Profiles2021-2026
Dacheng Tao
Nanyang Technological University
150Papers
133Last author
262Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers150
- Odysseus: Jailbreaking Commercial Multimodal LLM-integrated Systems via Dual SteganographyAuthor 5 of 5NDSS 2026 · 9 citations
- PromptCOS: Towards Content-Only System Prompt Copyright Auditing for LLMsAuthor 8 of 9S&P 2026 · 5 citations
- SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMsAuthor 9 of 9AAAI 2026 · 5 citations
- GlyphPrinter: Region-Grouped Direct Preference Optimization for Glyph-Accurate Visual Text RenderingAuthor 4 of 4CVPR 2026 · 4 citations
- Free-Form Scene Editor: Enabling Multi-Round Object Manipulation Like in a 3D EngineAuthor 4 of 4AAAI 2026 · 2 citations
- Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive SmoothingAuthor 5 of 5ICML 2026 · 1 citation
- PSDesigner: Automated Graphic Design with a Human-Like Creative WorkflowAuthor 5 of 5CVPR 2026 · 1 citation
- The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality CheckAuthor 5 of 5ACL 2026 · 1 citation
- Bridging the Tokenizer Gap: Semantics and Distribution-aware Knowledge Transfer for Unbiased Cross-Tokenizer DistillationAuthor 7 of 7AAAI 2026
- CoFact: Conformal Factuality Guarantees for Language Models under Covariate ShiftAuthor 5 of 5ICLR 2026
- Distillation Traps and Guards: A Calibration Knob for LLM DistillabilityAuthor 4 of 4ACL 2026
- Heuristic-inspired Reasoning Priors Facilitate Data-Efficient Referring Object DetectionAuthor 4 of 4CVPR 2026
- MedCoG: Maximizing LLM Inference Density in Medical Reasoning via Meta-Cognitive RegulationAuthor 5 of 5ICML 2026
- Offline Behavioral Data SelectionAuthor 3 of 3KDD 2026
- OSCS: Online Selection with Provable FAR Control for LLM SafetyAuthor 4 of 4ICML 2026
- Reasoning-Guided Exploration for Online DPOAuthor 6 of 6ACL Findings 2026
- SAFER: A Controllable Safeguard for LLMs against Backdoor AttacksAuthor 4 of 4ACL Findings 2026
- SkillCODER: Towards Auditing and Attribution of Copyright Infringement in LLM Agent SkillsAuthor 7 of 8CCS 2026
- The State of Reinforcement Finetuning for Transformer-based AgentsAuthor 7 of 7ICLR 2026
- Time-Frequency Token Advantage Clipping for Training Efficient Large Reasoning ModelAuthor 9 of 9AAAI 2026
- Towards a Theoretical Understanding of In-context Learning: Stability and Non-I.I.D GeneralisationAuthor 7 of 7ICLR 2026
- VeriLoRA: Fine-Tuning Large Language Models with Verifiable Security via Zero-Knowledge ProofsAuthor 6 of 6NDSS 2026
- SeRL: Self-play Reinforcement Learning for Large Language Models with Limited DataAuthor 8 of 8NeurIPS 2025 · 53 citations
- Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM ReasoningAuthor 8 of 8NeurIPS 2025 · 45 citations
- Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum TuningAuthor 6 of 6AAAI 2025 · 19 citations
- Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data SchedulerAuthor 5 of 5NeurIPS 2025 · 16 citations
- CopyrightShield: Enhancing Diffusion Model Security Against Copyright Infringement AttacksAuthor 4 of 4ICCV 2025 · 8 citations
- Merging on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model MergingAuthor 8 of 8NeurIPS 2025 · 8 citations
- Value-Guided Decision Transformer: A Unified Reinforcement Learning Framework for Online and Offline SettingsAuthor 8 of 8NeurIPS 2025 · 6 citations
- On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene SegmentationAuthor 3 of 3NeurIPS 2025 · 5 citations
Showing the 30 most recent indexed papers.
