1 citations · 1 across the 18 of their papers we have counts for
11 papers · 1 filter
ECG-RSI: Recursive Self-Improvement through Targeted Electrocardiogram Waveform Evolution
Xiaoliang Wang, Zhuo Chen, Chuanyang Zheng +9
Electrocardiogram (ECG) models need supervision that targets evolving weaknesses and remains faithful to waveform evidence. We introduce ECG-RSI, a recursive self-improvement frame…
MedEvo: Medical Reasoning Evolution through Knowledge Navigation
Xiaoliang Wang, Zhuo Chen, Chuanyang Zheng +11
Medical multimodal reasoning models are typically trained on teacher-generated rationales, discarding the valid reasoning in students' own failed trajectories, while general-domain…
Teacher-Student Gaps Are Not Enough: Outcome-Guided On-Policy Distillation for Multi-Turn Autonomous Agents
Tong Zhang, Zhou Liu, Yihao Liu +8
On-policy distillation (OPD) trains a student on its own trajectories with dense teacher supervision. Recent work on OPD for multi-turn autonomous agents often treats large teacher…
ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL
Zhuoshi Pan, Qizhi Pei, Junru Lu +4
Long-horizon agentic tasks require large language models (LLMs) to iteratively retrieve, integrate, and maintain dispersed information across multi-turn interactions, but preservin…
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…
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…
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…
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…
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…
Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility
Honglin Lin, Zheng Liu, Chonghan Qin +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…
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…