Wang, Zihao
64 publications
ICLR
2025
SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-Wise Optimal Budget
ICML
2025
The Illusion of Role Separation: Hidden Shortcuts in LLM Role Learning (and How to Fix Them)
AAAI
2024
A User-Friendly Framework for Generating Model-Preferred Prompts in Text-to-Image Synthesis
NeurIPS
2024
OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents
NeurIPSW
2024
RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning and Verification in Long-Horizon Generation
NeurIPS
2023
Describe, Explain, Plan and Select: Interactive Planning with LLMs Enables Open-World Multi-Task Agents
NeurIPSW
2023
JARVIS-1: Open-World Multi-Task Agents with Memory-Augmented Multimodal Language Models
CVPR
2023
Learning Transformation-Predictive Representations for Detection and Description of Local Features