20 citations · 44 across the 14 of their papers we have counts for
7 papers · 1 filter
-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation
Fangzhi Xu, Hang Yan, Chang Ma +4
Inference-time optimization scales computation to derive deliberate reasoning steps for effective performance. While previous search-based strategies address the short-sightedness…
BioMaze: Benchmarking and Enhancing Large Language Models for Biological Pathway Reasoning
Haiteng Zhao, Chang Ma, Fangzhi Xu +2
The applications of large language models (LLMs) in various biological domains have been explored recently, but their reasoning ability in complex biological systems, such as pathw…
Instruction-Based Molecular Graph Generation with Unified Text-Graph Diffusion Model
Yuran Xiang, Haiteng Zhao, Chang Ma +1
Recent advancements in computational chemistry have increasingly focused on synthesizing molecules based on textual instructions. Integrating graph generation with these instructio…
GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning
Haiteng Zhao, Shengchao Liu, Chang Ma +5
Molecule property prediction has gained significant attention in recent years. The main bottleneck is the label insufficiency caused by expensive lab experiments. In order to allev…
Are More Layers Beneficial to Graph Transformers?
Haiteng Zhao, Shuming Ma, Dongdong Zhang +2
Despite that going deep has proven successful in many neural architectures, the existing graph transformers are relatively shallow. In this work, we explore whether more layers are…
Certified Robustness Against Natural Language Attacks by Causal Intervention
Haiteng Zhao, Chang Ma, Xinshuai Dong +3
Deep learning models have achieved great success in many fields, yet they are vulnerable to adversarial examples. This paper follows a causal perspective to look into the adversari…
Domain Adaptation via Maximizing Surrogate Mutual Information
Haiteng Zhao, Chang Ma, Qinyu Chen +1
Unsupervised domain adaptation (UDA) aims to predict unlabeled data from target domain with access to labeled data from the source domain. In this work, we propose a novel framewor…