6 papers
Non-contact Vital Signs Detection in Dynamic Environments
Shuai Sun, Chong-Xi Liang, Chengwei Ye +2
Accurate phase demodulation is critical for vital sign detection using millimeter-wave radar. However, in complex environments, time-varying DC offsets and phase imbalances can sev…
CCL: Collaborative Curriculum Learning for Sparse-Reward Multi-Agent Reinforcement Learning via Co-evolutionary Task Evolution
Yufei Lin, Chengwei Ye, Huanzhen Zhang +4
Sparse reward environments pose significant challenges in reinforcement learning, especially within multi-agent systems (MAS) where feedback is delayed and shared across agents, le…
Efficient Knowledge Transfer in Multi-Task Learning through Task-Adaptive Low-Rank Representation
Xiao Zhang, Kangsheng Wang, Tianyu Hu +1
Pre-trained language models (PLMs) demonstrate remarkable intelligence but struggle with emerging tasks unseen during training in real-world applications. Training separate models…
MedConv: Convolutions Beat Transformers on Long-Tailed Bone Density Prediction
Xuyin Qi, Zeyu Zhang, Huazhan Zheng +19
Bone density prediction via CT scans to estimate T-scores is crucial, providing a more precise assessment of bone health compared to traditional methods like X-ray bone density tes…
CSCE: Boosting LLM Reasoning by Simultaneous Enhancing of Causal Significance and Consistency
Kangsheng Wang, Xiao Zhang, Juntao Lyu +2
Chain-based reasoning methods like chain of thought (CoT) play a rising role in solving reasoning tasks for large language models (LLMs). However, the causal hallucinations between…
CreDes: Causal Reasoning Enhancement and Dual-End Searching for Solving Long-Range Reasoning Problems using LLMs
Kangsheng Wang, Xiao Zhang, Hao Liu +3
Large language models (LLMs) have demonstrated limitations in handling combinatorial optimization problems involving long-range reasoning, partially due to causal hallucinations an…