4 citations · 11 across the 17 of their papers we have counts for
20 papers
Ripple-Pivot Search: Active Parallel Decoding for Diffusion Large Language Models
Yushi Ye, Xu Chen, Haoyun Jiang +9
Diffusion Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive language models, offering the potential for substantially faster inference throu…
Dementia Etiology Diagnosis via Collaborative Meta Knowledge Enhancement
Siyuan Du, Mengxi Chen, Xinyang Jiang +6
Although artificial intelligence (AI) has shown promising performance in several medical tasks, accurate dementia etiology diagnosis with AI remains challenging due to complex over…
Deep Reprogramming Distillation for Medical Foundation Models
Siyuan Du, Yuhang Zhou, Haolin Li +5
Medical foundation models pre-trained on large-scale datasets have shown powerful versatile performance. However, when adapting medical foundation models for specific medical scena…
Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning Approach
Haolin Li, Shuyang Jiang, Ruipeng Zhang +3
While large language models hold promise for complex medical applications, their development is hindered by the scarcity of high-quality reasoning data. To address this issue, exis…
Rejection Mixing: Fast Semantic Propagation of Mask Tokens for Efficient DLLM Inference
Yushi Ye, Feng Hong, Huangjie Zheng +4
Diffusion Large Language Models (DLLMs) promise fast non-autoregressive inference but suffer a severe quality-speed trade-off in parallel decoding. This stems from the ''combinator…
Dual-granularity Sinkhorn Distillation for Enhanced Learning from Long-tailed Noisy Data
Feng Hong, Yu Huang, Zihua Zhao +5
Real-world datasets for deep learning frequently suffer from the co-occurring challenges of class imbalance and label noise, hindering model performance. While methods exist for ea…
RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis
Haolin Li, Tianjie Dai, Zhe Chen +4
Clinical diagnosis is a highly specialized discipline requiring both domain expertise and strict adherence to rigorous guidelines. While current AI-driven medical research predomin…
Decouple before Align: Visual Disentanglement Enhances Prompt Tuning
Fei Zhang, Tianfei Zhou, Jiangchao Yao +3
Prompt tuning (PT), as an emerging resource-efficient fine-tuning paradigm, has showcased remarkable effectiveness in improving the task-specific transferability of vision-language…
Differential-informed Sample Selection Accelerates Multimodal Contrastive Learning
Zihua Zhao, Feng Hong, Mengxi Chen +5
The remarkable success of contrastive-learning-based multimodal models has been greatly driven by training on ever-larger datasets with expensive compute consumption. Sample select…
Wide-In, Narrow-Out: Revokable Decoding for Efficient and Effective DLLMs
Feng Hong, Geng Yu, Yushi Ye +5
Diffusion Large Language Models (DLLMs) have emerged as a compelling alternative to Autoregressive models, designed for fast parallel generation. However, existing DLLMs are plague…
ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verification
Ziqing Fan, Cheng Liang, Chaoyi Wu +3
Recent advances in reasoning-enhanced large language models (LLMs) and multimodal LLMs (MLLMs) have significantly improved performance in complex tasks, yet medical AI models often…
Combatting Dimensional Collapse in LLM Pre-Training Data via Diversified File Selection
Ziqing Fan, Siyuan Du, Shengchao Hu +5
Selecting high-quality pre-training data for large language models (LLMs) is crucial for enhancing their overall performance under limited computation budget, improving both traini…
Learning to Instruct for Visual Instruction Tuning
Zhihan Zhou, Feng Hong, Jiaan Luo +5
We propose L2T, an advancement of visual instruction tuning (VIT). While VIT equips Multimodal LLMs (MLLMs) with promising multimodal capabilities, the current design choices for V…
Task-Aware Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning
Ziqing Fan, Shengchao Hu, Yuhang Zhou +4
The purpose of offline multi-task reinforcement learning (MTRL) is to develop a unified policy applicable to diverse tasks without the need for online environmental interaction. Re…
Self-supervised Anomaly Detection Pretraining Enhances Long-tail ECG Diagnosis
Aofan Jiang, Chaoqin Huang, Qing Cao +5
Current computer-aided ECG diagnostic systems struggle with the underdetection of rare but critical cardiac anomalies due to the imbalanced nature of ECG datasets. This study intro…
Few-Shot Anomaly Detection via Category-Agnostic Registration Learning
Chaoqin Huang, Haoyan Guan, Aofan Jiang +4
Most existing anomaly detection (AD) methods require a dedicated model for each category. Such a paradigm, despite its promising results, is computationally expensive and inefficie…
Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization
Ziqing Fan, Shengchao Hu, Jiangchao Yao +4
In federated learning (FL), the multi-step update and data heterogeneity among clients often lead to a loss landscape with sharper minima, degenerating the performance of the resul…
Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts
Ruipeng Zhang, Ziqing Fan, Jiangchao Yao +2
This paper presents a Domain-Inspired Sharpness-Aware Minimization (DISAM) algorithm for optimization under domain shifts. It is motivated by the inconsistent convergence degree of…
HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning
Shengchao Hu, Ziqing Fan, Li Shen +3
The purpose of offline multi-task reinforcement learning (MTRL) is to develop a unified policy applicable to diverse tasks without the need for online environmental interaction. Re…
Q-value Regularized Transformer for Offline Reinforcement Learning
Shengchao Hu, Ziqing Fan, Chaoqin Huang +4
Recent advancements in offline reinforcement learning (RL) have underscored the capabilities of Conditional Sequence Modeling (CSM), a paradigm that learns the action distribution…