HY
Han-Jia Ye
cs.LGcs.CVcs.AIcs.CLcs.IRstat.MLAbductive learningcs.CRcs.MMcs.SE
On Valency
published · living versionsW_wdj6ccbs·v1 · currentpublished
Toward Collective Model Intelligence: Characterizing and Coordinating Models
with SinapisAI Team, Jian-Dong Liu, Qun Dai, Zhendong Du +25
1 version
W_cn5584dm·v2published
Preprints & journals
111 papers in the corpus · 2018–2026Learning What to Remember: Resource-Efficient Self-Improvement for Lifelong Agents2610.26453v2 · Guannan Lai, Zi-Yang Bai, Jun-Peng Jiang et al.2026 · 0 citationsarXivon Valency
Toward Collective Model Intelligence: Characterizing and Coordinating Models2610.24739v1 · SinapisAI Team: Jian-Dong Liu, Qun Dai, Zhendong Du et al.2026 · 0 citationsarXivon Valency
TabGift: A Context-Efficient Foundation Model for Tabular Data Generation2610.16990v1 · Yu-Sheng Li, Jun-Peng Jiang, Han-Jia Ye2026 · 0 citationsarXiv
Thinking in Depth: Retrospective Inference for Tabular Foundation Models2610.10317v1 · Hao-Run Cai, Si-Yang Liu, Zi-Jian Cheng et al.2026 · 0 citationsarXiv
SchemaFill: Efficient LLM Tool Calling via Slot-Parallel Speculative Decoding2610.07086v1 · Zhi-Kai Chen, Song-Yan Li, De-Chuan Zhan et al.2026 · 0 citationsarXiv
Selecting and Distilling Cross-Label Models.42247535 · Lu, Su, Ye, Han-Jia, Zhan, De-Chuan2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(10):12661-12678
Consistent Plan-Act for Long-Horizon Agentic Tasks2609.38891v1 · Heng-Zhuang Li, Yi-Kai Zhang, Yu Wang et al.2026 · 0 citationsarXiv
Token-Disentangled Latent Test-Time Scaling for Vision-Language Reasoning2609.35228v1 · Hao-Xuan Ma, Yihao Liu, Yutao Sun et al.2026 · 0 citationsarXiv
CausalArena: Benchmarking Causal Discovery in the Foundation Model Era2609.11897v1 · Zi-Rong Li, Si-Yang Liu, Tian-Zuo Wang et al.2026 · 0 citationsarXiv
Dual-Latent Memory Routing for Vision-Language Reasoning2609.05539v1 · Hao-Xuan Ma, Jin-Fei Qi, Yicheng Xiao et al.2026 · 0 citationsarXiv
ResiSpec: Enhancing Multi-Candidate Speculative Sampling via Residual Distribution Shaping2608.24411v1 · Zhi-Kai Chen, Jun-Jie Tao, Wei-Xiang Mao et al.2026 · 0 citationsarXiv
PeakBench: Benchmarking Resource-Aware Tool Invocation in LLM Agents2608.24509v1 · Zhi-Kai Chen, Xu-Xiang Zhong, Song-Yan Li et al.2026 · 0 citationsarXiv
CAST: Game Solvers as Turn-Level Teachers for LLM Agents2607.25308v1 · Yu Wang, Yi-Kai Zhang, Wentao Shi et al.2026 · 0 citationsarXiv
RouteJudge: An Open Platform for Reproducible and Preference-Aware LLM Routing2606.18774v2 · Guannan Lai, Haoran Hu, Han-Jia Ye2026 · 0 citationsarXiv
Dense Supervision, Sparse Updates: On the Sparsity and Geometry of On-Policy Distillation2606.13657v3 · Guo Yu, Wenlin Liu, Yulan Hu et al.2026 · 0 citationsarXiv
From Sampled Outcomes to Capability Distributions: Rethinking Supervision for LLM Routing2606.06924v2 · Guannan Lai, Haoran Hu, Long Chen et al.2026 · 0 citationsarXiv
TabSwift: An Efficient Tabular Foundation Model with Row-Wise Attention2606.07345v1 · Si-Yang Liu, Han-Jia Ye2026 · 0 citationsarXiv
Polaris: Scaling Up Instruction-Guided Image Generation Towards Millions of Personalized Style Needs2606.01858v1 · Zhi-Kai Chen, Jun-Peng Jiang, Jun-Jie Tao et al.2026 · 0 citationsarXiv
Representation Learning for Tabular Data: A Comprehensive Survey.41615982 · Jiang, Jun-Peng, Liu, Si-Yang, Cai, Hao-Run et al.2026 · 24 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(6):6488-6508
TabCausal: Pretraining Across Causal Environments for Tabular Causal Discovery2605.31156v2 · Zi-Rong Li, Si-Yang Liu, Tian-Zuo Wang et al.2026 · 0 citationsarXiv
Cross-Sample Relational Fusion: Unifying Domain Generalization and Class-Incremental Learning2605.08839v1 · Zhen-Hao Xie, Yan Wang, Hao Sun et al.2026 · 0 citationsarXiv
Non-Parametric Rehearsal Learning via Conditional Mean Embeddings2605.08999v1 · Wen-Bo Du, Tian-Zuo Wang, Han-Jia Ye et al.2026 · 0 citationsarXiv
TopBench: A Benchmark for Implicit Predictive Reasoning in Tabular Question Answering2604.28076v2 · An-Yang Ji, Jun-Peng Jiang, De-Chuan Zhan et al.2026 · 0 citationsarXiv
The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation2603.21928v1 · Guannan Lai, Da-Wei Zhou, Zhenguo Li et al.2026 · 0 citationsarXiv
: Generalist Value Model as a Prior for Sparse RL Rollouts2603.10848v1 · Yi-Kai Zhang, Yueqing Sun, Hongyan Hao et al.2026 · 0 citationsarXiv
When Routing Collapses: On the Degenerate Convergence of LLM Routers2602.03478v1 · Guannan Lai, Han-Jia Ye2026 · 0 citationsarXiv
: A Generalist Value Model for Any Policy at State Zero2602.03584v2 · Yi-Kai Zhang, Zhiyuan Yao, Hongyan Hao et al.2026 · 0 citationsarXiv
SAME: Stabilized Mixture-of-Experts for Multimodal Continual Instruction Tuning2602.01990v3 · Zhen-Hao Xie, Jun-Tao Tang, Yu-Cheng Shi et al.2026 · 0 citationsarXiv
MMR-Bench: A Comprehensive Benchmark for Multimodal LLM Routing2601.17814v1 · Haoxuan Ma, Guannan Lai, Han-Jia Ye2026 · 0 citationsarXiv
Feature-aware Modulation for Learning from Temporal Tabular Data2512.03678v1 · Hao-Run Cai, Han-Jia Ye2025 · 0 citationsarXiv
BOFA: Bridge-Layer Orthogonal Low-Rank Fusion for CLIP-Based Class-Incremental Learning2511.11421v2 · Lan Li, Tao Hu, Da-Wei Zhou et al.2025 · 2 citationsProceedings of the AAAI Conference on Artificial Intelligence, 40(27): 22967-22975, 2026
Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation2510.25739v1 · Zhi-Kai Chen, Jun-Peng Jiang, Han-Jia Ye et al.2025 · 1 citationarXiv
One-Embedding-Fits-All: Efficient Zero-Shot Time Series Forecasting by a Model Zoo2509.04208v2 · Hao-Nan Shi, Ting-Ji Huang, Lu Han et al.2025 · 0 citationsarXiv
Integrating Task-Specific and Universal Adapters for Pre-Trained Model-based Class-Incremental Learning2508.08165v1 · Yan Wang, Da-Wei Zhou, Han-Jia Ye2025 · 10 citationsarXiv
Addressing Imbalanced Domain-Incremental Learning through Dual-Balance Collaborative Experts2507.07100v1 · Lan Li, Da-Wei Zhou, Han-Jia Ye et al.2025 · 0 citationsarXiv
UniCA: Unified Covariate Adaptation for Time Series Foundation Model2506.22039v2 · Lu Han, Yu Liu, Lan Li et al.2025 · 0 citationsarXiv
Multimodal Tabular Reasoning with Privileged Structured Information2506.04088v1 · Jun-Peng Jiang, Yu Xia, Hai-Long Sun et al.2025 · 0 citationsarXiv
Make Still Further Progress: Chain of Thoughts for Tabular Data Leaderboard2505.13421v1 · Si-Yang Liu, Qile Zhou, Han-Jia Ye2025 · 0 citationsarXiv
Learning Without Forgetting for Vision-Language Models.40184303 · Zhou, Da-Wei, Zhang, Yuanhan, Wang, Yan et al.2025 · 57 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(6):4489-4504
Generalized Conditional Similarity Learning via Semantic Matching.40184301 · Shi, Yi, Li, Rui-Xiang, Gan, Le et al.2025 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(5):3847-3862
Efficient Evaluation of Large Language Models via Collaborative Filtering2504.08781v1 · Xu-Xiang Zhong, Chao Yi, Han-Jia Ye2025 · 0 citationsarXiv
Model Assembly Learning with Heterogeneous Layer Weight Merging2503.21657v1 · Yi-Kai Zhang, Jin Wang, Xu-Xiang Zhong et al.2025 · 0 citationsarXiv
Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning2503.13360v2 · Hai-Long Sun, Zhun Sun, Houwen Peng et al.2025 · 5 citationsarXiv
External Knowledge Injection for CLIP-Based Class-Incremental Learning2503.08510v2 · Da-Wei Zhou, Kai-Wen Li, Jingyi Ning et al.2025 · 16 citationsarXiv
Research on the development of image-based Deep Learning (DL) model for serum quality recognition.40042089 · Man, Dongliang, Yang, Xiaotao, Du, Wei et al.2026 · 3 citationsClinical chemistry and laboratory medicine. 2025;63(7):e179-e183
SeqFusion: Sequential Fusion of Pre-Trained Models for Zero-Shot Time-Series Forecasting2503.02836v1 · Ting-Ji Huang, Xu-Yang Chen, Han-Jia Ye2025 · 0 citationsarXiv
Task-Agnostic Guided Feature Expansion for Class-Incremental Learning2503.00823v1 · Bowen Zheng, Da-Wei Zhou, Han-Jia Ye et al.2025 · 21 citationsarXiv
Understanding the Limits of Deep Tabular Methods with Temporal Shift2502.20260v2 · Hao-Run Cai, Han-Jia Ye2025 · 0 citationsarXiv
Capability Instruction Tuning: A New Paradigm for Dynamic LLM Routing2502.17282v1 · Yi-Kai Zhang, De-Chuan Zhan, Han-Jia Ye2025 · 0 citationsarXiv
A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities2502.17361v2 · Han-Jia Ye, Si-Yang Liu, Wei-Lun Chao2025 · 6 citationsarXiv
Career total: 154 works. 111 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.