6 papers
-Emotion-Bench: Exposing the Interaction Fragility of LLM Agents through Real-World User Emotions
Rishitosh Kumar Singh, Amir Saeidi, Shamanthak Hegde +2
In long-horizon tool-calling tasks, LLM agents can fail not only because of tool-use errors, but also because of ineffective interaction with users. Yet existing benchmarks largely…
Where Hallucinations Live: A Cross-Architecture Circuit in VQ-Tokenized Vision-Language Models
Shamanthak Hegde, Xiangrui Liu, Maitreya Patel +1
Unified vision-language models (VLMs) that tokenize images through a vector-quantized (VQ) codebook routinely hallucinate objects on grounded yes/no benchmarks, yet existing decodi…
ChartQA-X: Generating Explanations for Visual Chart Reasoning
Shamanthak Hegde, Pooyan Fazli, Hasti Seifi
The ability to explain complex information from chart images is vital for effective data-driven decision-making. In this work, we address the challenge of generating detailed expla…
Dual Caption Preference Optimization for Diffusion Models
Amir Saeidi, Yiran Luo, Agneet Chatterjee +4
Recent advancements in human preference optimization, originally developed for Large Language Models (LLMs), have shown significant potential in improving text-to-image diffusion m…
Making the V in Text-VQA Matter
Shamanthak Hegde, Soumya Jahagirdar, Shankar Gangisetty
Text-based VQA aims at answering questions by reading the text present in the images. It requires a large amount of scene-text relationship understanding compared to the VQA task.…
Weakly Supervised Visual Question Answer Generation
Charani Alampalle, Shamanthak Hegde, Soumya Jahagirdar +1
Growing interest in conversational agents promote twoway human-computer communications involving asking and answering visual questions have become an active area of research in AI.…