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
3,822 results for “area:"applications to computer vision, audio, language, and other modalities"” in ICLR 2027. 1,645 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]DeclareViT: Decoupling Early Classification from Feature Refinement with Exit Query for Efficient ViTs▲5103.00
[PDF]You Only Forward Once: Rethinking Video Temporal Grounding in MLLMs as Single-Pass Parallel Boundary Probability Prediction▼12k1.67
[PDF]Thinking Beyond Videos: Unifying Video Reasoning and Deep Research for Open-World Video Agents▼5.1k2.60
[PDF]Joint Fidelity and Perceptual Modulation via Adaptive Corrections for Implicit-Motion Neural Video Compression▲3.9k1.67
[PDF]ContourVLA: A Closed-Loop Perception-Action Contour Policy for Generalized Referring Expression Segmentation▼4.5k2.67
[PDF]MoE4D: Mixture of Spatio-Temporal Experts with Frequency-Modulated Router for LiDAR Novel View Synthesis▲1.9k3.67
[PDF]Think with Motion: A Unified Understanding and Generation Framework for Individual and Interactive Human Motion▲3.0k2.33
[PDF]Scope2Rubric: Recovering Query-Specific Evaluation Scope before Rubric Generation for Long-Form Deep Research▼1391.40
[PDF]PROBE: Protected Observation-Subspace Energy for Fine-Grained Open-Set Recognition on Frozen Classifiers▼4.3k2.00
[PDF]SwiftAD: Visibility-Guided Hierarchical Token Pruning for Efficient Zero-Shot 3D Anomaly Detection▼5.8k2.33
[PDF]Deformable Vision Query Connector: Letting LLMs Query Vision Information through Position-Grounded Lookup▼4.3k2.00
[PDF]Cross-modal Heterogeneous Privileged Policy Optimization for Medical Image Understanding▼5.9k2.50
[PDF]GeoHaze: Geometry-Conditioned Spectral Propagation for Structure-Preserving Image Dehazing▲3952.67
[PDF]VidForensics-M1: AI-Generated Video Detection and Forensics via Verifiable Meta-Detection Reinforcement Learning▼5.9k2.50
[PDF]Selecting What Matters: Semantic Compression-Guided Selective Pooling for Long-Context Embeddings
[PDF]ScoutCrew: Coordinating Multi-View Exploration and Evidence Synthesis for Spatial Reasoning▲9.2k2.67
[PDF]What Retrieval Buys Depends on Who Reads: Splitting Multi-Hop RAG Accuracy into Assembly and Reading▼1.2k1.67
[PDF]HalluMirror: Discovering and Mitigating Multimodal Hallucinations via Co-Evolutionary Self-Play▲5103.00
[PDF]Beyond Modality Level Competition: Frequency-Resolved Spectral Regulation for Multimodal Learning▼4.3k2.00
[PDF]Beyond Generator-Specific Shortcuts: Open-World AI-Generated Video Detection via Adversarial Training▲8.9k2.75
[PDF]Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Grounding▲5.4k3.00
[PDF]Compress at Input, Recover at Depth: Improving the Efficiency–Performance Trade-off for MLLMs▼5.8k2.33
Withdrawn or desk rejected (1,645)
[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