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
128 results for “keyword:"multimodal model"” in ICLR 2027. 37 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]CrossTimeBench: Benchmarking Cross-Temporal Video Reasoning in Complex Multi-Event Scenarios▼1.3k1.75
[PDF]Exploiting Video Temporal Capability as an Attack Pathway in Multimodal Large Language Models▼4.3k2.00
[PDF]What to Trust, What to Learn: A Grounded Learning Curriculum for Self-Evolving Large Multimodal Models▲5103.00
[PDF]Cross-Feature Guided Reinforcement Learning for Unified Multimodal Understanding and Generation▲3.0k2.33
[PDF]MaLoRA: Mitigating Text-Centric Bias in Multimodal Large Language Models through Key-Space Alignment▲3952.67
[PDF]Beyond Generation and Accuracy: Diagnosing and Enhancing Visual Chain-of-Thought for Geometry Problem Solving▲5103.00
[PDF]When Reflection Fails: Improving Self-Reflective Unified Multimodal Models with Correction Amplification and Fallback▲3.0k2.33
[PDF]HUG: Learning and Transferring Visual Tokens for Unified Image Understanding and Generation▼5.8k2.33
[PDF]CHIAA-Bench: Aligning Cinematic Human Image Aesthetic Assessment with Human Aesthetic Judgments▼4.3k2.00
[PDF]FoldUMM: Unlocking Efficient Inference in Unified Multimodal Models via Task-Specific Layer Folding▼1.2k3.00
[PDF]Do You See What You Draw? A Semantic Closed-Loop Framework for Holistic Evaluation of Unified Multimodal Models▲3952.67
[PDF]SteerGrounding: Instance-Adaptive Representation Steering for Reasoning Segmentation with Frozen LMMs▼4.3k2.00
[PDF]When Debiasing Relocates Shortcuts: Orthogonal Interaction Fine-Tuning for 3D Large Multimodal Models▲3952.67
[PDF]Towards Personalized Visual Imagination from Everyday User–MLLM Interaction with Unified Multimodal Models▼4.5k2.67
[PDF]From Scan to Focus: Learning a Value-Guided Adaptive Browsing Policy for Efficient Long-Video Reasoning▲3.0k2.33
[PDF]What Generation Knows: Unlocking Fine-Grained Understanding in Unified Multimodal Models▼5.9k2.50
[PDF]SC-CoIT: Self-Corrective Interleaved Chain of Thought via Bidirectional Cross-Modal Recovery▼5.8k2.33
[PDF]Learning Phylogeny-Constrained Relative Competition for Hierarchical Visual Recognition▼4.3k2.00
Withdrawn or desk rejected (37)
[PDF]Beyond Layers: Position-Resolved Gradient Conflict and Position-Aware Modulation for Unified Multimodal ModelsWithdrawn2.00
[PDF]Unified Multimodal Models Do Not Learn in Unison: Active Probing of Cross-Capability TransferWithdrawn1.33
[PDF]EgoAhead: Egocentric Human Motion Understanding with Joint Video–Motion PredictionWithdrawn2.00