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
1,223 results for “keyword:"vision language models"” in ICLR 2027. 507 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]RL-Trained Crop-and-Zoom Is Often Decorative: Pixel Budgets, Protocol Costs, and Causal Credit▼4.5k2.67
[PDF]Seeing Before Distilling: Prefill Visual Alignment for Multimodal On-Policy Distillation▼4.3k2.00
[PDF]SAGA: Single-Sequence Coupling of Description and Scoring via Scene-Attribute Graphs based Aesthetic Learning▼5.8k2.33
[PDF]Provenance is not Universal: Discovering and Distilling Forensic Subspaces in Frozen Vision-Language Models▼5.8k2.33
[PDF]MARP: Task-Generalized Meta-Attack for Promotion in CLIP-Based Text-to-Image Retrieval▲3.0k2.33
[PDF]When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models▼4.3k2.00
[PDF]Harnessing Domain Specialists in Multimodal Mixture-of-Experts for Efficient Adaptation▲5103.00
[PDF]PLAN-Bench: Can Existing VLMs Go Well Beyond Perception to Reason and Plan in Embodied Worlds?▼1.2k1.67
[PDF]PhysEvolve: Verifier-Grounded Self-Evolution for Physical Reasoning with Executable Worlds▼5.9k2.50
[PDF]EAPlace-VLM: Evolutionary Macro Placement via Vision-Language Topological Diagnosis and Grid-Free Continuous Refinement▼1.2k1.67
[PDF]Less Data, Better Timing: Student–Curriculum Coupling for VLM On-Policy Distillation in Temporal Video Grounding▲9.2k2.67
[PDF]Learning to Zoom at the Right Difficulty: Dynamic Curricula for Visual Tool-Use Reinforcement Learning▲5103.00
[PDF]What Should a VLM Tell an Action Expert? Comparing Conditioning Interfaces for Long-Horizon Furniture Assembly▼1361.33
[PDF]RGB-OPD: Representation-Guided Budgeting for On-Policy Distillation in Multimodal Reasoning▼4.3k2.00
[PDF]Measuring Alignment Collapse: A Training-Free Framework for Object Hallucination in Vision-Language Models▼1361.33
[PDF]FinVQA-Chart: A Diagnostic Benchmark Isolating the Multimodal Fusion Bottleneck in Financial Chart Understanding▼1.2k1.67
[PDF]ViCoR: Reliable Molecular Structure Extraction via Spatially Aligned Verification and Executable Revision▲3.0k2.50
[PDF]Still There, No Longer Seen: Exposing Compression-Induced Risk In Large Vision-Language Models▲5103.00
[PDF]Sampling Versus Longer Responses for Visual Reasoning: A Matched-Prompt MathVista Study▼1361.33
Withdrawn or desk rejected (507)
[PDF]Counterfactual Auditing of Object Presence and Quantity Judgments in Vision-Language ModelsWithdrawn1.67
[PDF]TFAG-OVD: Training-Free Attribute-Guided Open-Vocabulary Detection via LLM Semantic CompositionWithdrawn1.67
[PDF]Now You See It, Now You Don’t: Rethinking visual token allocation across Vision Language Model layersWithdrawn1.33
[PDF]Most of the Gain Is Not Video: Taking Apart a Fine-Tuned Video Question-Answering ScoreWithdrawn1.67
[PDF]When Visual Signals Mislead: A Mechanistic Study of Attribute Hallucination in Vision-Language ModelsWithdrawn1.33