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
24 results for “keyword:"visual understanding"” in ICLR 2027. 10 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]ChainDiff: Controllable Fine-Grained Image-Pair Synthesis and Frequency-Domain Difference Attention for Image Difference Captioning▼1351.33
[PDF]Seeing What Matters: Reward-Anchored Visual Credit Assignment via Self-Distilled Reinforcement Learning▼5.8k2.33
[PDF]Hourglass: Towards Better Unified Multimodal Modeling Through Hierarchical Sharing and Conflict-Aware Gradient Surgery▼5.9k2.50
[PDF]MuseFACET: Benchmarking Trustworthy and Controllable Image-to-Text Generation for Musuem Collection Interpretation▲5.4k3.00
[PDF]Blind at Gigapixel Scale: Visual Information Utilization in MLLMs for Whole-Slide Images▼4.5k2.67
[PDF]Omni-InteractScope: Benchmarking Proactive and Agentic Interaction in Continuous Omnimodal Streams▼1.2k1.67
[PDF]Why MLLMs Struggle to Count: Overcoming Individuation and Aggregation Bottlenecks with ConvStack▼1.2k3.00
[PDF]Knossos and Ariadne: Benchmarking and Learning Complete Diagram Topology Extraction with Vision–Language Models▲2843.00
[PDF]Rethinking Audio-Visual Temporal Alignment with Self-Supervised Reinforcement Learning▼1.2k1.67
[PDF]What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models▼5.9k2.50
[PDF]DIVE: Benchmarking Full-Duplex Interaction with Visual Engagement in Continuous Streams▲3.0k2.33
Withdrawn or desk rejected (10)
[PDF]Now You See It, Now You Don’t: Rethinking visual token allocation across Vision Language Model layersWithdrawn1.33
[PDF]Sight or Sound: Do Multimodal Large Language Models Have Blind Faith in Vision for Audio-Visual Understanding?Withdrawn1.33
[PDF]TrajSP: Trajectory-Grounded Structured Prompting for Feedback-Guided Text-to-Image GenerationWithdrawn2.00
[PDF]ShopEye: Bridging Agentic Data Construction and Active Visual Verification for Fine-Grained E-Commerce AIGC DetectionWithdrawn2.00
[PDF]EGAA: Evidence-Grounded Answer Alignment for Mitigating Cross-Modal Hallucination in Omni-Modal LLMsWithdrawn2.00
[PDF]Generation as Auxiliary Supervision: Enhancing Visual Understanding at Zero Inference Overhead via Decoupled Embedding PredictionDesk rejected