Yongyuan Liang
- Papers
- 9
Cite
Notes
Only stored in your browser.
Authored papers
9Magma: A Foundation Model for Multimodal AI Agents
CVPR 2025 1
WEAVE: Unleashing and Benchmarking the In-context Interleaved Comprehension and Generation
arXiv 2025
MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning
arXiv 2025
ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs
arXiv 2025
ACE : Off-Policy Actor-Critic with Causality-Aware Entropy Regularization
arXiv 2024
Is poisoning a real threat to LLM alignment? Maybe more so than you think
arXiv 2024
Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss
arXiv 2024
Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies
arXiv 2024
DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
arXiv 2023
Affiliations
Frequent co-authors
10from 9 papers