Kai Fan

Zhipeng Qian, Pei Zhang, Baosong Yang et al.

This paper introduces AnyTrans, an all-encompassing framework for the task-Translate AnyText in the Image (TATI), which includes multilingual text translation and text fusion within images. Our framework leverages the strengths of large-scale models, such as Large Language Models (LLMs) and text-guided diffusion models, to incorporate contextual cues from both textual and visual elements during translation. The few-shot learning capability of LLMs allows for the translation of fragmented texts by considering the overall context. Meanwhile, the advanced inpainting and editing abilities of diffusion models make it possible to fuse translated text seamlessly into the original image while preserving its style and realism. Additionally, our framework can be constructed entirely using open-source models and requires no training, making it highly accessible and easily expandable. To encourage advancement in the TATI task, we have meticulously compiled a test dataset called MTIT6, which consists of multilingual text image translation data from six language pairs.

Biao Fu, Minpeng Liao, Kai Fan et al.

When the complete source sentence is provided, Large Language Models (LLMs) perform excellently in offline machine translation even with a simple prompt "Translate the following sentence from [src lang] into [tgt lang]:". However, in many real scenarios, the source tokens arrive in a streaming manner and simultaneous machine translation (SiMT) is required, then the efficiency and performance of decoder-only LLMs are significantly limited by their auto-regressive nature. To enable LLMs to achieve high-quality SiMT as efficiently as offline translation, we propose a novel paradigm that includes constructing supervised fine-tuning (SFT) data for SiMT, along with new training and inference strategies. To replicate the token input/output stream in SiMT, the source and target tokens are rearranged into an interleaved sequence, separated by special tokens according to varying latency requirements. This enables powerful LLMs to learn read and write operations adaptively, based on varying latency prompts, while still maintaining efficient auto-regressive decoding. Experimental results show that, even with limited SFT data, our approach achieves state-of-the-art performance across various SiMT benchmarks, and preserves the original abilities of offline translation. Moreover, our approach generalizes well to document-level SiMT setting without requiring specific fine-tuning, even beyond the offline translation model.

Guoxin Chen, Zile Qiao, Wenqing Wang et al.

Large Reasoning Models (LRMs) often exhibit a tendency for overanalysis in simple tasks, where the models excessively utilize System 2-type, deliberate reasoning, leading to inefficient token generation. Furthermore, these models face challenges in adapting their reasoning capabilities to rapidly changing environments due to the static nature of their pretraining data. To address these issues, advancing Large Language Models (LLMs) for complex reasoning tasks requires innovative approaches that bridge intuitive and deliberate cognitive processes, akin to human cognition's dual-system dynamic. This paper introduces a Multi-Agent System for Deep ReSearch (MARS) enabling seamless integration of System 1's fast, intuitive thinking with System 2's deliberate reasoning within LLMs. MARS strategically integrates multiple external tools, such as Google Search, Google Scholar, and Python Interpreter, to access up-to-date information and execute complex computations, while creating a specialized division of labor where System 1 efficiently processes and summarizes high-volume external information, providing distilled insights that expand System 2's reasoning context without overwhelming its capacity. Furthermore, we propose a multi-agent reinforcement learning framework extending Group Relative Policy Optimization to simultaneously optimize both systems with multi-turn tool interactions, bin-packing optimization, and sample balancing strategies that enhance collaborative efficiency. Extensive experiments demonstrate MARS achieves substantial improvements of 3.86% on the challenging Humanity's Last Exam (HLE) benchmark and an average gain of 8.9% across 7 knowledge-intensive tasks, validating the effectiveness of our dual-system paradigm for complex reasoning in dynamic information environments.

Guoxin Chen, Minpeng Liao, Chengxi Li et al.

Although recent advancements in large language models (LLMs) have significantly improved their performance on various tasks, they still face challenges with complex and symbolic multi-step reasoning, particularly in mathematical reasoning. To bolster the mathematical reasoning capabilities of LLMs, most existing efforts concentrate on seeking assistance from either domain experts or GPT-4 for high-quality process-supervised data, which is not only expensive but also labor-intensive. In our study, we propose an innovative framework, AlphaMath, that bypasses the need for process annotations (from humans or GPTs) by leveraging Monte Carlo Tree Search (MCTS). This framework focuses on unleashing the potential of a well-pretrained LLM to autonomously enhance its mathematical reasoning. Specifically, we integrate a value model with the LLM, automatically generating both process supervision and step-level evaluation signals in MCTS. Furthermore, we propose an efficient inference strategy, step-level beam search, where the value model is crafted to assist the policy model (i.e., LLM) in navigating more effective reasoning paths, rather than solely relying on prior probabilities. The experimental results on both in-domain and out-of-domain datasets demonstrate that even without GPT-4 or human-annotated process supervision, our AlphaMath framework achieves comparable or superior results to previous state-of-the-art methods.

Pei Zhang, Boxing Chen, Niyu Ge et al.

Many document-level neural machine translation (NMT) systems have explored the utility of context-aware architecture, usually requiring an increasing number of parameters and computational complexity. However, few attention is paid to the baseline model. In this paper, we research extensively the pros and cons of the standard transformer in document-level translation, and find that the auto-regressive property can simultaneously bring both the advantage of the consistency and the disadvantage of error accumulation. Therefore, we propose a surprisingly simple long-short term masking self-attention on top of the standard transformer to both effectively capture the long-range dependence and reduce the propagation of errors. We examine our approach on the two publicly available document-level datasets. We can achieve a strong result in BLEU and capture discourse phenomena.

Jiayi Wang, Ke Wang, Niyu Ge et al.

With the advent of neural machine translation, there has been a marked shift towards leveraging and consuming the machine translation results. However, the gap between machine translation systems and human translators needs to be manually closed by post-editing. In this paper, we propose an end-to-end deep learning framework of the quality estimation and automatic post-editing of the machine translation output. Our goal is to provide error correction suggestions and to further relieve the burden of human translators through an interpretable model. To imitate the behavior of human translators, we design three efficient delegation modules -- quality estimation, generative post-editing, and atomic operation post-editing and construct a hierarchical model based on them. We examine this approach with the English--German dataset from WMT 2017 APE shared task and our experimental results can achieve the state-of-the-art performance. We also verify that the certified translators can significantly expedite their post-editing processing with our model in human evaluation.

Shanchan Wu, Kai Fan

Either human annotation or rule based automatic labeling is an effective method to augment data for relation extraction. However, the inevitable wrong labeling problem for example by distant supervision may deteriorate the performance of many existing methods. To address this issue, we introduce a practical end-to-end deep learning framework, including a standard feature extractor and a novel noisy classifier with our proposed doubly transitional mechanism. One transition is basically parameterized by a non-linear transformation between hidden layers that implicitly represents the conversion between the true and noisy labels, and it can be readily optimized together with other model parameters. Another is an explicit probability transition matrix that captures the direct conversion between labels but needs to be derived from an EM algorithm. We conduct experiments on the NYT dataset and SemEval 2018 Task 7. The empirical results show comparable or better performance over state-of-the-art methods.

Kai Fan, Jiayi Wang, Bo Li et al.

The performances of automatic speech recognition (ASR) systems are usually evaluated by the metric word error rate (WER) when the manually transcribed data are provided, which are, however, expensively available in the real scenario. In addition, the empirical distribution of WER for most ASR systems usually tends to put a significant mass near zero, making it difficult to simulate with a single continuous distribution. In order to address the two issues of ASR quality estimation (QE), we propose a novel neural zero-inflated model to predict the WER of the ASR result without transcripts. We design a neural zero-inflated beta regression on top of a bidirectional transformer language model conditional on speech features (speech-BERT). We adopt the pre-training strategy of token level mask language modeling for speech-BERT as well, and further fine-tune with our zero-inflated layer for the mixture of discrete and continuous outputs. The experimental results show that our approach achieves better performance on WER prediction in the metrics of Pearson and MAE, compared with most existed quality estimation algorithms for ASR or machine translation.

Pei Zhang, Boxing Chen, Niyu Ge et al.

Recent advances in sequence modeling have highlighted the strengths of the transformer architecture, especially in achieving state-of-the-art machine translation results. However, depending on the up-stream systems, e.g., speech recognition, or word segmentation, the input to translation system can vary greatly. The goal of this work is to extend the attention mechanism of the transformer to naturally consume the lattice in addition to the traditional sequential input. We first propose a general lattice transformer for speech translation where the input is the output of the automatic speech recognition (ASR) which contains multiple paths and posterior scores. To leverage the extra information from the lattice structure, we develop a novel controllable lattice attention mechanism to obtain latent representations. On the LDC Spanish-English speech translation corpus, our experiments show that lattice transformer generalizes significantly better and outperforms both a transformer baseline and a lattice LSTM. Additionally, we validate our approach on the WMT 2017 Chinese-English translation task with lattice inputs from different BPE segmentations. In this task, we also observe the improvements over strong baselines.

Yuanhang Su, Kai Fan, Nguyen Bach et al.

Unsupervised neural machine translation (UNMT) has recently achieved remarkable results with only large monolingual corpora in each language. However, the uncertainty of associating target with source sentences makes UNMT theoretically an ill-posed problem. This work investigates the possibility of utilizing images for disambiguation to improve the performance of UNMT. Our assumption is intuitively based on the invariant property of image, i.e., the description of the same visual content by different languages should be approximately similar. We propose an unsupervised multi-modal machine translation (UMNMT) framework based on the language translation cycle consistency loss conditional on the image, targeting to learn the bidirectional multi-modal translation simultaneously. Through an alternate training between multi-modal and uni-modal, our inference model can translate with or without the image. On the widely used Multi30K dataset, the experimental results of our approach are significantly better than those of the text-only UNMT on the 2016 test dataset.

Shanchan Wu, Kai Fan, Qiong Zhang

Distant supervised relation extraction has been successfully applied to large corpus with thousands of relations. However, the inevitable wrong labeling problem by distant supervision will hurt the performance of relation extraction. In this paper, we propose a method with neural noise converter to alleviate the impact of noisy data, and a conditional optimal selector to make proper prediction. Our noise converter learns the structured transition matrix on logit level and captures the property of distant supervised relation extraction dataset. The conditional optimal selector on the other hand helps to make proper prediction decision of an entity pair even if the group of sentences is overwhelmed by no-relation sentences. We conduct experiments on a widely used dataset and the results show significant improvement over competitive baseline methods.

Kai Fan, Jiayi Wang, Bo Li et al.

Recent advances in statistical machine translation via the adoption of neural sequence-to-sequence models empower the end-to-end system to achieve state-of-the-art in many WMT benchmarks. The performance of such machine translation (MT) system is usually evaluated by automatic metric BLEU when the golden references are provided for validation. However, for model inference or production deployment, the golden references are prohibitively available or require expensive human annotation with bilingual expertise. In order to address the issue of quality evaluation (QE) without reference, we propose a general framework for automatic evaluation of translation output for most WMT quality evaluation tasks. We first build a conditional target language model with a novel bidirectional transformer, named neural bilingual expert model, which is pre-trained on large parallel corpora for feature extraction. For QE inference, the bilingual expert model can simultaneously produce the joint latent representation between the source and the translation, and real-valued measurements of possible erroneous tokens based on the prior knowledge learned from parallel data. Subsequently, the features will further be fed into a simple Bi-LSTM predictive model for quality evaluation. The experimental results show that our approach achieves the state-of-the-art performance in the quality estimation track of WMT 2017/2018.

Kai Fan, Qi Wei, Wenlin Wang et al.

We propose a new method that uses deep learning techniques to solve the inverse problems. The inverse problem is cast in the form of learning an end-to-end mapping from observed data to the ground-truth. Inspired by the splitting strategy widely used in regularized iterative algorithm to tackle inverse problems, the mapping is decomposed into two networks, with one handling the inversion of the physical forward model associated with the data term and one handling the denoising of the output from the former network, i.e., the inverted version, associated with the prior/regularization term. The two networks are trained jointly to learn the end-to-end mapping, getting rid of a two-step training. The training is annealing as the intermediate variable between these two networks bridges the gap between the input (the degraded version of output) and output and progressively approaches to the ground-truth. The proposed network, referred to as InverseNet, is flexible in the sense that most of the existing end-to-end network structure can be leveraged in the first network and most of the existing denoising network structure can be used in the second one. Extensive experiments on both synthetic data and real datasets on the tasks, motion deblurring, super-resolution, and colorization, demonstrate the efficiency and accuracy of the proposed method compared with other image processing algorithms.

Wenlin Wang, Yunchen Pu, Vinay Kumar Verma et al.

We present a deep generative model for learning to predict classes not seen at training time. Unlike most existing methods for this problem, that represent each class as a point (via a semantic embedding), we represent each seen/unseen class using a class-specific latent-space distribution, conditioned on class attributes. We use these latent-space distributions as a prior for a supervised variational autoencoder (VAE), which also facilitates learning highly discriminative feature representations for the inputs. The entire framework is learned end-to-end using only the seen-class training data. The model infers corresponding attributes of a test image by maximizing the VAE lower bound; the inferred attributes may be linked to labels not seen when training. We further extend our model to a (1) semi-supervised/transductive setting by leveraging unlabeled unseen-class data via an unsupervised learning module, and (2) few-shot learning where we also have a small number of labeled inputs from the unseen classes. We compare our model with several state-of-the-art methods through a comprehensive set of experiments on a variety of benchmark data sets.

Qi Wei, Kai Fan, Lawrence Carin et al.

We propose a new method that uses deep learning techniques to accelerate the popular alternating direction method of multipliers (ADMM) solution for inverse problems. The ADMM updates consist of a proximity operator, a least squares regression that includes a big matrix inversion, and an explicit solution for updating the dual variables. Typically, inner loops are required to solve the first two sub-minimization problems due to the intractability of the prior and the matrix inversion. To avoid such drawbacks or limitations, we propose an inner-loop free update rule with two pre-trained deep convolutional architectures. More specifically, we learn a conditional denoising auto-encoder which imposes an implicit data-dependent prior/regularization on ground-truth in the first sub-minimization problem. This design follows an empirical Bayesian strategy, leading to so-called amortized inference. For matrix inversion in the second sub-problem, we learn a convolutional neural network to approximate the matrix inversion, i.e., the inverse mapping is learned by feeding the input through the learned forward network. Note that training this neural network does not require ground-truth or measurements, i.e., it is data-independent. Extensive experiments on both synthetic data and real datasets demonstrate the efficiency and accuracy of the proposed method compared with the conventional ADMM solution using inner loops for solving inverse problems.

Yizhe Zhang, Zhe Gan, Kai Fan et al.

The Generative Adversarial Network (GAN) has achieved great success in generating realistic (real-valued) synthetic data. However, convergence issues and difficulties dealing with discrete data hinder the applicability of GAN to text. We propose a framework for generating realistic text via adversarial training. We employ a long short-term memory network as generator, and a convolutional network as discriminator. Instead of using the standard objective of GAN, we propose matching the high-dimensional latent feature distributions of real and synthetic sentences, via a kernelized discrepancy metric. This eases adversarial training by alleviating the mode-collapsing problem. Our experiments show superior performance in quantitative evaluation, and demonstrate that our model can generate realistic-looking sentences.

Kai Fan

Stochastic gradient descent based algorithms are typically used as the general optimization tools for most deep learning models. A Restricted Boltzmann Machine (RBM) is a probabilistic generative model that can be stacked to construct deep architectures. For RBM with Bernoulli inputs, non-Euclidean algorithm such as stochastic spectral descent (SSD) has been specifically designed to speed up the convergence with improved use of the gradient estimation by sampling methods. However, the existing algorithm and corresponding theoretical justification depend on the assumption that the possible configurations of inputs are finite, like binary variables. The purpose of this paper is to generalize SSD for Gaussian RBM being capable of mod- eling continuous data, regardless of the previous assumption. We propose the gradient descent methods in non-Euclidean space of parameters, via de- riving the upper bounds of logarithmic partition function for RBMs based on Schatten-infinity norm. We empirically show that the advantage and improvement of SSD over stochastic gradient descent (SGD).

Fangjian Guo, Xiangyu Wang, Kai Fan et al.

Variational inference (VI) provides fast approximations of a Bayesian posterior in part because it formulates posterior approximation as an optimization problem: to find the closest distribution to the exact posterior over some family of distributions. For practical reasons, the family of distributions in VI is usually constrained so that it does not include the exact posterior, even as a limit point. Thus, no matter how long VI is run, the resulting approximation will not approach the exact posterior. We propose to instead consider a more flexible approximating family consisting of all possible finite mixtures of a parametric base distribution (e.g., Gaussian). For efficient inference, we borrow ideas from gradient boosting to develop an algorithm we call boosting variational inference (BVI). BVI iteratively improves the current approximation by mixing it with a new component from the base distribution family and thereby yields progressively more accurate posterior approximations as more computing time is spent. Unlike a number of common VI variants including mean-field VI, BVI is able to capture multimodality, general posterior covariance, and nonstandard posterior shapes.

Yizhe Zhang, Xiangyu Wang, Changyou Chen et al.

We unify slice sampling and Hamiltonian Monte Carlo (HMC) sampling, demonstrating their connection via the Hamiltonian-Jacobi equation from Hamiltonian mechanics. This insight enables extension of HMC and slice sampling to a broader family of samplers, called Monomial Gamma Samplers (MGS). We provide a theoretical analysis of the mixing performance of such samplers, proving that in the limit of a single parameter, the MGS draws decorrelated samples from the desired target distribution. We further show that as this parameter tends toward this limit, performance gains are achieved at a cost of increasing numerical difficulty and some practical convergence issues. Our theoretical results are validated with synthetic data and real-world applications.

Chunyuan Li, Changyou Chen, Kai Fan et al.

Learning in deep models using Bayesian methods has generated significant attention recently. This is largely because of the feasibility of modern Bayesian methods to yield scalable learning and inference, while maintaining a measure of uncertainty in the model parameters. Stochastic gradient MCMC algorithms (SG-MCMC) are a family of diffusion-based sampling methods for large-scale Bayesian learning. In SG-MCMC, multivariate stochastic gradient thermostats (mSGNHT) augment each parameter of interest, with a momentum and a thermostat variable to maintain stationary distributions as target posterior distributions. As the number of variables in a continuous-time diffusion increases, its numerical approximation error becomes a practical bottleneck, so better use of a numerical integrator is desirable. To this end, we propose use of an efficient symmetric splitting integrator in mSGNHT, instead of the traditional Euler integrator. We demonstrate that the proposed scheme is more accurate, robust, and converges faster. These properties are demonstrated to be desirable in Bayesian deep learning. Extensive experiments on two canonical models and their deep extensions demonstrate that the proposed scheme improves general Bayesian posterior sampling, particularly for deep models.

Kai Fan, Katherine Heller

For regular particle filter algorithm or Sequential Monte Carlo (SMC) methods, the initial weights are traditionally dependent on the proposed distribution, the posterior distribution at the current timestamp in the sampled sequence, and the target is the posterior distribution of the previous timestamp. This is technically correct, but leads to algorithms which usually have practical issues with degeneracy, where all particles eventually collapse onto a single particle. In this paper, we propose and evaluate using $k$ means clustering to attack and even take advantage of this degeneracy. Specifically, we propose a Stochastic SMC algorithm which initializes the set of $k$ means, providing the initial centers chosen from the collapsed particles. To fight against degeneracy, we adjust the regular SMC weights, mediated by cluster proportions, and then correct them to retain the same expectation as before. We experimentally demonstrate that our approach has better performance than vanilla algorithms.

Kai Fan, Ziteng Wang, Jeff Beck et al.

We propose a second-order (Hessian or Hessian-free) based optimization method for variational inference inspired by Gaussian backpropagation, and argue that quasi-Newton optimization can be developed as well. This is accomplished by generalizing the gradient computation in stochastic backpropagation via a reparametrization trick with lower complexity. As an illustrative example, we apply this approach to the problems of Bayesian logistic regression and variational auto-encoder (VAE). Additionally, we compute bounds on the estimator variance of intractable expectations for the family of Lipschitz continuous function. Our method is practical, scalable and model free. We demonstrate our method on several real-world datasets and provide comparisons with other stochastic gradient methods to show substantial enhancement in convergence rates.