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
137 results for “keyword:"multimodal reasoning"” in ICLR 2027. 65 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Discrimination Is Not Selection: Rethinking Verifier Evaluation for Multimodal Test-Time Scaling▼1.2k1.67
[PDF]RLHarness: Co-evolving Procedural Skills with Reinforcement Learning for Long-horizon Multimodal Reasoning▼1.2k1.67
[PDF]Right Answers for the Right Reasons? Bridging Reasoning Utility and Visual Dependency in Multimodal Reinforcement Learning▲3952.67
[PDF]Prototype-driven Hierarchical Rule Induction and Matching for Efficient Video Anomaly Detection▼1361.33
[PDF]Structured Latent Reasoning: Refactoring Reasoning with Reusable Primitives for Multimodal LLMs▼4.5k2.67
[PDF]Faithful-MR1: Faithful Multimodal Reasoning via Anchoring and Reinforcing Visual Attention▼5.8k2.33
[PDF]EOR: Evidence-Obligation Reasoning for Verification-Driven Long-Video Question Answering▼4.3k2.00
[PDF]TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos▼4.5k2.67
[PDF]Label-Free Steering: Compressing Test-Time Reinforcement Learning into Bias-Only Subspaces▲6.1k2.00
[PDF]AffToM: Benchmarking Recursive Affective Theory of Mind in Dynamic Multi-Party Interactions▲4.6k3.00
[PDF]Knossos and Ariadne: Benchmarking and Learning Complete Diagram Topology Extraction with Vision–Language Models▲2843.00
[PDF]OpenTumorBoard: A Real-World Benchmark of Multidisciplinary Tumor Board Discussion Trajectories▼5.8k2.33
[PDF]SpatialCORE: Confidence-Aware Grounded Spatial Reasoning in Large Vision–Language Models▲432.75
[PDF]SC-CoIT: Self-Corrective Interleaved Chain of Thought via Bidirectional Cross-Modal Recovery▼5.8k2.33
[PDF]GroundForm: Learning to Ground Autoformalization with Verified Hindsight Credit and Growing Memory▼4.3k2.00
[PDF]SCAS: Symmetrical Concept-space Activation Steering for Joint Hallucination Mitigation and Capability Enhancement in VLMs▼12k1.67
[PDF]Scaffolding Minds: Optimizing Latent Visual Target Representations for Multimodal Reasoning▲5103.00
[PDF]Visual Logical Rule Induction by Bridging Inductive Logic Programming and Multimodal Large Language Models▼4.3k2.00
[PDF]Bifocal Self-Rewarding: Aligning Answer Sufficiency with Visual Fidelity in VLM Reasoning▲3.0k2.33
[PDF]Reason the Scene, Reconstruct the Space, Render the Unseen: TinkerCube for Spatial Intelligence▼5.8k2.33
[PDF]CrystalBench Dynamics: A Multimodal Benchmark for dynamic reasoning in crystal systems▼4.5k2.67
[PDF]VL-ReasonHijack: A Cross-Modal Collaborative Adversarial Attack Method for Vision-Language Model Reasoning▲3.0k2.33
Withdrawn or desk rejected (65)
[PDF]Now You See It, Now You Don’t: Rethinking visual token allocation across Vision Language Model layersWithdrawn1.33