8 papers
Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation
Yuying Li, Leqi Zheng, Yongzi Yu +6
On-Policy distillation (OPD) in large language models is shifting from full-trace KL supervision toward more selective training paradigms. Recent OPD methods increasingly focus on…
Efficient LLM Reasoning via Variational Posterior Guidance with Efficiency Awareness
Zizhao Chen, Yuying Li, Siting Lin +1
Although large language models rely on chain-of-thought for complex reasoning, the overthinking phenomenon severely degrades inference efficiency. Existing reinforcement learning m…
RealChart2Code: Advancing Chart-to-Code Generation with Real Data and Multi-Task Evaluation
Jiajun Zhang, Yuying Li, Zhixun Li +13
Vision-Language Models (VLMs) have demonstrated impressive capabilities in code generation across various domains. However, their ability to replicate complex, multi-panel visualiz…
VeriSciQA: An Auto-Verified Dataset for Scientific Visual Question Answering
Yuyi Li, Daoyuan Chen, Zhen Wang +2
Large Vision-Language Models (LVLMs) show promise for scientific applications, yet open-source models still struggle with Scientific Visual Question Answering (SVQA), namely answer…
What Should I Cite? A RAG Benchmark for Academic Citation Prediction
Leqi Zheng, Jiajun Zhang, Canzhi Chen +13
With the rapid growth of Web-based academic publications, more and more papers are being published annually, making it increasingly difficult to find relevant prior work. Citation…
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…