Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World
DiaVLo: Diagnosing Behaviours of Vision-Language Models
When Should a Failing Robot Ask? Initiating Corrective Human-Robot Dialogue from Audited Sensor Evidence
Cross-Modal Attention Acts as a Frequency Filter: Why Verbose Prompts Improve Robustness in Vision-Language Models
1
PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection
Reporting Practice Matters: The Impact of Reference Choice on Chest X-ray Report Evaluation
MUSE: Benchmarking Large Vision-Language Models on Multi-Modal Understanding in Situated Education
1
Bridging the Confidence Gap: Temperature Scaling for Calibrating Test-Time Prompt Tuning
1
Don't Send What You Don't Need: Question-Guided Token Pruning as a Privacy Defense for Vision-Language Models
1
E2A-Bench: Benchmarking Evidence-to-Action Reliability in Financial Chart Reasoning
Can Edge-Deployable Vision-Language Models Identify Species?
1
Feature Recovery for Object Understanding After Irreversible Fire Damage
Show-Harness: Just a VLM Agent Can Play Robots
Think Before You Link: Rarity, Reasoning, and Retrieval in Multilingual Entity Linking
1
GoDeep: Annotation-Free Open-Vocabulary 3D Scene Understanding via Language-Space Lifting
CoVeR: Coverage-Based Token Pruning for Multi-View 3D Reasoning in VLMs
SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking Problem
Reason Through the Latent! Making Latent Visual Reasoning Necessary
Knowing What Not to Answer: Selective Non-Compliance in Vision-Language Models
1
Real-World Knowledge-Guided Change Data Synthesis for Remote Sensing
