283 citations · 814 across the 69 of their papers we have counts for
72 papers
Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing
Guannan Lai, Han-Jia Ye
Large language model (LLM) routing aims to assign each query to the most suitable model from a heterogeneous candidate pool, improving the quality--efficiency trade-off of LLM infe…
ResiSpec: Enhancing Multi-Candidate Speculative Sampling via Residual Distribution Shaping
Zhi-Kai Chen, Jun-Jie Tao, Wei-Xiang Mao +2
The efficiency of Large Language Model (LLM) serving is fundamentally limited by the sequential nature of autoregressive decoding. Speculative Decoding (SD) mitigates this by using…
RouteJudge: An Open Platform for Reproducible and Preference-Aware LLM Routing
Guannan Lai, Haoran Hu, Han-Jia Ye
We present RouteJudge, an online pairwise preference evaluation framework for LLM routing systems, with a public platform available at https://routejudge.cn. Different from model-l…
TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention
Si-Yang Liu, Han-Jia Ye
Tabular foundation models, exemplified by TabPFN, perform prediction via in-context learning, inferring test labels directly from labeled training examples. They have demonstrated…
From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing
Guannan Lai, Haoran Hu, Long Chen +2
Existing LLM routing methods often construct supervision from a single sampled response for each query--model pair. Because LLM generation is stochastic, however, such an observati…
Polaris: Scaling Up Instruction-Guided Image Generation Towards Millions of Personalized Style Needs
Zhi-Kai Chen, Jun-Peng Jiang, Jun-Jie Tao +2
Users increasingly expect image generation models to quickly adapt to highly diverse and personalized requirements, such as producing images with distinctive styles or characterist…
TopBench: A Benchmark for Implicit Predictive Reasoning in Tabular Question Answering
An-Yang Ji, Jun-Peng Jiang, De-Chuan Zhan +1
Large Language Models (LLMs) have advanced Table Question Answering, where most queries can be answered by extracting information or simple aggregation. However, a common class of…
: A Generalist Value Model for Any Policy at State Zero
Yi-Kai Zhang, Zhiyuan Yao, Hongyan Hao +6
Policy gradient methods rely on a baseline to measure the relative advantage of an action, ensuring the model reinforces behaviors that outperform its current average capability. I…
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…
BOFA: Bridge-Layer Orthogonal Low-Rank Fusion for CLIP-Based Class-Incremental Learning
Lan Li, Tao Hu, Da-Wei Zhou +3
Class-Incremental Learning (CIL) aims to continually learn new categories without forgetting previously acquired knowledge. Vision-language models such as CLIP offer strong transfe…
Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation
Zhi-Kai Chen, Jun-Peng Jiang, Han-Jia Ye +1
Autoregressive (AR) image generation models are capable of producing high-fidelity images but often suffer from slow inference due to their inherently sequential, token-by-token de…
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…
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…
SeqFusion: Sequential Fusion of Pre-Trained Models for Zero-Shot Time-Series Forecasting
Ting-Ji Huang, Xu-Yang Chen, Han-Jia Ye
Unlike traditional time-series forecasting methods that require extensive in-task data for training, zero-shot forecasting can directly predict future values given a target time se…
Task-Agnostic Guided Feature Expansion for Class-Incremental Learning
Bowen Zheng, Da-Wei Zhou, Han-Jia Ye +1
The ability to learn new concepts while preserve the learned knowledge is desirable for learning systems in Class-Incremental Learning (CIL). Recently, feature expansion of the mod…
External Knowledge Injection for CLIP-Based Class-Incremental Learning
Da-Wei Zhou, Kai-Wen Li, Jingyi Ning +3
Class-Incremental Learning (CIL) enables learning systems to continuously adapt to evolving data streams. With the advancement of pre-training, leveraging pre-trained vision-langua…
Capability Instruction Tuning: A New Paradigm for Dynamic LLM Routing
Yi-Kai Zhang, De-Chuan Zhan, Han-Jia Ye
Large Language Models (LLMs) have demonstrated human-like instruction-following abilities, particularly those exceeding 100 billion parameters. The combined capability of some smal…
MIETT: Multi-Instance Encrypted Traffic Transformer for Encrypted Traffic Classification
Xu-Yang Chen, Lu Han, De-Chuan Zhan +1
Network traffic includes data transmitted across a network, such as web browsing and file transfers, and is organized into packets (small units of data) and flows (sequences of pac…
Dual Consolidation for Pre-Trained Model-Based Domain-Incremental Learning
Da-Wei Zhou, Zi-Wen Cai, Han-Jia Ye +2
Domain-Incremental Learning (DIL) involves the progressive adaptation of a model to new concepts across different domains. While recent advances in pre-trained models provide a sol…
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…
Revisiting Nearest Neighbor for Tabular Data: A Deep Tabular Baseline Two Decades Later
Han-Jia Ye, Huai-Hong Yin, De-Chuan Zhan +1
The widespread enthusiasm for deep learning has recently expanded into the domain of tabular data. Recognizing that the advancement in deep tabular methods is often inspired by cla…
A Closer Look at Deep Learning Methods on Tabular Datasets
Han-Jia Ye, Si-Yang Liu, Hao-Run Cai +2
Tabular data is prevalent across diverse domains in machine learning. With the rapid progress of deep tabular prediction methods, especially pretrained (foundation) models, there i…
Improving LLMs for Recommendation with Out-Of-Vocabulary Tokens
Ting-Ji Huang, Jia-Qi Yang, Chunxu Shen +3
Characterizing users and items through vector representations is crucial for various tasks in recommender systems. Recent approaches attempt to apply Large Language Models (LLMs) i…