activity
20212026
most citedUnderstanding and Enhancing Robustness of Concept-based Models

2 citations · 5 across the 23 of their papers we have counts for

collaborators
Showing 2025 · cs.CVShow all

5 papers · 2 filters

cs.CV2025★ 1 cited

Concept-RuleNet: Grounded Multi-Agent Neurosymbolic Reasoning in Vision Language Models

Sanchit Sinha, Guangzhi Xiong, Zhenghao He +1

Modern vision-language models (VLMs) deliver impressive predictive accuracy yet offer little insight into 'why' a decision is reached, frequently hallucinating facts, particularly…

cs.CV2025

COCO-Tree: Compositional Hierarchical Concept Trees for Enhanced Reasoning in Vision Language Models

Sanchit Sinha, Guangzhi Xiong, Aidong Zhang

Compositional reasoning remains a persistent weakness of modern vision language models (VLMs): they often falter when a task hinges on understanding how multiple objects, attribute…

cs.CV2025

Chart-RVR: Reinforcement Learning with Verifiable Rewards for Explainable Chart Reasoning

Sanchit Sinha, Oana Frunza, Kashif Rasul +2

The capabilities of Large Vision-Language Models (LVLMs) have reached state-of-the-art on many visual reasoning tasks, including chart reasoning, yet they still falter on out-of-di…

cs.CV2025

GCAV: A Global Concept Activation Vector Framework for Cross-Layer Consistency in Interpretability

Zhenghao He, Sanchit Sinha, Guangzhi Xiong +1

Concept Activation Vectors (CAVs) provide a powerful approach for interpreting deep neural networks by quantifying their sensitivity to human-defined concepts. However, when comput…

cs.CV2025

ASCENT-ViT: Attention-based Scale-aware Concept Learning Framework for Enhanced Alignment in Vision Transformers

Sanchit Sinha, Guangzhi Xiong, Aidong Zhang

As Vision Transformers (ViTs) are increasingly adopted in sensitive vision applications, there is a growing demand for improved interpretability. This has led to efforts to forward…