Profiles2021-2026ORCID 0000-0001-6033-6102
Jun Zhou
Ant Group
32Papers
14Last author
82Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers32
- Thinker: Training LLMs in Hierarchical Thinking for Deep Search via Multi-Turn InteractionAuthor 20 of 20AAAI 2026 · 3 citations
- Adaptive Mixture of Disentangled Experts for Dynamic Graph Out-of-Distribution GeneralizationAuthor 9 of 11ICLR 2026
- Taming the Long Tail: Efficient Item-wise Sharpness-Aware Minimization for LLM-based Recommender SystemsAuthor 7 of 7WWW 2026
- ARGenSeg: Image Segmentation with Autoregressive Image Generation ModelAuthor 7 of 7NeurIPS 2025 · 8 citations
- IceBerg: Debiased Self-Training for Class-Imbalanced Node ClassificationAuthor 7 of 8WWW 2025 · 7 citations
- LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace FusionAuthor 7 of 7ACL 2025 · 5 citations
- Improving Natural Language Understanding for LLMs via Large-Scale Instruction SynthesisAuthor 7 of 7AAAI 2025 · 3 citations
- Learning Causal Transition Matrix for Instance-dependent Label NoiseAuthor 6 of 6AAAI 2025 · 3 citations
- BOSE: A Systematic Evaluation Method Optimized for Base ModelsAuthor 7 of 7ACL Findings 2025 · 1 citation
- LLMOPT: Learning to Define and Solve General Optimization Problems from ScratchAuthor 5 of 7ICLR 2025
- MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language ModelsAuthor 5 of 7ICML 2025
- RED: Unleashing Token-Level Rewards from Holistic Feedback via Reward RedistributionAuthor 6 of 7EMNLP 2025
- Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction TuningAuthor 5 of 8ICLR 2025
- TimeMixer: Decomposable Multiscale Mixing for Time Series ForecastingAuthor 8 of 8ICLR 2024 · 573 citations
- MDGNN: Multi-Relational Dynamic Graph Neural Network for Comprehensive and Dynamic Stock Investment PredictionAuthor 10 of 10AAAI 2024 · 65 citations
- LLMRG: Improving Recommendations through Large Language Model Reasoning GraphsAuthor 12 of 13AAAI 2024 · 47 citations
- Leave No One Behind: Online Self-Supervised Self-Distillation for Sequential RecommendationAuthor 4 of 6WWW 2024 · 10 citations
- Collaborative Refining for Learning from Inaccurate LabelsAuthor 7 of 9NeurIPS 2024 · 4 citations
- Rethinking Memory and Communication Costs for Efficient Data Parallel Training of Large Language ModelsAuthor 13 of 13NeurIPS 2024 · 4 citations
- Optimizing Language Models with Fair and Stable Reward Composition in Reinforcement LearningAuthor 7 of 7EMNLP 2024 · 2 citations
- Self-cognitive Denoising in the Presence of Multiple Noisy Label SourcesAuthor 5 of 5ICML 2024 · 2 citations
- Language Models Can Improve Event Prediction by Few-Shot Abductive ReasoningAuthor 6 of 9NeurIPS 2023 · 95 citations
- Unleashing the Power of Graph Data Augmentation on Covariate Distribution ShiftAuthor 6 of 8NeurIPS 2023 · 63 citations
- Financial Default Prediction via Motif-preserving Graph Neural Network with Curriculum LearningAuthor 3 of 6KDD 2023 · 12 citations
- Graph Neural Network with Two Uplift Estimators for Label-Scarcity Individual Uplift ModelingAuthor 7 of 8WWW 2023 · 3 citations
- Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork PromptsAuthor 5 of 7EMNLP Findings 2023 · 2 citations
- FAST: a Fused and Accurate Shrinkage Tree for Heterogeneous Treatment Effects EstimationAuthor 6 of 6NeurIPS 2023 · 1 citation
- Difference-in-Differences Meets Tree-based Methods: Heterogeneous Treatment Effects Estimation with Unmeasured ConfoundingAuthor 6 of 6ICML 2023
- SAIL: Self-Augmented Graph Contrastive LearningAuthor 4 of 7AAAI 2022 · 47 citations
- Debiased Causal Tree: Heterogeneous Treatment Effects Estimation with Unmeasured ConfoundingAuthor 8 of 9NeurIPS 2022 · 12 citations
Showing the 30 most recent indexed papers.
