Hao Wu

Yifei She, Huangxuan Wu

Multimodal Large Language Models (MLLMs) have made significant progress in bridging visual perception with high-level textual reasoning. However, they face a fundamental contradiction: while excelling at complex semantic understanding, these models often fail at basic visual tasks that require precise detail perception. This deficiency primarily stems from the prevalent architectural reliance on a single vision encoder optimized for high-level semantic alignment, which inherently sacrifices the ability to capture fine-grained visual information. To address this issue, we introduce Fusion to Enhance (FtZ), a novel vision tower framework. FtZ moves beyond the single-encoder design by innovatively composing a semantically powerful anchor encoder with a perception-rich augmenting encoder via a lightweight Multi-Head Cross-Attention mechanism. Experimental results demonstrate that on several challenging benchmarks demanding fine-grained visual understanding, such as TextVQA, POPE, MMMU, MME and MM-Vet, our FtZ model significantly outperforms baselines that use only a single encoder or existing feature fusion methods. This work proves that composing heterogeneous expert encoders is an efficient and effective path to overcoming the visual perception bottleneck in current MLLMs, offering a new design paradigm for building next-generation AI systems with stronger perceptual capabilities.

Hao Wu, Jiangchao Yao, Jiajie Wang et al.

Deep neural networks (DNNs) have the capacity to fit extremely noisy labels nonetheless they tend to learn data with clean labels first and then memorize those with noisy labels. We examine this behavior in light of the Shannon entropy of the predictions and demonstrate the low entropy predictions determined by a given threshold are much more reliable as the supervision than the original noisy labels. It also shows the advantage in maintaining more training samples than previous methods. Then, we power this entropy criterion with the Collaborative Label Correction (CLC) framework to further avoid undesired local minimums of the single network. A range of experiments have been conducted on multiple benchmarks with both synthetic and real-world settings. Extensive results indicate that our CLC outperforms several state-of-the-art methods.

Xu Zhao, Zihao Wang, Hao Wu et al.

Recently unsupervised Bilingual Lexicon Induction (BLI) without any parallel corpus has attracted much research interest. One of the crucial parts in methods for the BLI task is the matching procedure. Previous works impose a too strong constraint on the matching and lead to many counterintuitive translation pairings. Thus, We propose a relaxed matching procedure to find a more precise matching between two languages. We also find that aligning source and target language embedding space bidirectionally will bring significant improvement. We follow the previous iterative framework to conduct experiments. Results on standard benchmark demonstrate the effectiveness of our proposed method, which substantially outperforms previous unsupervised methods.

Hao Wu, Kristina Lerman

We propose a neural embedding algorithm called Network Vector, which learns distributed representations of nodes and the entire networks simultaneously. By embedding networks in a low-dimensional space, the algorithm allows us to compare networks in terms of structural similarity and to solve outstanding predictive problems. Unlike alternative approaches that focus on node level features, we learn a continuous global vector that captures each node's global context by maximizing the predictive likelihood of random walk paths in the network. Our algorithm is scalable to real world graphs with many nodes. We evaluate our algorithm on datasets from diverse domains, and compare it with state-of-the-art techniques in node classification, role discovery and concept analogy tasks. The empirical results show the effectiveness and the efficiency of our algorithm.

Hao Wu, Jing Chen, Hao Jing et al.

This paper introduces the auxiliary function method (AFM), a novel, fast and simple approach for waveform based earthquake location. From any initial hypocenter and origin time, we can construct the auxiliary function, whose zero set contains the real earthquake hypocenter and the origin time. In most of situations, there are very few elements in this set. The overall computational cost of the AFM is significantly less than that of the iterative methods. According to our numerical tests, even for large noise, the method can still achieve good location results. These allow us to determine the earthquake hypocenter and the origin time extremely fast and accurate.

Hao Wu

It has been quite a long time since AI researchers in the field of computer science stop talking about simulating human intelligence or trying to explain how brain works. Recently, represented by deep learning techniques, the field of machine learning is experiencing unprecedented prosperity and some applications with near human-level performance bring researchers confidence to imply that their approaches are the promising candidate for understanding the mechanism of human brain. However apart from several ancient philological criteria and some imaginary black box tests (Turing test, Chinese room) there is no computational level explanation, definition or criteria about intelligence or any of its components. Base on the common sense that learning ability is one critical component of intelligence and inspect from the viewpoint of mapping relations, this paper presents two laws which explains what is the "learning ability" as we familiar with and under what conditions a mapping relation can be acknowledged as "Learning Model".