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
1,357 results for “keyword:"image"” in ICLR 2027. 591 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]How Do MLLMs Detect AI-Generated Facial Images? A Study of Cross-Source Detection, Provenance, and Explanations▼4.5k2.67
[PDF]Structural Illumination under Control–Realization Mismatch for Compositional Text-to-Image Generation▼1361.33
[PDF]Diffusion Prior-driven Pseudo Target Extraction for Training-Free Zero-Shot Composed Image Retrieval▼4.3k2.00
[PDF]NeuroIntentFormer: Evidence-Conditioned Temporal Aggregation for Motor Imagery Decoding in Stroke Rehabilitation▼13k2.00
[PDF]SwiftRegen: Efficient Image Watermark Evasion Beyond Output Imitation and Evidence Removal▼1.2k1.67
[PDF]LETHE: Defending against Unauthorized Image-to-Video Generation via Value Diversity Collapse▲143.33
[PDF]Seeing Is Not Judging: Evidence-Grounded Evaluation of Multimodal Models for Professional Preschool Environment Assessment▲9.2k2.67
[PDF]PhaDiSR: Phase-Aware One-Step Diffusion Transformer for Real-World Image Super-Resolution▲5.4k3.00
[PDF]MEDAGENT-X: An Agentic Framework for Retrieval-Grounded and Auditable Medical Image Classification▼1.2k1.67
[PDF]SciGen-Verifier: A Multimodal Reasoner for Explainable Verification in Scientific Image Generation▲6.6k3.33
[PDF]CV-Arena: An Open Benchmark for Instructional Computer Vision Problem Solving with Human-AI Collaborative Preferences▲3952.67
[PDF]Dispersed Any-Order Speculative Decoding for Exact Parallel Autoregressive Image Generation▲4.6k3.00
[PDF]WideR: Rate-adaptive Balancing for Wide-range Rate-Distortion-Perception Control in Neural Image Compression▲3.0k2.33
[PDF]Training Recipes Leak Through Behavioral Fingerprints in Text-to-Image Diffusion Models▼4.5k2.67
[PDF]How Much Alignment Capacity Does EEG-to-Visual Decoding Need? Retrieval Is Preserved with 42% Fewer Parameters▼1361.33
[PDF]Foveation as a Self-Supervision Signal: Blurring Beats Blanking for Learning Robust Visual Representations▼4.3k2.00
[PDF]An End-to-End Latent-Rollout Approach for Pushing Few-Step ImageNet- Generation to FID without Fr\'echet Losses▼1.2k1.67
[PDF]Look Back to Move Forward: Learning to Revisit for Agentic Compositional Image Generation▲9.2k2.67
[PDF]How Far Do Simple Transformations Translate Across Heterogeneous Text and Image Embedding Models?▼4.3k2.00
Withdrawn or desk rejected (591)
[PDF]DelibRRG: Trustworthy Cross-Examination and Clinical-First Deliberation for Radiology Report GenerationWithdrawn2.00
[PDF]DualBridge: What to Transmit Between Heterogeneous Foundation Models for Domain-Generalized Medical Image SegmentationWithdrawn1.67
[PDF]Beyond Domain Alignment: Anatomically Constrained Unsupervised Adaptation for Optic Nerve Head SegmentationWithdrawn1.00