Zhuotao Tian
- Papers
- 16
Cite
Notes
Only stored in your browser.
Authored papers
16FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging
arXiv 2026
Efficient Reasoning with Balanced Thinking
arXiv 2026
Video-ToC: Video Tree-of-Cue Reasoning
arXiv 2026
Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations
arXiv 2025
Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models
arXiv 2025
DeCLIP: Decoupled Learning for Open-Vocabulary Dense Perception
CVPR 2025 1
Mitigating Object Hallucinations via Sentence-Level Early Intervention
ICCV 2025
Omni-DPO: A Dual-Perspective Paradigm for Dynamic Preference Learning of LLMs
arXiv 2025
Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior
arXiv 2025
HiconAgent: History Context-aware Policy Optimization for GUI Agents
arXiv 2025
VisionZip: Longer is Better but Not Necessary in Vision Language Models
CVPR 2025 1
Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs
arXiv 2024
Explore the Potential of CLIP for Training-Free Open Vocabulary Semantic Segmentation
arXiv 2024
Scalable Language Model with Generalized Continual Learning
arXiv 2024
Unified Language-driven Zero-shot Domain Adaptation
CVPR 2024 1
LISA: Reasoning Segmentation via Large Language Model
CVPR 2024 1
Affiliations
Frequent co-authors
10from 16 papers