AgentVQA benchmarks vision-language models on agentic visual tasks
The best of 22 models scores 58.5% on 1,000 examples drawn from 23 datasets across five agent domains.
Stories per day · 30 days
7 stories, newest first · one card per story
Stories tagged #visual-grounding
Jag: Direct Box Prediction for Efficient Visual Grounding
Jag predicts bounding boxes in one forward pass, specializing a compact multimodal model for faster visual grounding.
GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed
GroundAnything, a 4B model, pairs parallel diffusion decoding with precise visual grounding and large inference speedups.
From Routing Signals to Selective Review: Visual regrounding in MoE VLMs
MoE routing signals detect missing visual targets in Qwen and Gemma VLMs and trigger selective review.
AnchorReasoning: A Visual Grounding and Causal Reasoning Dataset in Long-Tail Autonomous Driving Scenarios
AnchorReasoning provides visually grounded reasoning data for long-tail autonomous driving across 416,119 annotated frames.
Augustinian BabyLM: What Ostensive Definition Can and Cannot Teach a Small Language Model
Study shows visually grounded token embeddings in a small masked LM persist through training and improve object-property knowledge, but escape standard BabyLM benchmarks.
What Matters, When? Diagnosing and Improving Conditional Visual Grounding in Visuomotor Imitation Policies
Researchers diagnose conditional visual grounding failures in visuomotor imitation policies and show targeted interventions substantially improve distractor robustness.