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628 results for “keyword:"understanding"” in ICLR 2027. 278 withdrawn or desk rejected listed apart.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]SonarLLM: A Native Sonar–Optical Multimodal Large Language Model for Underwater Perception▼1.2k3.00
[PDF]MatchVLM: Synergizing Vision-Language Models and Local Feature Matching for Cross-View Point Correspondence▲5103.00
[PDF]FINE-GRAINED DEVICE-DIRECTED SPEECH RECOGNITION: FROM OFFLINE MODELING TO STREAMING INFERENCE▼1361.33
[PDF]DiFuse: Fusing Native Diffusion Representations for Spatial Reasoning in Unified Multimodal Models▼4.3k2.00
[PDF]Cognitive Liquid World Models: Continuous-Time Causal Verification over Decoupled Latent Manifolds▼4.3k2.00
[PDF]Separate to Deliberate, Fuse to Decide: Perspective-Factorized Latent Reasoning for Video Anomaly Understanding▼5.8k2.33
[PDF]VideoPursuit: From Retrieval Actions to Local Retrieval Processes for Agentic Long-Video Understanding▲3952.67
[PDF]FactMix: Evaluating and Improving Mixed-Fact Robustness in Large Audio-Language Models▼1.2k1.67
[PDF]Structure-Preserving Visual Token Compression for Streaming Video Understanding via Bilateral Grid Splatting▼4.5k2.67
[PDF]The Allocentric Shift: Multi-Ego Contrastive Perceptual Alignment from Coordinated Behavior▲1.7k3.33
[PDF]PaperMolBench: Benchmarking and Understanding Molecular Structure Recognition in Scientific Figures▼3.7k2.25
[PDF]ITJoint: Benchmarking and Diagnosing MLLMs on Query-Driven Image-Text Joint Extraction from Long Documents▼5.8k2.33
[PDF]Anomaly-Guided Observation and Two-Level Semantic Feedback for Training-Free Video Anomaly Analysis▲6.1k2.00
[PDF]Tracing Arrow-of-Time: Diagnosing and Addressing Temporal Information Loss in Video-LLMs▼5.8k2.33
[PDF]TrajsCogMap-Bench: Evaluating Cognitive Mapping and Spatial Memory from Egocentric Video Trajectories▼1361.33
[PDF]From Partial Observation to Complete Understanding: Unified 3D Semantic and Affordance Reasoning from a Single Image▼4.5k2.67
[PDF]EM-Lens: Towards Observation-Level Electromagnetic Signal Understanding via Agentic Zoom-and-Measure▲3.8k2.50
[PDF]Self-calibrating Agentic Generation and Answering over Multimodal Instructional Collections▲3952.67
[PDF]From Perception to Prediction and Intervention: Benchmarking Proactive Video Assistants in Real-Life Scenarios▼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Withdrawn or desk rejected (278)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