Picture for Spandana Gella

Spandana Gella

Rendering-Aware Reinforcement Learning for Vector Graphics Generation

Add code
May 27, 2025
Figure 1 for Rendering-Aware Reinforcement Learning for Vector Graphics Generation
Figure 2 for Rendering-Aware Reinforcement Learning for Vector Graphics Generation
Figure 3 for Rendering-Aware Reinforcement Learning for Vector Graphics Generation
Figure 4 for Rendering-Aware Reinforcement Learning for Vector Graphics Generation
Viaarxiv icon

Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QA

Add code
May 22, 2025
Viaarxiv icon

AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery

Add code
Apr 10, 2025
Viaarxiv icon

StarFlow: Generating Structured Workflow Outputs From Sketch Images

Add code
Mar 27, 2025
Figure 1 for StarFlow: Generating Structured Workflow Outputs From Sketch Images
Figure 2 for StarFlow: Generating Structured Workflow Outputs From Sketch Images
Figure 3 for StarFlow: Generating Structured Workflow Outputs From Sketch Images
Figure 4 for StarFlow: Generating Structured Workflow Outputs From Sketch Images
Viaarxiv icon

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

Add code
Mar 19, 2025
Viaarxiv icon

SafeArena: Evaluating the Safety of Autonomous Web Agents

Add code
Mar 06, 2025
Viaarxiv icon

PairBench: A Systematic Framework for Selecting Reliable Judge VLMs

Add code
Feb 21, 2025
Viaarxiv icon

AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding

Add code
Feb 03, 2025
Figure 1 for AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding
Figure 2 for AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding
Figure 3 for AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding
Figure 4 for AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding
Viaarxiv icon

FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering

Add code
Dec 09, 2024
Figure 1 for FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering
Figure 2 for FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering
Figure 3 for FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering
Figure 4 for FM2DS: Few-Shot Multimodal Multihop Data Synthesis with Knowledge Distillation for Question Answering
Viaarxiv icon

"What do others think?": Task-Oriented Conversational Modeling with Subjective Knowledge

Add code
May 20, 2023
Figure 1 for "What do others think?": Task-Oriented Conversational Modeling with Subjective Knowledge
Figure 2 for "What do others think?": Task-Oriented Conversational Modeling with Subjective Knowledge
Figure 3 for "What do others think?": Task-Oriented Conversational Modeling with Subjective Knowledge
Figure 4 for "What do others think?": Task-Oriented Conversational Modeling with Subjective Knowledge
Viaarxiv icon