SynthDocBench: Controlled Benchmark for Long-Context Visual Document Understanding
Paper • 2607.10400 • Published • 71
Agent Poirot
non-profit
AI & ML interests
None defined yet.
Recent Activity
View all activity
rajeswarsai
authored a
paper 14 days ago
rajeswarsai
authored 5
papers 15 days ago
Multi-scale Predictive Representations for Goal-conditioned Reinforcement Learning
Paper • 2605.09364 • Published
Therefore I am. I Think
Paper • 2604.01202 • Published • 33
VectorGym: A Multitask Benchmark for SVG Code Generation, Sketching, and Editing
Paper • 2603.29852 • Published • 6
ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval
Paper • 2511.00903 • Published
BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning
Paper • 2508.09804 • Published
rajeswarsai
authored a
paper 3 months ago
rajeswarsai
authored 2
papers 4 months ago
rajeswarsai
authored a
paper 5 months ago
rajeswarsai
authored a
paper 9 months ago
rajeswarsai
authored 9
papers 10 months ago
BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks
Paper • 2412.04626 • Published • 15
AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Understanding
Paper • 2502.01341 • Published • 39
InsightBench: Evaluating Business Analytics Agents Through Multi-Step Insight Generation
Paper • 2407.06423 • Published • 2
UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction
Paper • 2503.15661 • Published • 3
StarFlow: Generating Structured Workflow Outputs From Sketch Images
Paper • 2503.21889 • Published • 4
Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QA
Paper • 2505.16293 • Published • 3
Rendering-Aware Reinforcement Learning for Vector Graphics Generation
Paper • 2505.20793 • Published • 13
The Promise of RL for Autoregressive Image Editing
Paper • 2508.01119 • Published • 11
Apriel-Nemotron-15B-Thinker
Paper • 2508.10948 • Published • 6