Unlimited OCR Works

Unlimited OCR introduces Reference Sliding Window Attention to eliminate growing memory consumption during long-sequence OCR tasks, enabling efficient transcription of multiple pages in a single forward pass.

https://arxiv.org/abs/2606.23050

https://hjfy.top/arxiv/2606.23050

https://github.com/baidu/Unlimited-OCR (30222)

HairDeck: Animation-Ready Stylized Hair Cards from a Single Image

HairDeck generates stylized hair cards and spring-bone animations as unordered token sets using a diffusion transformer, improving accuracy and speed over prior methods.

https://arxiv.org/abs/2610.40599

https://hjfy.top/arxiv/2610.40599

https://github.com/hyz317/HairDeck (563)

Very Large-Scale Multi-Agent Simulation in AgentScope

Enhancements to the AgentScope platform improve scalability, efficiency, and ease of use for large-scale multi-agent simulations through distributed mechanisms, flexible environments, and user-friendly tools.

https://arxiv.org/abs/2407.17789

https://hjfy.top/arxiv/2407.17789

https://github.com/modelscope/agentscope (35121)

AgentScope 1.0: A Developer-Centric Framework for Building AgenticApplications

AgentScope enhances agentic applications by providing flexible tool-based interactions, unified interfaces, and advanced infrastructure based on the ReAct paradigm, supporting efficient and safe development and deployment.

https://arxiv.org/abs/2508.16279

https://hjfy.top/arxiv/2508.16279

https://github.com/agentscope-ai/agentscope (35122)

Xiaomi-OCR-0 Technical Report

Xiaomi-OCR-0 is a compact vision-language model that unifies document parsing and OCR understanding through automated data synthesis, progressive training with text anchoring and reinforcement learning, and achieves state-of-the-art results on multiple benchmarks.

https://arxiv.org/abs/2609.36136

https://hjfy.top/arxiv/2609.36136

https://github.com/SeerRay-Lab/Xiaomi-OCR-0 (567)

FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution

FreeToken is an edge-native Mixture-of-Experts serving system that dynamically maps computation and model state onto heterogeneous local hardware to run large open-weight models on personal machines.

https://arxiv.org/abs/2608.16157

https://hjfy.top/arxiv/2608.16157

https://github.com/FlashML-org/FreeToken (15178)

Investor's Last Exam: Can AI Agents Do Equity Investment Without Seeing the Future?

Investor's Last Exam evaluates financial agents on end-to-end equity research using frozen evidence, expert criteria, and dependency graphs, revealing that top models excel at research but fail at forecasting and investment judgments.

https://arxiv.org/abs/2610.38342

https://hjfy.top/arxiv/2610.38342

https://github.com/Prophetlab/Investor-Last-Exam (128)

Efficient Memory Management for Large Language Model Serving withPagedAttention

PagedAttention algorithm and vLLM system enhance the throughput of large language models by efficiently managing memory and reducing waste in the key-value cache.

https://arxiv.org/abs/2309.06180

https://hjfy.top/arxiv/2309.06180

https://github.com/vllm-project/vllm (86094)

Differentiable Data Augmentation with Kornia

This paper reviews the Kornia differentiable data augmentation module for both 2D and 3D tensors, integrating with PyTorch's autograd and optim, and benchmarks it against other frameworks.

https://arxiv.org/abs/2011.09832

https://hjfy.top/arxiv/2011.09832

https://github.com/arraiyopensource/kornia (11763)