arXiv AI
Jul 7
Iterative Visual Thinking and the Self-Correction Mirage in VLM Grounding
arXiv:2606. 13156v2 Announce Type: replace-cross Abstract: Letting a vision-language model (VLM) think longer at test time has driven much recent progress.
When Does Consensus Mean Correctness? Measuring the Agreement-Accuracy Coupling with Semantics-Preserving Re-Rendering
arXiv:2608. 05670v1 Announce Type: new Abstract: A model's agreement across perturbed inputs is used both as a label-free reliability signal and as a self-training target, on the premise that agreement tracks correctness.
Related stories
arXiv Machine Learning
Sep 15
GroundBench: A Factorized, Counterfactual Benchmark for Locating VLM Affordance Failures
arXiv:2609.13308v1 Announce Type: cross Abstract: A companion evaluation found that naming the target part in a manipulation prompt increased action accuracy by 0.32-0.63 across eight vision-language...
arXiv Computer Vision
Sep 23
RECAP: Relation Evidence Calibration for Detecting Spatial Relation Hallucinations in Vision-Language Models
arXiv:2609.26093v1 Announce Type: new Abstract: Vision-language models can answer spatial relation questions confidently even when the image supports an incompatible relation. We formulate relation-g...
arXiv Machine Learning
Jun 18
A Cross-Model VLM-Judge Protocol for Single-Image 3D Mesh Quality (and Why Cheap Proxies Fall Short)
arXiv:2606. 18451v1 Announce Type: new Abstract: Single-image-to-3D generators are improving quickly, but there is no agreed, human-free way to tell whether one generated mesh is better than another.
arXiv AI
Jul 14
Interaction Scaling: Grounding the Third Axis of Test-Time Compute
arXiv:2607. 11598v1 Announce Type: new Abstract: There are two standard ways to spend more compute at test time: let a model reason longer, or sample more attempts and keep one.
arXiv AI
Aug 14
Decomposition of Evidence, Contradiction, and Fragility in Perturbation Responses
arXiv:2608. 12935v1 Announce Type: new Abstract: Perturbation methods explain model decisions by measuring prediction changes under altered inputs, but response magnitude tells us only how much a model reacts, not what that reaction means.
arXiv AI
Sep 16
Same Answer, Different Representations: Hidden instability in VLMs
arXiv:2602.06652v2 Announce Type: replace Abstract: The robustness of Vision Language Models (VLMs) is commonly assessed through output-level invariance, implicitly assuming that stable predictions r...
Hugging Face Trending Papers
Jul 13
Interaction Scaling: Grounding the Third Axis of Test-Time Compute
There are two standard ways to spend more compute at test time: let a model reason longer, or sample more attempts and keep one. Both share a hidden limit: they are internal.
arXiv Machine Learning
Jul 28
EditCLEVR: A Paired-Scene Intervention Benchmark for Compositional Faithfulness of Object-Centric Representations
arXiv:2607. 22705v1 Announce Type: cross Abstract: Object-centric learning aims to represent scenes as objects whose properties can be reused in new combinations.
arXiv Machine Learning
Sep 1
HalluPrism: When Multimodal Uncertainty Should Diagnose, Not Decide
arXiv:2608.29193v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) can assign similar confidence to answers that fail for different reasons. We propose HalluPrism, a behavioral...
arXiv AI
Sep 15
One Model, Two Physical Stories: Auditing Misalignment in Multi-Modal World Modeling
The paper investigates how multi‑modal world models can produce inconsistent outputs across different modalities, such as a video showing a ball not rebounding while a text description indicates it should. It defines two types of misalignment—internal (between modalities) and external (against a physical environment)—and introduces a physics‑grounded pipeline to measure these discrepancies. Experiments across multiple settings reveal that while the model’s language output matches the true environment, its video output frequently disagrees, indicating current unified backbones struggle with simultaneous reasoning, consistency, and physical fidelity.
arXiv Machine Learning
Aug 7
Consistency Has a Computable Blind Spot: A Commutation Theory of Label-Free Reliability for Vision-Language Figure Reading
arXiv:2608. 05675v1 Announce Type: new Abstract: Label-free reliability for vision-language models rests on invariance: perturb the input and a faithful reader's answer should not change.