28 citations · 88 across the 25 of their papers we have counts for
25 papers
InstMoE: Adaptive Multimodal Routing with Specialized Experts
Guimin Hu, Xiang He, Yingjian Li +3
Multimodal inputs are inherently heterogeneous, not only across modalities but also in the information pathways required for effective prediction. To address this limitation, we pr…
SANE: State Anomaly Neutralization for Stable Extreme-Context Delta-Rule Models
Qingwen Lin, Boyan Xu, Xiao Liu +2
Delta-Rule recurrent models maintain a fixed-size state, enabling inference memory but potentially becoming unstable under extreme-context extrapolation. By tracking RWKV-7…
CDFM: Towards a General-Purpose Causal Discovery Foundation Model
Jie Qiao, Ruichu Cai, Zijian Li +6
Causal discovery, the process of recovering underlying causal structures from observational data, is a fundamental pursuit across scientific disciplines. Over the past decades, num…
Rose-SQL: Role-State Evolution Guided Structured Reasoning for Multi-Turn Text-to-SQL
Le Zhou, Feng Yao, Fengcai Qiao +3
Recent advances in Large Reasoning Models (LRMs) trained with Long Chain-of-Thought have demonstrated remarkable capabilities in code generation and mathematical reasoning. However…
SAM-NER: Semantic Archetype Mediation for Zero-Shot Named Entity Recognition
Ruichu Cai, Juntao Gan, Miao Mai +2
Zero-shot Named Entity Recognition (ZS-NER) remains brittle under domain and schema shifts, where unseen label definitions often misalign with a large language model's (LLM's) intr…
SERE: Structural Example Retrieval for Enhancing LLMs in Event Causality Identification
Zhifeng Hao, Zhongjie Chen, Junhao Lu +5
Event Causality Identification (ECI) requires models to determine whether a given pair of events in a context exhibits a causal relationship. While Large Language Models (LLMs) hav…
IT: Stepwise Syntax Integration Tuning for Large Language Models in Aspect Sentiment Quad Prediction
Bingfeng Chen, Chenjie Qiu, Yifeng Xie +3
Aspect Sentiment Quad Prediction (ASQP) has seen significant advancements, largely driven by the powerful semantic understanding and generative capabilities of large language model…
Track-SQL: Enhancing Generative Language Models with Dual-Extractive Modules for Schema and Context Tracking in Multi-turn Text-to-SQL
Bingfeng Chen, Shaobin Shi, Yongqi Luo +3
Generative language models have shown significant potential in single-turn Text-to-SQL. However, their performance does not extend equivalently to multi-turn Text-to-SQL. This is p…
Hierarchical Action Learning for Weakly-Supervised Action Segmentation
Junxian Huang, Ruichu Cai, Hao Zhu +5
Humans perceive actions through key transitions that structure actions across multiple abstraction levels, whereas machines, relying on visual features, tend to over-segment. This…
What Gets Activated: Uncovering Domain and Driver Experts in MoE Language Models
Guimin Hu, Meng Li, Qiwei Peng +3
Most interpretability work focuses on layer- or neuron-level mechanisms in Transformers, leaving expert-level behavior in MoE LLMs underexplored. Motivated by functional specializa…
ENTRA: Entropy-Based Redundancy Avoidance in Large Language Model Reasoning
Ruichu Cai, Haopeng Du, Qingwen Lin +3
Large Reasoning Models (LRMs) often suffer from overthinking, generating unnecessarily long reasoning chains even for simple tasks. This leads to substantial computational overhead…
Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation
Zhifeng Hao, Qibin Song, Ruichu Cai +1
Recent divide-and-conquer reasoning approaches, particularly those based on Chain-of-Thought (CoT), have substantially improved the Text-to-SQL capabilities of Large Language Model…
Causal-aware Large Language Models: Enhancing Decision-Making Through Learning, Adapting and Acting
Wei Chen, Jiahao Zhang, Haipeng Zhu +5
Large language models (LLMs) have shown great potential in decision-making due to the vast amount of knowledge stored within the models. However, these pre-trained models are prone…
Causal View of Time Series Imputation: Some Identification Results on Missing Mechanism
Ruichu Cai, Kaitao Zheng, Junxian Huang +4
Time series imputation is one of the most challenge problems and has broad applications in various fields like health care and the Internet of Things. Existing methods mainly aim t…
CMCTS: A Constrained Monte Carlo Tree Search Framework for Mathematical Reasoning in Large Language Model
Qingwen Lin, Boyan Xu, Guimin Hu +4
This paper introduces the Constrained Monte Carlo Tree Search (CMCTS) framework to enhance the mathematical reasoning capabilities of Large Language Models (LLM). By incorporating…
TP-UNet: Temporal Prompt Guided UNet for Medical Image Segmentation
Ranmin Wang, Limin Zhuang, Hongkun Chen +2
The advancement of medical image segmentation techniques has been propelled by the adoption of deep learning techniques, particularly UNet-based approaches, which exploit semantic…
SGSL: Incorporating Segment to Syntactic Enhanced Graph Structure Learning for Aspect-based Sentiment Analysis
Bingfeng Chen, Qihan Ouyang, Yongqi Luo +3
Previous graph-based approaches in Aspect based Sentiment Analysis(ABSA) have demonstrated impressive performance by utilizing graph neural networks and attention mechanisms to lea…
From Large to Tiny: Distilling and Refining Mathematical Expertise for Math Word Problems with Weakly Supervision
Qingwen Lin, Boyan Xu, Zhengting Huang +1
Addressing the challenge of high annotation costs in solving Math Word Problems (MWPs) through full supervision with intermediate equations, recent works have proposed weakly super…
SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL
Ruichu Cai, Jinjie Yuan, Boyan Xu +1
The Text-to-SQL task, aiming to translate the natural language of the questions into SQL queries, has drawn much attention recently. One of the most challenging problems of Text-to…
Semi-Supervised Disentangled Framework for Transferable Named Entity Recognition
Zhifeng Hao, Di Lv, Zijian Li +3
Named entity recognition (NER) for identifying proper nouns in unstructured text is one of the most important and fundamental tasks in natural language processing. However, despite…
TAG : Type Auxiliary Guiding for Code Comment Generation
Ruichu Cai, Zhihao Liang, Boyan Xu +3
Existing leading code comment generation approaches with the structure-to-sequence framework ignores the type information of the interpretation of the code, e.g., operator, string,…
Disentanglement Challenge: From Regularization to Reconstruction
Jie Qiao, Zijian Li, Boyan Xu +2
The challenge of learning disentangled representation has recently attracted much attention and boils down to a competition using a new real world disentanglement dataset (Gondal e…
Causal Mechanism Transfer Network for Time Series Domain Adaptation in Mechanical Systems
Zijian Li, Ruichu Cai, Kok Soon Chai +7
Data-driven models are becoming essential parts in modern mechanical systems, commonly used to capture the behavior of various equipment and varying environmental characteristics.…
Data Driven Chiller Plant Energy Optimization with Domain Knowledge
Hoang Dung Vu, Kok Soon Chai, Bryan Keating +5
Refrigeration and chiller optimization is an important and well studied topic in mechanical engineering, mostly taking advantage of physical models, designed on top of over-simplif…