Lune

Profiles2024-2026

Dacheng Tao

Nanyang Technological University

39Papers
31Last author
86Unique co-authors
0First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers39

  1. A Simple "Motivation" Can Enhance Reinforcement Finetuning of Large Reasoning ModelsAuthor 9 of 9ICLR 2026 · 6 citations
  2. Better, Faster: Harnessing Self-Improvement in Large Reasoning ModelsAuthor 6 of 6ICML 2026 · 3 citations
  3. AQER: A Scalable and Efficient Data Loader for Digital Quantum ComputersAuthor 5 of 5ICLR 2026 · 2 citations
  4. Language-based Trial and Error Falls Behind in the Era of ExperienceAuthor 10 of 10ICML 2026 · 2 citations
  5. What Makes Value Learning Efficient in Residual Reinforcement Learning?Author 6 of 6ICML 2026 · 2 citations
  6. MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMsAuthor 6 of 6ICLR 2026 · 1 citation
  7. CogniTrust: Cognitive Memory-Driven Verifiable Supervision for Robust HashingAuthor 11 of 12AAAI 2026
  8. Controllable Contamination Detection for Reliable LLM Evaluation with Statistical GuaranteesAuthor 11 of 11ACL 2026
  9. Convergent Differential Privacy Analysis for General Federated LearningAuthor 4 of 4ICLR 2026
  10. Lightning Fast Caching-based Parallel Denoising Prediction for Accelerating Talking Head GenerationAuthor 4 of 4AAAI 2026
  11. Singular Proxies for Adaptive Caching in Diffusion Language ModelsAuthor 7 of 7ICML 2026
  12. TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series ForecastingAuthor 5 of 5ICML 2026
  13. VORTA: Efficient Video Diffusion via Routing Sparse AttentionAuthor 7 of 7NeurIPS 2025 · 25 citations
  14. T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak AttacksAuthor 7 of 8NeurIPS 2025 · 18 citations
  15. SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual GroundingAuthor 7 of 7NeurIPS 2025 · 13 citations
  16. FreDF: Learning to Forecast in the Frequency DomainAuthor 10 of 10ICLR 2025 · 7 citations
  17. Effective Policy Learning for Multi-Agent Online Coordination Beyond Submodular ObjectivesAuthor 8 of 8NeurIPS 2025 · 4 citations
  18. D2GS: Dense Depth Regularization for LiDAR-free Urban Scene ReconstructionAuthor 6 of 7NeurIPS 2025 · 3 citations
  19. AiDE-Q: Synthetic Labeled Datasets Can Enhance Learning Models for Quantum Property EstimationAuthor 8 of 8NeurIPS 2025 · 1 citation
  20. SEGA: Shaping Semantic Geometry for Robust Hashing under Noisy SupervisionAuthor 8 of 9NeurIPS 2025 · 1 citation
  21. AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and RestorationAuthor 5 of 5ICML 2025
  22. Combatting Dimensional Collapse in LLM Pre-Training Data via Submodular File SelectionAuthor 7 of 8ICLR 2025
  23. ICLShield: Exploring and Mitigating In-Context Learning Backdoor AttacksAuthor 4 of 4ICML 2025
  24. Near-Optimal Online Learning for Multi-Agent Submodular Coordination: Tight Approximation and Communication EfficiencyAuthor 5 of 5ICLR 2025
  25. Network Sparsity Unlocks the Scaling Potential of Deep Reinforcement LearningAuthor 6 of 6ICML 2025
  26. Revisiting Backdoor Attacks against Large Vision-Language Models from Domain ShiftAuthor 8 of 8CVPR 2025
  27. One For All: Towards Training One Graph Model For All Classification TasksAuthor 5 of 7ICLR 2024 · 253 citations
  28. Parameter-Efficient Multi-Task Model Fusion with Partial LinearizationAuthor 8 of 8ICLR 2024 · 63 citations
  29. Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training StagesAuthor 9 of 9ICLR 2024 · 32 citations
  30. Revisiting Catastrophic Forgetting in Large Language Model TuningAuthor 4 of 4EMNLP Findings 2024 · 26 citations

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines