$\mathbb{USCD}$: Improving Code Generation of LLMs by Uncertainty-Aware Selective Contrastive Decoding

Large language models (LLMs) have shown remarkable capabilities in code generation. However, the effects of hallucinations (e.g., output noise) make it particularly challenging for LLMs to generate high-quality code in one pass. In this work, we propose a simple and effective \textbf{u}ncertainty-aware \textbf{s}elective \textbf{c}ontrastive \textbf{d}ecoding ($\mathbb{USCD}$) mechanism to improve the quality of one-pass code generation in LLMs and reduce the impact of output noise. To be specific, we first elaborately designed a negative prompt (namely lame prompt) to output noise by removing input-output examples from the standard few-shot prompt. Our preliminary study shows that the Jensen-Shannon divergence (JS divergence) between token distribution uncertainty and the output noise is relatively low (approximately $0.25$), indicating their high relevance. Then, we selectively eliminate output noise induced by lame prompts based on the uncertainty of the prediction distribution from the standard prompt. Notably, our proposed plug-and-play mechanism is an inference-only method, enjoying appealing flexibility. Extensive experiments on widely used benchmarks, e.g., HumanEval, MBPP, and MultiPL-E, upon several LLMs (i.e., Inocder-6b, CodeLlama-7b, WizardCoder-15b, StarCoder, and Llama2-7b), demonstrate that our proposed USCD significantly improves one-pass code generation, with an average \textit{pass@$1$} scores increase of 16.59\%. We will release code and data on GitHub.

MTGA: Multi-view Temporal Granularity aligned Aggregation for Event-based Lip-reading

Lip-reading is to utilize the visual information of the speaker's lip movements to recognize words and sentences. Existing event-based lip-reading solutions integrate different frame rate branches to learn spatio-temporal features of varying granularities. However, aggregating events into event frames inevitably leads to the loss of fine-grained temporal information within frames. To remedy this drawback, we propose a novel framework termed Multi-view Temporal Granularity aligned Aggregation (MTGA). Specifically, we first present a novel event representation method, namely time-segmented voxel graph list, where the most significant local voxels are temporally connected into a graph list. Then we design a spatio-temporal fusion module based on temporal granularity alignment, where the global spatial features extracted from event frames, together with the local relative spatial and temporal features contained in voxel graph list are effectively aligned and integrated. Finally, we design a temporal aggregation module that incorporates positional encoding, which enables the capture of local absolute spatial and global temporal information. Experiments demonstrate that our method outperforms both the event-based and video-based lip-reading counterparts. Our code will be publicly available.

A Protein Structure Prediction Approach Leveraging Transformer and CNN Integration

Proteins are essential for life, and their structure determines their function. The protein secondary structure is formed by the folding of the protein primary structure, and the protein tertiary structure is formed by the bending and folding of the secondary structure. Therefore, the study of protein secondary structure is very helpful to the overall understanding of protein structure. Although the accuracy of protein secondary structure prediction has continuously improved with the development of machine learning and deep learning, progress in the field of protein structure prediction, unfortunately, remains insufficient to meet the large demand for protein information. Therefore, based on the advantages of deep learning-based methods in feature extraction and learning ability, this paper adopts a two-dimensional fusion deep neural network model, DstruCCN, which uses Convolutional Neural Networks (CCN) and a supervised Transformer protein language model for single-sequence protein structure prediction. The training features of the two are combined to predict the protein Transformer binding site matrix, and then the three-dimensional structure is reconstructed using energy minimization.

Construction and application of artificial intelligence crowdsourcing map based on multi-track GPS data

In recent years, the rapid development of high-precision map technology combined with artificial intelligence has ushered in a new development opportunity in the field of intelligent vehicles. High-precision map technology is an important guarantee for intelligent vehicles to achieve autonomous driving. However, due to the lack of research on high-precision map technology, it is difficult to rationally use this technology in the field of intelligent vehicles. Therefore, relevant researchers studied a fast and effective algorithm to generate high-precision GPS data from a large number of low-precision GPS trajectory data fusion, and generated several key data points to simplify the description of GPS trajectory, and realized the "crowdsourced update" model based on a large number of social vehicles for map data collection came into being. This kind of algorithm has the important significance to improve the data accuracy, reduce the measurement cost and reduce the data storage space. On this basis, this paper analyzes the implementation form of crowdsourcing map, so as to improve the various information data in the high-precision map according to the actual situation, and promote the high-precision map can be reasonably applied to the intelligent car.

Rethinking the Structure of Stochastic Gradients: Empirical and Statistical Evidence

Stochastic gradients closely relate to both optimization and generalization of deep neural networks (DNNs). Some works attempted to explain the success of stochastic optimization for deep learning by the arguably heavy-tail properties of gradient noise, while other works presented theoretical and empirical evidence against the heavy-tail hypothesis on gradient noise. Unfortunately, formal statistical tests for analyzing the structure and heavy tails of stochastic gradients in deep learning are still under-explored. In this paper, we mainly make two contributions. First, we conduct formal statistical tests on the distribution of stochastic gradients and gradient noise across both parameters and iterations. Our statistical tests reveal that dimension-wise gradients usually exhibit power-law heavy tails, while iteration-wise gradients and stochastic gradient noise caused by minibatch training usually do not exhibit power-law heavy tails. Second, we further discover that the covariance spectra of stochastic gradients have the power-law structures in deep learning. While previous papers believed that the anisotropic structure of stochastic gradients matters to deep learning, they did not expect the gradient covariance can have such an elegant mathematical structure. Our work challenges the existing belief and provides novel insights on the structure of stochastic gradients in deep learning.

Sparse Double Descent: Where Network Pruning Aggravates Overfitting

People usually believe that network pruning not only reduces the computational cost of deep networks, but also prevents overfitting by decreasing model capacity. However, our work surprisingly discovers that network pruning sometimes even aggravates overfitting. We report an unexpected sparse double descent phenomenon that, as we increase model sparsity via network pruning, test performance first gets worse (due to overfitting), then gets better (due to relieved overfitting), and gets worse at last (due to forgetting useful information). While recent studies focused on the deep double descent with respect to model overparameterization, they failed to recognize that sparsity may also cause double descent. In this paper, we have three main contributions. First, we report the novel sparse double descent phenomenon through extensive experiments. Second, for this phenomenon, we propose a novel learning distance interpretation that the curve of $\ell_{2}$ learning distance of sparse models (from initialized parameters to final parameters) may correlate with the sparse double descent curve well and reflect generalization better than minima flatness. Third, in the context of sparse double descent, a winning ticket in the lottery ticket hypothesis surprisingly may not always win.