MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding
Paper • 2603.22458 • Published • 123 •
6
Grant Singleton
grantsing
AI & ML interests
Computer vision, robotics, LLMs
Recent Activity
commentedon a paper about 16 hours ago
MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding commentedon a paper about 16 hours ago
SIMART: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLM commentedon a paper about 16 hours ago
SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and PlanningOrganizations
None yet
commented 5
papers about 16 hours ago
SIMART: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLM
Paper • 2603.23386 • Published • 40 •
3
SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning
Paper • 2603.23483 • Published • 56 •
4
DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models
Paper • 2603.23499 • Published • 46 •
3
CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents
Paper • 2603.24440 • Published • 83 •
5
commented 6
papers 1 day ago
Demystifing Video Reasoning
Paper • 2603.16870 • Published • 360 •
7
InCoder-32B: Code Foundation Model for Industrial Scenarios
Paper • 2603.16790 • Published • 301 •
5
MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild
Paper • 2603.17187 • Published • 131 •
4
Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs
Paper • 2603.16932 • Published • 83 •
5
Look Where It Matters: High-Resolution Crops Retrieval for Efficient VLMs
Paper • 2603.16932 • Published • 83 •
5
Efficient Reasoning with Balanced Thinking
Paper • 2603.12372 • Published • 142 •
4
commented 5
papers 3 days ago
GENIUS: Generative Fluid Intelligence Evaluation Suite
Paper • 2602.11144 • Published • 55 •
3
Dynamic Long Context Reasoning over Compressed Memory via End-to-End Reinforcement Learning
Paper • 2602.08382 • Published • 11 •
3
Data Repetition Beats Data Scaling in Long-CoT Supervised Fine-Tuning
Paper • 2602.11149 • Published • 15 •
5
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
Paper • 2602.10604 • Published • 193 •
6
Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task
Paper • 2506.08872 • Published • 13 •
2
commented 4
papers 4 days ago
Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation
Paper • 2602.12125 • Published • 60 •
3
OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens
Paper • 2603.02138 • Published • 149 •
5
Utonia: Toward One Encoder for All Point Clouds
Paper • 2603.03283 • Published • 184 •
4
UniG2U-Bench: Do Unified Models Advance Multimodal Understanding?
Paper • 2603.03241 • Published • 86 •
4