13 citations · 16 across the 28 of their papers we have counts for
14 papers · 1 filter
SchemaFill: Efficient LLM Tool Calling via Slot-Parallel Speculative Decoding
Zhi-Kai Chen, Song-Yan Li, De-Chuan Zhan +1
LLM agents interact with external systems by generating structured tool calls. Given a user request, conversational context, and a catalog of tool schemas, a tool-calling model mus…
: Generalist Value Model as a Prior for Sparse RL Rollouts
Yi-Kai Zhang, Yueqing Sun, Hongyan Hao +4
In Reinforcement Learning with Verifiable Rewards (RLVR), constructing a robust advantage baseline is critical for policy gradients, effectively guiding the policy model to reinfor…
SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning
Zhen-Hao Xie, Jun-Tao Tang, Yu-Cheng Shi +3
Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, but real-world deployment requires them to continually expand their capabilities, ma…
One-Embedding-Fits-All: Efficient Zero-Shot Time Series Forecasting by a Model Zoo
Hao-Nan Shi, Ting-Ji Huang, Lu Han +2
The proliferation of Time Series Foundation Models (TSFMs) has significantly advanced zero-shot forecasting, enabling predictions for unseen time series without task-specific fine-…
Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts
Lan Li, Da-Wei Zhou, Han-Jia Ye +1
Domain-Incremental Learning (DIL) focuses on continual learning in non-stationary environments, requiring models to adjust to evolving domains while preserving historical knowledge…
Multimodal Tabular Reasoning with Privileged Structured Information
Jun-Peng Jiang, Yu Xia, Hai-Long Sun +6
Tabular reasoning involves multi-step information extraction and logical inference over tabular data. While recent advances have leveraged large language models (LLMs) for reasonin…
UniCA: Unified Covariate Adaptation for Time Series Foundation Model
Lu Han, Yu Liu, Lan Li +9
Time Series Foundation Models (TSFMs) have achieved remarkable success through large-scale pretraining. However, their design primarily targets real-valued series, limiting their a…
Model Assembly Learning with Heterogeneous Layer Weight Merging
Yi-Kai Zhang, Jin Wang, Xu-Xiang Zhong +2
Model merging acquires general capabilities without extra data or training by combining multiple models' parameters. Previous approaches achieve linear mode connectivity by alignin…
MOS: Model Surgery for Pre-Trained Model-Based Class-Incremental Learning
Hai-Long Sun, Da-Wei Zhou, Hanbin Zhao +3
Class-Incremental Learning (CIL) requires models to continually acquire knowledge of new classes without forgetting old ones. Despite Pre-trained Models (PTMs) have shown excellent…
Adaptive Adapter Routing for Long-Tailed Class-Incremental Learning
Zhi-Hong Qi, Da-Wei Zhou, Yiran Yao +2
In our ever-evolving world, new data exhibits a long-tailed distribution, such as e-commerce platform reviews. This necessitates continuous model learning imbalanced data without f…
Visualizing, Rethinking, and Mining the Loss Landscape of Deep Neural Networks
Yichu Xu, Xin-Chun Li, Lan Li +1
The loss landscape of deep neural networks (DNNs) is commonly considered complex and wildly fluctuated. However, an interesting observation is that the loss surfaces plotted along…
Exploring and Exploiting the Asymmetric Valley of Deep Neural Networks
Xin-Chun Li, Jin-Lin Tang, Bo Zhang +2
Exploring the loss landscape offers insights into the inherent principles of deep neural networks (DNNs). Recent work suggests an additional asymmetry of the valley beyond the flat…
SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion
Lu Han, Xu-Yang Chen, Han-Jia Ye +1
Multivariate time series forecasting plays a crucial role in various fields such as finance, traffic management, energy, and healthcare. Recent studies have highlighted the advanta…
Twice Class Bias Correction for Imbalanced Semi-Supervised Learning
Lan Li, Bowen Tao, Lu Han +2
Differing from traditional semi-supervised learning, class-imbalanced semi-supervised learning presents two distinct challenges: (1) The imbalanced distribution of training samples…