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