Tao LIN

Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning ACL 2026 GIFT: Unlocking Full Potential of Labels in Distilled Dataset at Near-zero Cost ICLR 2025 Enhancing Clustered Federated Learning: Integration of Strategies and Improved Methodologies ICLR 2025 ELICIT: LLM Augmentation Via External In-context Capability ICLR 2025 CollabEdit: Towards Non-destructive Collaborative Knowledge Editing ICLR 2025 PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration ICLR 2025 Generalized Principal-Agent Problem with a Learning Agent ICLR 2025 Learn How to Query from Unlabeled Data Streams in Federated Learning AAAI 2025 CPath-Omni: A Unified Multimodal Foundation Model for Patch and Whole Slide Image Analysis in Computational Pathology CVPR 2025 DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference ICLR 2025 IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents EMNLP 2025 Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models ICLR 2025 STI-Bench: Are MLLMs Ready for Precise Spatial-Temporal World Understanding? ICCV 2025 Client2Vec: Improving Federated Learning by Distribution Shifts Aware Client Indexing ICCV 2025 Out-of-Bounding-Box Triggers: A Stealthy Approach to Cheat Object Detectors ECCV 2024 FedRC: Tackling Diverse Distribution Shifts Challenge in Federated Learning by Robust Clustering ICML 2024 Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning ICLR 2024 Towards Robust Multi-Modal Reasoning via Model Selection ICLR 2024 PathMMU: A Massive Multimodal Expert-Level Benchmark for Understanding and Reasoning in Pathology ECCV 2024 On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm CVPR 2024 Learning Thresholds with Latent Values and Censored Feedback ICLR 2024 Multi-Sender Persuasion: A Computational Perspective ICML 2024 Efficiency for Free: Ideal Data Are Transportable Representations NIPS 2024 Bias Detection via Signaling NIPS 2024 Cooperative Hardware-Prompt Learning for Snapshot Compressive Imaging NIPS 2024 User-Creator Feature Polarization in Recommender Systems with Dual Influence NIPS 2024 Revisiting Weighted Aggregation in Federated Learning with Neural Networks ICML 2023 Sample Complexity of Forecast Aggregation NIPS 2023 DELTA: Diverse Client Sampling for Fasting Federated Learning NIPS 2023 From Monopoly to Competition: Optimal Contests Prevail AAAI 2023 No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier ICCV 2023 Test-Time Robust Personalization for Federated Learning ICLR 2023 FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction ICML 2023 Online Restless Bandits with Unobserved States ICML 2023 On Pitfalls of Test-Time Adaptation ICML 2023 Prediction with Incomplete Data under Agnostic Mask Distribution Shift IJCAI 2023 Adversarial training for high-stakes reliability NIPS 2022 How Many Representatives Do We Need? The Optimal Size of a Congress Voting on Binary Issues AAAI 2022 An Improved Analysis of Gradient Tracking for Decentralized Machine Learning NIPS 2021 Consensus Control for Decentralized Deep Learning ICML 2021 Quasi-global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data ICML 2021 RelaySum for Decentralized Deep Learning on Heterogeneous Data NIPS 2021 Extrapolation for Large-batch Training in Deep Learning ICML 2020 Masking as an Efficient Alternative to Finetuning for Pretrained Language Models EMNLP 2020 A Game-Theoretic Analysis of the Empirical Revenue Maximization Algorithm with Endogenous Sampling NIPS 2020 Don't Use Large Mini-batches, Use Local SGD ICLR 2020 On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them NIPS 2020 Dynamic Model Pruning with Feedback ICLR 2020 Ensemble Distillation for Robust Model Fusion in Federated Learning NIPS 2020 Learning Utilities and Equilibria in Non-Truthful Auctions NIPS 2020 Exploring interpretable LSTM neural networks over multi-variable data ICML 2019 Training DNNs with Hybrid Block Floating Point NIPS 2018 Hybrid Neural Networks for Learning the Trend in Time Series IJCAI 2017