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
511 results for “keyword:"multimodal large language models"” in ICLR 2027. 210 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Attention-Entropy Decoding with Visual Grounding for Hallucination Mitigation in Multimodal Large Language Models▲5.4k3.00
[PDF]VAD-TTRL: Propose, Verify, Reinforce for Label-Free Test-Time Video Anomaly Detection and Understanding▼5.8k2.33
[PDF]FloodMark: A Benchmark for Flood Scene Understanding and Reasoning in Multimodal Large Language Models▲3952.67
[PDF]Beyond Feature Fidelity: Recovery and Readout Adaptation in Multimodal Large Language Models▲3.0k2.33
[PDF]MECoBench: A Systematic Study of Multimodal Agent Collaboration in Embodied Environments▼1361.33
[PDF]First Generate, Then Delete: Test-Time Thinking-Token Deletion for Multimodal Reasoning▼5.8k2.33
[PDF]SIGHT-Bench: Diagnosing Reference-Frame Consistency and Global Spatial Reasoning in Multimodal Models▼4.5k2.67
[PDF]Noise-Robust Reinforcement Learning with Verifiable Rewards for Open-ended Medical Multimodal Reasoning▲3.0k2.33
[PDF]When Marginal Stability Is Not Enough: Auditing Benchmark Conclusions under Composition Shift▼4.3k2.00
[PDF]Mind the Spatial Gap: A Benchmark for Geospatial Reasoning and Constrained Spatial Editing▲1.9k3.67
[PDF]NeuroInject: Bridging Brain and Behavior without Paired Subjects via Intermediate Clinical-State Injection for Depression Recognition▼1.2k1.67
[PDF]SonarLLM: A Native Sonar–Optical Multimodal Large Language Model for Underwater Perception▼1.2k3.00
[PDF]CountRoute: Pattern Readout and Evidence-Grounded Counting for Streaming Video Counting▼5.8k2.33
[PDF]Dual Tuning: Joint Screening of Data Utility and Supervision Modes for Multimodal Fine-Tuning▼4.3k2.00
[PDF]Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes▲1.7k3.33
[PDF]Granularity Matters: Task-Level Preservation and Direction-Level Transfer for Continual Multimodal Instruction Tuning▼4.5k2.25
[PDF]Beyond Person-Cue Suppression: Three-View Matched Contrastive Correction for Visual Cultural Attribution▲1.7k3.33
[PDF]Black-Box Backdoor Detection in Multimodal Large Language Models via Counterfactual Response Persistence▲3.0k2.33
[PDF]EviPatrol: Evidence-Grounded Split-Modal MLLM for Audio-Visual Deepfake Localization and Diagnosis▼4.3k2.00
[PDF]Evaluating Reasoning under Multimodal Conflict: Separating Score Gains from Evidence Selection▼1361.33
[PDF]Not All Preferences Are Strict: Tie-Aware Preference Optimization for Multi-Image MLLMs▼5.8k2.33
[PDF]Beyond Fixed Sampling: Uncertainty-Aware Retrieval and Spatially-Grounded Reasoning for Fine-Grained Visual Recognition▼1.2k1.67
Withdrawn or desk rejected (210)
[PDF]ViGa-SR: LLM-based Evolutionary Search for Symbolic Regression with Visual Priors Guidance from Multimodal Representation of DataWithdrawn1.33
[PDF]Beyond Online Accuracy: What Persists After Continual Test-Time Adaptation of Multimodal LLMs on Multiple-Choice VQA?Withdrawn1.67
[PDF]Learning When to Look: Attention-Proposed Temporal Rewards for Grounded Video ReasoningWithdrawn1.67
[PDF]Contrastive Trajectory-Guided Visual Evidence Reinforcement for Hallucination MitigationWithdrawn2.00
[PDF]VOLT: Joint Token Selection and Frame Budget Allocation via Subspace Volume MaximizationDesk rejected2.00