Spandana Gella

DRBench: A Realistic Benchmark for Enterprise Deep Research

Grounding Computer Use Agents on Human Demonstrations

VectorGym: A Multi-Task Benchmark for SVG Code Generation and Manipulation

Improving GUI Grounding with Explicit Position-to-Coordinate Mapping

AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery

PairBench: Are Vision-Language Models Reliable at Comparing What They See?

Rendering-Aware Reinforcement Learning for Vector Graphics Generation

AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding

SafeArena: Evaluating the Safety of Autonomous Web Agents

BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning

BigDocs: An Open Dataset for Training Multimodal Models on Document and Code Tasks

UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction