Zhenhua Liu
- Papers
- 7
Cite
Notes
Only stored in your browser.
7papers
Authored papers
7AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios
arXiv 2026
Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE
arXiv 2025
Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers
arXiv 2025
Nearly Lossless Adaptive Bit Switching
arXiv 2025
Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting
arXiv 2024
Learning to Refuse: Towards Mitigating Privacy Risks in LLMs
arXiv 2024
Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation
ICCV 2023 1
Affiliations
No known affiliations.
Frequent co-authors
10from 7 papers