3 citations · 7 across the 24 of their papers we have counts for
25 papers
MonkeyOCRv2: A Visual-Text Foundation Model for Document AI
Yuliang Liu, Zhang Li, Ziyang Zhang +11
Mainstream visual encoders are pretrained on natural images and cannot be effectively applied to document images without document-oriented adaptation, as dense text and fine-graine…
Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents
Ran Yan, Wei Fu, Jiale Li +21
LLM agents are rapidly being deployed in production, including coding assistants, customer-support chatbots, and scientific research assistants, yet they remain fundamentally stati…
Controllable Narrative Rendering for Enhanced Assisted Writing
Mingzhe Lu, Yanbing Liu, Jiayue Wu +5
Despite the remarkable proficiency of large language models (LLMs) in basic writing assistance, their utility in creative writing is fundamentally hindered by a persistent binary f…
D^2SD: Accelerating Speculative Decoding with Dual Diffusion Draft Models
Liyuan Zhang, Jiarui Zhang, Jinwei Yao +6
Speculative decoding accelerates autoregressive large language model inference by drafting multiple tokens and verifying them in a single target-model forward pass. Recent diffusio…
S^2tory: Story Spine Distillation for Movie Script Summarization
Mingzhe Lu, Yanbing Liu, Qihao Wang +5
Movie scripts pose a fundamental challenge for automatic summarization due to their non-linear, cross-cut narrative structure, which makes surface-level saliency methods ineffectiv…
Local-First Intelligence via Proactive SLM Collaborating with Feedback-Providing LLM
Hang Zeng, Xiangyu Liu, Yong Hu +5
Personal intelligence requires strong capabilities under strict privacy and efficiency constraints. Unlike cloud-first intelligence, which relies on powerful but costly and privacy…
From Myopic Selection to Long-Horizon Awareness: Sequential LLM Routing for Multi-Turn Dialogue
Jiarui Zhang, Xiangyu Liu, Yong Hu +5
Multi-turn dialogue is the predominant form of interaction with large language models (LLMs). While LLM routing is effective in single-turn settings, existing methods fail to maxim…
Automatic Method Illustration Generation for AI Scientific Papers via Drawing Middleware Creation, Evolution, and Orchestration
Zhuoling Li, Jiarui Zhang, Ping Hu +4
Method illustrations (MIs) play a crucial role in conveying the core ideas of scientific papers, yet their generation remains a labor-intensive process. Here, we take inspiration f…
MDPBench: A Benchmark for Multilingual Document Parsing in Real-World Scenarios
Zhang Li, Zhibo Lin, Qiang Liu +7
We introduce Multilingual Document Parsing Benchmark, the first benchmark for multilingual digital and photographed document parsing. Document parsing has made remarkable strides,…
DiffGraph: An Automated Agent-driven Model Merging Framework for In-the-Wild Text-to-Image Generation
Zhuoling Li, Hossein Rahmani, Jiarui Zhang +5
The rapid growth of the text-to-image (T2I) community has fostered a thriving online ecosystem of expert models, which are variants of pretrained diffusion models specialized for d…
DuCCAE: A Hybrid Engine for Immersive Conversation via Collaboration, Augmentation, and Evolution
Xin Shen, Zhishu Jiang, Jiaye Yang +13
Immersive conversational systems in production face a persistent trade-off between responsiveness and long-horizon task capability. Real-time interaction is achievable for lightwei…
Toward General Semantic Chunking: A Discriminative Framework for Ultra-Long Documents
Kaifeng Wu, Junyan Wu, Qiang Liu +2
Long-document topic segmentation plays an important role in information retrieval and document understanding, yet existing methods still show clear shortcomings in ultra-long text…
AREAL-DTA: Dynamic Tree Attention for Efficient Reinforcement Learning of Large Language Models
Jiarui Zhang, Yuchen Yang, Ran Yan +8
Reinforcement learning (RL)-based post-training for large language models (LLMs) is computationally expensive, as it generates many rollout sequences that frequently share long tok…
LitVISTA: A Benchmark for Narrative Orchestration in Literary Text
Mingzhe Lu, Yiwen Wang, Yanbing Liu +8
Computational narrative analysis aims to capture rhythm, tension, and emotional dynamics in literary texts. Existing large language models can generate long stories but overly focu…
MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns
Jiarui Zhang, Yuliang Liu, Zijun Wu +17
Document parsing is a core task in document intelligence, supporting applications such as information extraction, retrieval-augmented generation, and automated document analysis. H…
MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm
Zhang Li, Yuliang Liu, Qiang Liu +8
We introduce MonkeyOCR, a document parsing model that advances the state of the art by leveraging a Structure-Recognition-Relation (SRR) triplet paradigm. This design simplifies wh…
LLM-based Automated Theorem Proving Hinges on Scalable Synthetic Data Generation
Junyu Lai, Jiakun Zhang, Shuo Xu +6
Recent advancements in large language models (LLMs) have sparked considerable interest in automated theorem proving and a prominent line of research integrates stepwise LLM-based p…
RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models
Jiarui Zhang, Xiangyu Liu, Yong Hu +3
Retrieval-Augmented Generation (RAG) significantly improves the performance of Large Language Models (LLMs) on knowledge-intensive tasks. However, varying response quality across L…
Relative Counterfactual Contrastive Learning for Mitigating Pretrained Stance Bias in Stance Detection
Jiarui Zhang, Shaojuan Wu, Xiaowang Zhang +1
Stance detection classifies stance relations (namely, Favor, Against, or Neither) between comments and targets. Pretrained language models (PLMs) are widely used to mine the stance…
Helping Language Models Learn More: Multi-dimensional Task Prompt for Few-shot Tuning
Jinta Weng, Jiarui Zhang, Yue Hu +3
Large language models (LLMs) can be used as accessible and intelligent chatbots by constructing natural language queries and directly inputting the prompt into the large language m…
Towards Perceiving Small Visual Details in Zero-shot Visual Question Answering with Multimodal LLMs
Jiarui Zhang, Mahyar Khayatkhoei, Prateek Chhikara +1
Multimodal Large Language Models (MLLMs) have recently achieved promising zero-shot accuracy on visual question answering (VQA) -- a fundamental task affecting various downstream a…
Using Visual Cropping to Enhance Fine-Detail Question Answering of BLIP-Family Models
Jiarui Zhang, Mahyar Khayatkhoei, Prateek Chhikara +1
Visual Question Answering is a challenging task, as it requires seamless interaction between perceptual, linguistic, and background knowledge systems. While the recent progress of…
Utilizing Background Knowledge for Robust Reasoning over Traffic Situations
Jiarui Zhang, Filip Ilievski, Aravinda Kollaa +3
Understanding novel situations in the traffic domain requires an intricate combination of domain-specific and causal commonsense knowledge. Prior work has provided sufficient perce…
An Empirical Investigation of Commonsense Self-Supervision with Knowledge Graphs
Jiarui Zhang, Filip Ilievski, Kaixin Ma +2
Self-supervision based on the information extracted from large knowledge graphs has been shown to improve the generalization of language models, in zero-shot evaluation on various…