Publications (32)
LLaVA-NeuMT: Selective Layer-Neuron Modulation for Efficient Multilingual Multimodal Translation
Jingxuan Wei, Caijun Jia, Qi Chen +5
Multimodal Machine Translation (MMT) enhances translation quality by incorporating visual context, helping to resolve textual ambiguities. While existing MMT methods perform well i…
ChartReasoner: Code-Driven Modality Bridging for Long-Chain Reasoning in Chart Question Answering
Caijun Jia, Nan Xu, Jingxuan Wei +4
Recently, large language models have shown remarkable reasoning capabilities through long-chain reasoning before responding. However, how to extend this capability to visual reason…
A Survey on Image-text Multimodal Models
Ruifeng Guo, Jingxuan Wei, Linzhuang Sun +7
With the significant advancements of Large Language Models (LLMs) in the field of Natural Language Processing (NLP), the development of image-text multimodal models has garnered wi…
GGBench: A Geometric Generative Reasoning Benchmark for Unified Multimodal Models
Jingxuan Wei, Caijun Jia, Xi Bai +7
The advent of Unified Multimodal Models (UMMs) signals a paradigm shift in artificial intelligence, moving from passive perception to active, cross-modal generation. Despite their…
How RL Unlocks the Aha Moment in Geometric Interleaved Reasoning
Xiangxiang Zhang, Caijun Jia, Siyuan Li +9
Solving complex geometric problems inherently requires interleaved reasoning: a tight alternation between constructing diagrams and performing logical deductions. Although recent M…
PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control
Jingxuan Wei, Xi Bai, Shan Liu +8
Large vision-language models have significantly advanced GUI agents, enabling executable interaction across web, mobile, and desktop interfaces. Yet these gains largely rely on a f…
Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration
Linzhuang Sun, Tianyu Guo, Hao Liang +6
Recent advances in Text-to-SQL have achieved strong results in static, single-turn tasks, where models generate SQL queries from natural language questions. However, these systems…
BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Search
Linzhuang Sun, Hao Liang, Jingxuan Wei +4
Large Language Models (LLMs) have exhibited exceptional performance across a broad range of tasks and domains. However, they still encounter difficulties in solving mathematical pr…
Brain-inspired Computing Based on Deep Learning for Human-computer Interaction: A Review
Bihui Yu, Sibo Zhang, Lili Zhou +3
The continuous development of artificial intelligence has a profound impact on biomedicine and other fields, providing new research ideas and technical methods. Brain-inspired comp…
ChartMind: A Comprehensive Benchmark for Complex Real-world Multimodal Chart Question Answering
Jingxuan Wei, Nan Xu, Junnan Zhu +4
Chart question answering (CQA) has become a critical multimodal task for evaluating the reasoning capabilities of vision-language models. While early approaches have shown promisin…
Guided Verifier: Collaborative Multimodal Reasoning via Dynamic Process Supervision
Lingzhuang Sun, Ruitong Liu, Yuxia Zhu +5
Reinforcement Learning (RL) has emerged as a pivotal mechanism for enhancing the complex reasoning capabilities of Multimodal Large Language Models (MLLMs). However, prevailing par…
StructVRM: Aligning Multimodal Reasoning with Structured and Verifiable Reward Models
Xiangxiang Zhang, Jingxuan Wei, Donghong Zhong +31
Existing Vision-Language Models often struggle with complex, multi-question reasoning tasks where partial correctness is crucial for effective learning. Traditional reward mechanis…
PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents
Bihui Yu, Xinglong Xu, Junjie Jiang +6
A LaTeX manuscript that compiles without error is not necessarily publication-ready. The resulting PDFs frequently suffer from misplaced floats, overflowing equations, inconsistent…
MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification
Linzhuang Sun, Hao Liang, Jingxuan Wei +5
According to the Test-Time Scaling, the integration of External Slow-Thinking with the Verify mechanism has been demonstrated to enhance multi-round reasoning in large language mod…
Thinking with Drafting: Optical Decompression via Logical Reconstruction
Jingxuan Wei, Honghao He, Caijun Jia +9
Existing multimodal large language models have achieved high-fidelity visual perception and exploratory visual generation. However, a precision paradox persists in complex reasonin…
From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editing
Jingxuan Wei, Cheng Tan, Qi Chen +6
We introduce the task of text-to-diagram generation, which focuses on creating structured visual representations directly from textual descriptions. Existing approaches in text-to-…
Enhancing Human-like Multi-Modal Reasoning: A New Challenging Dataset and Comprehensive Framework
Jingxuan Wei, Cheng Tan, Zhangyang Gao +5
Multimodal reasoning is a critical component in the pursuit of artificial intelligence systems that exhibit human-like intelligence, especially when tackling complex tasks. While t…
Unraveling Key Factors of Knowledge Distillation
Jingxuan Wei, Linzhuang Sun, Xu Tan +2
Knowledge distillation, a technique for model compression and performance enhancement, has gained significant traction in Neural Machine Translation (NMT). However, existing resear…
PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams
Fuqiang Wang, Song Tan, Zheng Guo +8
Scientific paper recommendation is typically evaluated as static ranking over a fixed candidate set, yet real scientific reading unfolds as a daily, longitudinal process in which i…
Synth-Empathy: Towards High-Quality Synthetic Empathy Data
Hao Liang, Linzhuang Sun, Jingxuan Wei +5
In recent years, with the rapid advancements in large language models (LLMs), achieving excellent empathetic response capabilities has become a crucial prerequisite. Consequently,…
Sentence-Level or Token-Level? A Comprehensive Study on Knowledge Distillation
Jingxuan Wei, Linzhuang Sun, Yichong Leng +3
Knowledge distillation, transferring knowledge from a teacher model to a student model, has emerged as a powerful technique in neural machine translation for compressing models or…
Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning
Cheng Tan, Jingxuan Wei, Linzhuang Sun +5
Large language models equipped with retrieval-augmented generation (RAG) represent a burgeoning field aimed at enhancing answering capabilities by leveraging external knowledge bas…
SketchAgent: Generating Structured Diagrams from Hand-Drawn Sketches
Cheng Tan, Qi Chen, Jingxuan Wei +6
Hand-drawn sketches are a natural and efficient medium for capturing and conveying ideas. Despite significant advancements in controllable natural image generation, translating fre…
The Trinity of Consistency as a Defining Principle for General World Models
Jingxuan Wei, Siyuan Li, Yuhang Xu +21
The construction of World Models capable of learning, simulating, and reasoning about objective physical laws constitutes a foundational challenge in the pursuit of Artificial Gene…
Canvas-of-Thought: Grounding Reasoning via Mutable Structured States
Lingzhuang Sun, Yuxia Zhu, Ruitong Liu +10
While Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of Multimodal Large Language Models (MLLMs), relying solely on linear text sequences re…
Rational Sensibility: LLM Enhanced Empathetic Response Generation Guided by Self-presentation Theory
Linzhuang Sun, Yao Dong, Nan Xu +3
The development of Large Language Models (LLMs) provides human-centered Artificial General Intelligence (AGI) with a glimmer of hope. Empathy serves as a key emotional attribute of…
Geoint-R1: Formalizing Multimodal Geometric Reasoning with Dynamic Auxiliary Constructions
Jingxuan Wei, Caijun Jia, Qi Chen +6
Mathematical geometric reasoning is essential for scientific discovery and educational development, requiring precise logic and rigorous formal verification. While recent advances…
TRACER: Verifiable Generative Provenance for Multimodal Tool-Using Agents
Bihui Yu, Caijun Jia, Jing Chi +6
Multimodal large language models increasingly solve vision-centric tasks by calling external tools for visual inspection, OCR, retrieval, calculation, and multi-step reasoning. Cur…
GenProve: Learning to Generate Text with Fine-Grained Provenance
Jingxuan Wei, Xingyue Wang, Yanghaoyu Liao +5
Large language models (LLM) often hallucinate, and while adding citations is a common solution, it is frequently insufficient for accountability as users struggle to verify how a c…
ResearchPulse: Building Method-Experiment Chains through Multi-Document Scientific Inference
Qi Chen, Jingxuan Wei, Zhuoya Yao +5
Understanding how scientific ideas evolve requires more than summarizing individual papers-it demands structured, cross-document reasoning over thematically related research. In th…
Efficient-Empathy: Towards Efficient and Effective Selection of Empathy Data
Linzhuang Sun, Hao Liang, Jingxuan Wei +4
In recent years, with the rapid advancements in large language models (LLMs), achieving excellent empathetic response capability has become a crucial prerequisite. Consequently, ma…
Boosting the Power of Small Multimodal Reasoning Models to Match Larger Models with Self-Consistency Training
Cheng Tan, Jingxuan Wei, Zhangyang Gao +5
Multimodal reasoning is a challenging task that requires models to reason across multiple modalities to answer questions. Existing approaches have made progress by incorporating la…