papers

Publications (20)

cs.CL2025

A Strategic Coordination Framework of Small LLMs Matches Large LLMs in Data Synthesis

Xin Gao, Qizhi Pei, Zinan Tang +5

While data synthesis and distillation are promising strategies to enhance small language models, current approaches heavily rely on Large Language Models (LLMs), which suffer from…

cs.AI2025

Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning

Yu Li, Zhuoshi Pan, Honglin Lin +3

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of LLMs. Existing research has predominantly conce…

cs.CV2026

Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility

Honglin Lin, Chonghan Qin, Zheng Liu +7

While synthetic data has proven effective for improving scientific reasoning in the text domain, multimodal reasoning remains constrained by the difficulty of synthesizing scientif…

cs.CV2026

ChartVerse: Scaling Chart Reasoning via Reliable Programmatic Synthesis from Scratch

Zheng Liu, Honglin Lin, Chonghan Qin +13

Chart reasoning is a critical capability for Vision Language Models (VLMs). However, the development of open-source models is severely hindered by the lack of high-quality training…

cs.CV2025

Where am I? Cross-View Geo-localization with Natural Language Descriptions

Junyan Ye, Honglin Lin, Leyan Ou +5

Cross-view geo-localization identifies the locations of street-view images by matching them with geo-tagged satellite images or OSM. However, most existing studies focus on image-t…

cs.CL2025

MetaLadder: Ascending Mathematical Solution Quality via Analogical-Problem Reasoning Transfer

Honglin Lin, Zhuoshi Pan, Yu Li +5

Large Language Models (LLMs) have demonstrated promising capabilities in solving mathematical reasoning tasks, leveraging Chain-of-Thought (CoT) data as a vital component in guidin…

cs.CV2026

MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods

Honglin Lin, Zheng Liu, Yun Zhu +6

Recent advances in Vision Language Models (VLMs) have driven significant progress in visual reasoning. However, open-source VLMs still lag behind proprietary systems, largely due t…

cs.LG2025

ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning

Qizhi Pei, Zhuoshi Pan, Honglin Lin +6

Large Reasoning Models (LRMs) have shown impressive capabilities in complex problem-solving, often benefiting from training on difficult mathematical problems that stimulate intric…

cs.LG2025

LEMMA: Learning from Errors for MatheMatical Advancement in LLMs

Zhuoshi Pan, Yu Li, Honglin Lin +7

Large language models (LLMs) have demonstrated remarkable reasoning capability in solving mathematical problems. However, existing approaches primarily focus on improving the quali…

cs.CV2024

ContextBLIP: Doubly Contextual Alignment for Contrastive Image Retrieval from Linguistically Complex Descriptions

Honglin Lin, Siyu Li, Guoshun Nan +8

Image retrieval from contextual descriptions (IRCD) aims to identify an image within a set of minimally contrastive candidates based on linguistically complex text. Despite the suc…

cs.LG2026

Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training

Chuxue Cao, Honglin Lin, Zhanping Zhong +5

Large Language Models (LLMs) have demonstrated strong general capabilities, yet their deployment in finance remains challenging due to dense domain-specific terminology, stringent…

cs.CV2026

SciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing

Tong Zhang, Honglin Lin, Zhou Liu +2

Scientific diagrams convey explicit structural information, yet modern text-to-image models often produce visually plausible but structurally incorrect results. Existing benchmarks…

cs.CV2022

AdaCM: Adaptive ColorMLP for Real-Time Universal Photo-realistic Style Transfer

Tianwei Lin, Honglin Lin, Fu Li +5

Photo-realistic style transfer aims at migrating the artistic style from an exemplar style image to a content image, producing a result image without spatial distortions or unreali…

cs.AI2026

Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs

Yu Li, Xiaoran Shang, Qizhi Pei +11

Post-training data plays a pivotal role in shaping the capabilities of Large Language Models (LLMs), yet datasets are often treated as isolated artifacts, overlooking the systemic…

cs.CL2025

MathFusion: Enhancing Mathematical Problem-solving of LLM through Instruction Fusion

Qizhi Pei, Lijun Wu, Zhuoshi Pan +6

Large Language Models (LLMs) have shown impressive progress in mathematical reasoning. While data augmentation is promising to enhance mathematical problem-solving ability, current…

cs.CL2025

Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning

Honglin Lin, Qizhi Pei, Xin Gao +5

Reasoning capability is pivotal for Large Language Models (LLMs) to solve complex tasks, yet achieving reliable and scalable reasoning remains challenging. While Chain-of-Thought (…

cs.CR2025

CipherBank: Exploring the Boundary of LLM Reasoning Capabilities through Cryptography Challenges

Yu Li, Qizhi Pei, Mengyuan Sun +6

Large language models (LLMs) have demonstrated remarkable capabilities, especially the recent advancements in reasoning, such as o1 and o3, pushing the boundaries of AI. Despite th…

cs.CV2025

LOKI: A Comprehensive Synthetic Data Detection Benchmark using Large Multimodal Models

Junyan Ye, Baichuan Zhou, Zilong Huang +12

With the rapid development of AI-generated content, the future internet may be inundated with synthetic data, making the discrimination of authentic and credible multimodal data in…

cs.AI2025

OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value

Mengzhang Cai, Xin Gao, Yu Li +13

The rapid evolution of Large Language Models (LLMs) is predicated on the quality and diversity of post-training datasets. However, a critical dichotomy persists: while models are r…

cs.CV2026

Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning

Juekai Lin, Yun Zhu, Honglin Lin +6

Graphics Program Synthesis is pivotal for interpreting and editing visual data, effectively facilitating the reverse-engineering of static visuals into editable TikZ code. While Ti…