejected (278)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