Lattice AI Research

Research focus

Computer Vision (2)Multimodal Models (2)Inference & Quantization (1)Robotics & Embodied AI (1)

Frequent co-authors

Yayun He (2)Jianzong Wang (2)Chuhan Liu (1)Chuhang Liu (1)

Papers (2)

Apr 7, 2026

Chuhan Liu +5Apr 7, 2026

VLA-InfoEntropy: A Training-Free Vision-Attention Information Entropy Approach for Vision-Language-Action Models Inference Acceleration and Success

Achieve faster VLA inference without retraining by using image and attention entropy to dynamically focus on the most relevant visual and textual information.

Chuhan Liu, Chuhang Liu, Yayun He +3

Computer Vision Inference & Quantization Multimodal Models

Mar 16, 2026

Yayun He +6Mar 16, 2026

Confusion-Aware In-Context-Learning for Vision-Language Models in Robotic Manipulation

VLMs stumble with confusable objects in robotic manipulation, but CAICL guides them to focus on the right features, boosting success rates by focusing on task-relevant features.

Yayun He, Zuheng Kang, Botao Zhao +4

Computer Vision Multimodal Models Robotics & Embodied AI

Search

Zuheng Kang

Research focus

Frequent co-authors

Papers (2)