Skip to content
conftrace_

Yongyuan Liang

15 papers · 2022–2026 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+7 more ↓ πŸ—ΊοΈ Taxonomy Completionist (27) 🌍 Conference Polyglot Β· Silver πŸŒ‰ Interdisciplinary Bridge Β· Silver 🀝 Dynamic Duo (12) πŸ† Grand Slam
🀝 Dynamic Duo (12) πŸ—ƒοΈ Keyword Collector (81) πŸ”₯ Unstoppable Β· Bronze ❓ The Questioner (2) ⚑ Prolific Year Β· Productive 🌈 Renaissance Researcher (5) πŸ’Ž Century Club Β· Bronze

Venues

ICLR (7) CVPR (3) ICML (2) NeurIPS (2) AAAI (1)

Top co-authors

Furong Huang (12) Ruijie Zheng (9) Huazhe Xu (5) Yanchao Sun (5) Xiangyu Liu (3) Hal Daume III (3) Xiyao Wang (2) Jianwei Yang (2) Yu Luo (2) Guowei Xu (2)

Research topics

Artificial Intelligence (13) Core AI (13) Reinforcement Learning (8) Methods (7) Machine Learning (5) Learning Types Β· Machine Learning (5) Deep Learning (3) Robotics (3) Capabilities (3) Applications Β· Reinforcement Learning (2) Computer Science (1) Computer Vision (1) Application Areas (1) Applications Β· Computer Science (1) Learning Types Β· Deep Learning (1)

Keywords

reinforcement learning (4) continuous control (4) robot manipulation (3) adversarial perturbation (3) adversarial attack (2) policy network (2) few-shot learning (1) adversarial robustness (1) contrastive learning (1) robotic manipulation (1) game theory (1) direct preference optimization (1) in-context learning (1) multimodal learning (1) policy optimization (1) sample efficiency (1) adversarial training (1) visual grounding (1) visual reinforcement learning (1) data poisoning (1)

Papers

TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos CVPR 2026 WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation CVPR 2026 Is Poisoning a Real Threat to DPO? Maybe More So Than You Think AAAI 2025 Magma: A Foundation Model for Multimodal AI Agents CVPR 2025 Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Datasets ICLR 2025 TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies ICLR 2025 ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization ICML 2024 Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies ICLR 2024 DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization ICLR 2024 Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations ICLR 2024 Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion NeurIPS 2024 Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss ICML 2024 Certifiably Robust Policy Learning against Adversarial Multi-Agent Communication ICLR 2023 Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning NeurIPS 2022 Who Is the Strongest Enemy? Towards Optimal and Efficient Evasion Attacks in Deep RL ICLR 2022