Lattice AI Research

Research focus

Multimodal Models (2)Red-Teaming & Adversarial Robustness (1)Robotics & Embodied AI (1)Reasoning & Chain-of-Thought (1)

Frequent co-authors

Pinhan Fu (1)Xianda Guo (1)Xuetao Li (1)Wenke Huang (1)

Papers (2)

Jul 14, 2026

Jul 14, 2026·also D-Robotics, NTU

TrustVLA: Mechanism-Guided Inference-Time Defense Against Vision-Language-Action Backdoors

TrustVLA can detect and recover from VLA backdoors with minimal clean data, all while preserving normal task performance.

Pinhan Fu, Xianda Guo, Xuetao Li +5

Multimodal Models Red-Teaming & Adversarial Robustness Robotics & Embodied AI

Jul 9, 2026

Yiyang Fang +9Jul 9, 2026

Switch-Reasoner: Learn When to Think in Multitask Mixtures via Reinforcement Learning

Switch-Reasoner reveals that adaptive reasoning selection can enhance MLLM performance by reducing unnecessary cognitive load while maintaining accuracy.

Yiyang Fang, Pei Fu, Jinjie Li +7

Multimodal Models Reasoning & Chain-of-Thought RLHF & Preference Learning

Mang Ye

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)

Search

Mang Ye

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)