BenchmarkRepo

non-profit

AI & ML interests

None defined yet.

Recent Activity

leviCCC authored a paper 17 days ago

Why MLLMs Struggle to Count: Overcoming Individuation and Aggregation Bottlenecks with ConvStack

leviCCC authored a paper 17 days ago

Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models

leviCCC authored a paper 17 days ago

Hallucinatory Image Tokens: A Training-free EAZY Approach on Detecting and Mitigating Object Hallucinations in LVLMs

View all activity

authored 3 papers 17 days ago

Why MLLMs Struggle to Count: Overcoming Individuation and Aggregation Bottlenecks with ConvStack

Paper • 2609.37096 • Published 23 days ago

Counting Circuits: Mechanistic Interpretability of Visual Reasoning in Large Vision-Language Models

Paper • 2603.18523 • Published Mar 19 • 1

Hallucinatory Image Tokens: A Training-free EAZY Approach on Detecting and Mitigating Object Hallucinations in LVLMs

Paper • 2503.07772 • Published Jul 4, 2025 • 1

updated 2 datasets 22 days ago

SLOCBench/conflict_subset40_complementary

Viewer • Updated 22 days ago • 351 • 62

SLOCBench/conflict_subset40

Viewer • Updated 22 days ago • 40 • 45