16 citations · 19 across the 22 of their papers we have counts for
25 papers
DEEPCHART: How Far are LLMs from Faithful Data-Science Chart Generation?
Jiahui tang, Kuicai Dong, Dexun Li +7
Faithful chart generation in real-world data-science workflows requires grounding visualizations in scattered evidence, computing chart-ready quantities, and rendering them accurat…
Code as Representation: A Compilable Parsing Paradigm for Academic Documents
Rihui Jin, Jun Wang, chengyuan zhu +11
Academic papers are a primary carrier of scientific knowledge, yet most of this knowledge remains locked in PDFs that are optimized for human reading rather than machine use. For M…
EvoThink: Evolving Thinking in Large Reasoning Models via Self-Pruning and Aha-Moment Preference Optimization
Xinbang Dai, Zheyu Xin, Huikang Hu +7
Large Reasoning Models (LRMs) often suffer from overthinking due to redundant verification steps. Existing approaches for mitigating overthinking, such as fast-slow thinking switch…
When Hard Negatives Hurt: Bridging the Generative-Discriminative Gap in Hard Negative Synthesis for Retrieval
Zhicheng Zhang, Jiwei Tang, Kuicai Dong +9
Hard negative mining has become the dominant strategy for training retrievers, yet it faces intrinsic limitations: negatives are bounded by corpus availability, selected by retriev…
Learning More from Less: Exploiting Counterfactuals for Data-Efficient Chart Understanding
Jianzhu Bao, Haozhen Zhang, Kuicai Dong +5
Vision-Language Models (VLMs) have demonstrated remarkable progress in chart understanding, largely driven by supervised fine-tuning (SFT) on increasingly large synthetic datasets.…
FollowTable: A Benchmark for Instruction-Following Table Retrieval
Rihui Jin, Yuchen Lu, Ting Zhang +7
Table Retrieval (TR) has traditionally been formulated as an ad-hoc retrieval problem, where relevance is primarily determined by topical semantic similarity. With the growing adop…
Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generation
Fangda Ye, Zhifei Xie, Yuxin Hu +5
Recent agentic search frameworks enable deep research via iterative planning and retrieval, reducing hallucinations and enhancing factual grounding. However, they remain text-centr…
SRR-Judge: Step-Level Rating and Refinement for Enhancing Search-Integrated Reasoning in Search Agents
Chen Zhang, Kuicai Dong, Dexun Li +4
Recent deep search agents built on large reasoning models (LRMs) excel at complex question answering by iteratively planning, acting, and gathering evidence, a capability known as…
To Search or Not to Search: Aligning the Decision Boundary of Deep Search Agents via Causal Intervention
Wenlin Zhang, Kuicai Dong, Junyi Li +9
Deep search agents, which autonomously iterate through multi-turn web-based reasoning, represent a promising paradigm for complex information-seeking tasks. However, current agents…
Exploring Recommender System Evaluation: A Multi-Modal User Agent Framework for A/B Testing
Wenlin Zhang, Xiangyang Li, Qiyuan Ge +9
In recommender systems, online A/B testing is a crucial method for evaluating the performance of different models. However, conducting online A/B testing often presents significant…
Doc-Researcher: A Unified System for Multimodal Document Parsing and Deep Research
Kuicai Dong, Shurui Huang, Fangda Ye +9
Deep Research systems have revolutionized how LLMs solve complex questions through iterative reasoning and evidence gathering. However, current systems remain fundamentally constra…
Reinforcement Learning Foundations for Deep Research Systems: A Survey
Wenjun Li, Zhi Chen, Jingru Lin +8
Deep research systems, agentic AI that solve complex, multi-step tasks by coordinating reasoning, search across the open web and user files, and tool use, are moving toward hierarc…
Humanity's Last Code Exam: Can Advanced LLMs Conquer Human's Hardest Code Competition?
Xiangyang Li, Xiaopeng Li, Kuicai Dong +7
Code generation is a core capability of large language models (LLMs), yet mainstream benchmarks (e.g., APPs and LiveCodeBench) contain questions with medium-level difficulty and po…
Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answering
Kuicai Dong, Yujing Chang, Shijie Huang +3
Document Visual Question Answering (DocVQA) faces dual challenges in processing lengthy multimodal documents (text, images, tables) and performing cross-modal reasoning. Current do…
Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning
Wenlin Zhang, Xiangyang Li, Kuicai Dong +9
Retrieval-augmented generation (RAG) enhances the text generation capabilities of large language models (LLMs) by integrating external knowledge and up-to-date information. However…
RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery
Hongchao Gu, Dexun Li, Kuicai Dong +6
Generating knowledge-intensive and comprehensive long texts, such as encyclopedia articles, remains significant challenges for Large Language Models. It requires not only the preci…
Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger
Wenjun Li, Dexun Li, Kuicai Dong +6
Large language models (LLMs) have shown remarkable emergent capabilities, transforming the execution of functional tasks by leveraging external tools for complex problems that requ…
MMDocIR: Benchmarking Multimodal Retrieval for Long Documents
Kuicai Dong, Yujing Chang, Xin Deik Goh +3
Multimodal document retrieval aims to identify and retrieve various forms of multimodal content, such as figures, tables, charts, and layout information from extensive documents. D…
Collaborative Cross-modal Fusion with Large Language Model for Recommendation
Zhongzhou Liu, Hao Zhang, Kuicai Dong +1
Despite the success of conventional collaborative filtering (CF) approaches for recommendation systems, they exhibit limitations in leveraging semantic knowledge within the textual…
CoIR: A Comprehensive Benchmark for Code Information Retrieval Models
Xiangyang Li, Kuicai Dong, Yi Quan Lee +5
Despite the substantial success of Information Retrieval (IR) in various NLP tasks, most IR systems predominantly handle queries and corpora in natural language, neglecting the dom…
CtrlA: Adaptive Retrieval-Augmented Generation via Inherent Control
Huanshuo Liu, Hao Zhang, Zhijiang Guo +6
Retrieval-augmented generation (RAG) has emerged as a promising solution for mitigating hallucinations of large language models (LLMs) with retrieved external knowledge. Adaptive R…
Multi-view Content-aware Indexing for Long Document Retrieval
Kuicai Dong, Derrick Goh Xin Deik, Yi Quan Lee +4
Long document question answering (DocQA) aims to answer questions from long documents over 10k words. They usually contain content structures such as sections, sub-sections, and pa…
LLMTreeRec: Unleashing the Power of Large Language Models for Cold-Start Recommendations
Wenlin Zhang, Chuhan Wu, Xiangyang Li +7
The lack of training data gives rise to the system cold-start problem in recommendation systems, making them struggle to provide effective recommendations. To address this problem,…
Aligning Crowd Feedback via Distributional Preference Reward Modeling
Dexun Li, Cong Zhang, Kuicai Dong +3
Deep Reinforcement Learning is widely used for aligning Large Language Models (LLM) with human preference. However, the conventional reward modelling is predominantly dependent on…