BZPEERPapers, people, evidence and research paths
Menu

Discover

SearchFind papers, people, topics, institutions and opportunities from one place.GraphSee how papers, authors, topics and evidence connect.

Research tools

HomeContinue from the papers, people and topics that matter now.CollectionsTurn saved papers into reading lists, evidence maps and shareable context.ResearchReconstruct the path that led you from search to paper to question.CollaborationMove from a paper, topic or expert request into a focused thread.PublishCreate full-text research articles with metadata, formulas and versions.

Network

ExpertsFind specialists whose work and reviews explain why they can help.CommunitiesJoin research groups organized around papers, topics and shared evidence.

Opportunities

ListingsBrowse roles, calls and collaborations connected to real research context.

Account

Log inReturn to your saved papers, graph views and active threads.Create accountStart saving papers, building a research trail and joining teams.
Log inCreate account

Source author record

Tong Xiao

Tong Xiao appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record
Computation and LanguageMachine LearningComputer VisionArtificial Intelligenceastro-phCryptography and SecurityDigital Librariesphysics.soc-phSocial and Information Networks

Catalog footprint

What is connected

18works
9topics
4close collaborators

Actions

Connect this record

Log in to claim
Open graphBrowse works

Research graph

See the researcher in context

Open full explorer

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

18 published item(s)

preprint2026arXiv

Empirical Analysis of Decoding Biases in Masked Diffusion Models

Masked diffusion models (MDMs), which leverage bidirectional attention and a denoising process, are narrowing the performance gap with autoregressive models (ARMs). However, their internal attention mechanisms remain under-explored. This paper investigates the attention behaviors in MDMs, revealing the phenomenon of Attention Floating. Unlike ARMs, where attention converges to a fixed sink, MDMs exhibit dynamic, dispersed attention anchors that shift across denoising steps and layers. Further analysis reveals its Shallow Structure-Aware, Deep Content-Focused attention mechanism: shallow layers utilize floating tokens to build a global structural framework, while deeper layers allocate more capability toward capturing semantic content. Empirically, this distinctive attention pattern provides a mechanistic explanation for the strong in-context learning capabilities of MDMs, allowing them to double the performance compared to ARMs in knowledge-intensive tasks. All codes are available at https://github.com/NEUIR/Uncode.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Teacher-Guided Policy Optimization for LLM Distillation

The convergence of reinforcement learning and imitation learning has positioned Reverse KL (RKL) as a promising paradigm for on-policy LLM distillation, aiming to unify exploration with teacher supervision. However, we identify a critical limitation: when the student and teacher distributions diverge significantly, standard RKL often fails to yield meaningful improvement due to uninformative negative feedback. To address this inefficiency, we propose Teacher-Guided Policy Optimization (TGPO), an on-policy algorithm that incorporates dense directional guidance by leveraging teacher predictions conditioned on the student's rollout. Because TGPO remains on-policy, the algorithm integrates seamlessly with existing RLVR frameworks without requiring additional data annotation. Experiments on complex reasoning benchmarks demonstrate that TGPO significantly outperforms standard baselines and is robust to different teachers.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Learning Multiscale Transformer Models for Sequence Generation

Multiscale feature hierarchies have been witnessed the success in the computer vision area. This further motivates researchers to design multiscale Transformer for natural language processing, mostly based on the self-attention mechanism. For example, restricting the receptive field across heads or extracting local fine-grained features via convolutions. However, most of existing works directly modeled local features but ignored the word-boundary information. This results in redundant and ambiguous attention distributions, which lacks of interpretability. In this work, we define those scales in different linguistic units, including sub-words, words and phrases. We built a multiscale Transformer model by establishing relationships among scales based on word-boundary information and phrase-level prior knowledge. The proposed \textbf{U}niversal \textbf{M}ulti\textbf{S}cale \textbf{T}ransformer, namely \textsc{Umst}, was evaluated on two sequence generation tasks. Notably, it yielded consistent performance gains over the strong baseline on several test sets without sacrificing the efficiency.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Modeling and Predicting Citation Count via Recurrent Neural Network with Long Short-Term Memory

The rapid evolution of scientific research has been creating a huge volume of publications every year. Among the many quantification measures of scientific impact, citation count stands out for its frequent use in the research community. Although peer review process is the mainly reliable way of predicting a paper's future impact, the ability to foresee lasting impact on the basis of citation records is increasingly important in the scientific impact analysis in the era of big data. This paper focuses on the long-term citation count prediction for individual publications, which has become an emerging and challenging applied research topic. Based on the four key phenomena confirmed independently in previous studies of long-term scientific impact quantification, including the intrinsic quality of publications, the aging effect and the Matthew effect and the recency effect, we unify the formulations of all these observations in this paper. Building on a foundation of the above formulations, we propose a long-term citation count prediction model for individual papers via recurrent neural network with long short-term memory units. Extensive experiments on a real-large citation data set demonstrate that the proposed model consistently outperforms existing methods, and achieves a significant performance improvement.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

ODE Transformer: An Ordinary Differential Equation-Inspired Model for Sequence Generation

Residual networks are an Euler discretization of solutions to Ordinary Differential Equations (ODE). This paper explores a deeper relationship between Transformer and numerical ODE methods. We first show that a residual block of layers in Transformer can be described as a higher-order solution to ODE. Inspired by this, we design a new architecture, {\it ODE Transformer}, which is analogous to the Runge-Kutta method that is well motivated in ODE. As a natural extension to Transformer, ODE Transformer is easy to implement and efficient to use. Experimental results on the large-scale machine translation, abstractive summarization, and grammar error correction tasks demonstrate the high genericity of ODE Transformer. It can gain large improvements in model performance over strong baselines (e.g., 30.77 and 44.11 BLEU scores on the WMT'14 English-German and English-French benchmarks) at a slight cost in inference efficiency.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

On Vision Features in Multimodal Machine Translation

Previous work on multimodal machine translation (MMT) has focused on the way of incorporating vision features into translation but little attention is on the quality of vision models. In this work, we investigate the impact of vision models on MMT. Given the fact that Transformer is becoming popular in computer vision, we experiment with various strong models (such as Vision Transformer) and enhanced features (such as object-detection and image captioning). We develop a selective attention model to study the patch-level contribution of an image in MMT. On detailed probing tasks, we find that stronger vision models are helpful for learning translation from the visual modality. Our results also suggest the need of carefully examining MMT models, especially when current benchmarks are small-scale and biased. Our code could be found at \url{https://github.com/libeineu/fairseq_mmt}.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Attention: to Better Stand on the Shoulders of Giants

Science of science (SciSci) is an emerging discipline wherein science is used to study the structure and evolution of science itself using large data sets. The increasing availability of digital data on scholarly outcomes offers unprecedented opportunities to explore SciSci. In the progress of science, the previously discovered knowledge principally inspires new scientific ideas, and citation is a reasonably good reflection of this cumulative nature of scientific research. The researches that choose potentially influential references will have a lead over the emerging publications. Although the peer review process is the mainly reliable way of predicting a paper's future impact, the ability to foresee the lasting impact based on citation records is increasingly essential in the scientific impact analysis in the era of big data. This paper develops an attention mechanism for the long-term scientific impact prediction and validates the method based on a real large-scale citation data set. The results break conventional thinking. Instead of accurately simulating the original power-law distribution, emphasizing the limited attention can better stand on the shoulders of giants.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Does Multi-Encoder Help? A Case Study on Context-Aware Neural Machine Translation

In encoder-decoder neural models, multiple encoders are in general used to represent the contextual information in addition to the individual sentence. In this paper, we investigate multi-encoder approaches in documentlevel neural machine translation (NMT). Surprisingly, we find that the context encoder does not only encode the surrounding sentences but also behaves as a noise generator. This makes us rethink the real benefits of multi-encoder in context-aware translation - some of the improvements come from robust training. We compare several methods that introduce noise and/or well-tuned dropout setup into the training of these encoders. Experimental results show that noisy training plays an important role in multi-encoder-based NMT, especially when the training data is small. Also, we establish a new state-of-the-art on IWSLT Fr-En task by careful use of noise generation and dropout methods.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild

We present a novel 3D pose refinement approach based on differentiable rendering for objects of arbitrary categories in the wild. In contrast to previous methods, we make two main contributions: First, instead of comparing real-world images and synthetic renderings in the RGB or mask space, we compare them in a feature space optimized for 3D pose refinement. Second, we introduce a novel differentiable renderer that learns to approximate the rasterization backward pass from data instead of relying on a hand-crafted algorithm. For this purpose, we predict deep cross-domain correspondences between RGB images and 3D model renderings in the form of what we call geometric correspondence fields. These correspondence fields serve as pixel-level gradients which are analytically propagated backward through the rendering pipeline to perform a gradient-based optimization directly on the 3D pose. In this way, we precisely align 3D models to objects in RGB images which results in significantly improved 3D pose estimates. We evaluate our approach on the challenging Pix3D dataset and achieve up to 55% relative improvement compared to state-of-the-art refinement methods in multiple metrics.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Learning Architectures from an Extended Search Space for Language Modeling

Neural architecture search (NAS) has advanced significantly in recent years but most NAS systems restrict search to learning architectures of a recurrent or convolutional cell. In this paper, we extend the search space of NAS. In particular, we present a general approach to learn both intra-cell and inter-cell architectures (call it ESS). For a better search result, we design a joint learning method to perform intra-cell and inter-cell NAS simultaneously. We implement our model in a differentiable architecture search system. For recurrent neural language modeling, it outperforms a strong baseline significantly on the PTB and WikiText data, with a new state-of-the-art on PTB. Moreover, the learned architectures show good transferability to other systems. E.g., they improve state-of-the-art systems on the CoNLL and WNUT named entity recognition (NER) tasks and CoNLL chunking task, indicating a promising line of research on large-scale pre-learned architectures.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Multi-layer Representation Fusion for Neural Machine Translation

Neural machine translation systems require a number of stacked layers for deep models. But the prediction depends on the sentence representation of the top-most layer with no access to low-level representations. This makes it more difficult to train the model and poses a risk of information loss to prediction. In this paper, we propose a multi-layer representation fusion (MLRF) approach to fusing stacked layers. In particular, we design three fusion functions to learn a better representation from the stack. Experimental results show that our approach yields improvements of 0.92 and 0.56 BLEU points over the strong Transformer baseline on IWSLT German-English and NIST Chinese-English MT tasks respectively. The result is new state-of-the-art in German-English translation.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Neural Machine Translation with Joint Representation

Though early successes of Statistical Machine Translation (SMT) systems are attributed in part to the explicit modelling of the interaction between any two source and target units, e.g., alignment, the recent Neural Machine Translation (NMT) systems resort to the attention which partially encodes the interaction for efficiency. In this paper, we employ Joint Representation that fully accounts for each possible interaction. We sidestep the inefficiency issue by refining representations with the proposed efficient attention operation. The resulting Reformer models offer a new Sequence-to- Sequence modelling paradigm besides the Encoder-Decoder framework and outperform the Transformer baseline in either the small scale IWSLT14 German-English, English-German and IWSLT15 Vietnamese-English or the large scale NIST12 Chinese-English translation tasks by about 1 BLEU point.We also propose a systematic model scaling approach, allowing the Reformer model to beat the state-of-the-art Transformer in IWSLT14 German-English and NIST12 Chinese-English with about 50% fewer parameters. The code is publicly available at https://github.com/lyy1994/reformer.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Towards Differentially Private Text Representations

Most deep learning frameworks require users to pool their local data or model updates to a trusted server to train or maintain a global model. The assumption of a trusted server who has access to user information is ill-suited in many applications. To tackle this problem, we develop a new deep learning framework under an untrusted server setting, which includes three modules: (1) embedding module, (2) randomization module, and (3) classifier module. For the randomization module, we propose a novel local differentially private (LDP) protocol to reduce the impact of privacy parameter $ε$ on accuracy, and provide enhanced flexibility in choosing randomization probabilities for LDP. Analysis and experiments show that our framework delivers comparable or even better performance than the non-private framework and existing LDP protocols, demonstrating the advantages of our LDP protocol.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Towards Fully 8-bit Integer Inference for the Transformer Model

8-bit integer inference, as a promising direction in reducing both the latency and storage of deep neural networks, has made great progress recently. On the other hand, previous systems still rely on 32-bit floating point for certain functions in complex models (e.g., Softmax in Transformer), and make heavy use of quantization and de-quantization. In this work, we show that after a principled modification on the Transformer architecture, dubbed Integer Transformer, an (almost) fully 8-bit integer inference algorithm Scale Propagation could be derived. De-quantization is adopted when necessary, which makes the network more efficient. Our experiments on WMT16 En<->Ro, WMT14 En<->De and En->Fr translation tasks as well as the WikiText-103 language modelling task show that the fully 8-bit Transformer system achieves comparable performance with the floating point baseline but requires nearly 4x less memory footprint.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Convolutional neural networks with low-rank regularization

Large CNNs have delivered impressive performance in various computer vision applications. But the storage and computation requirements make it problematic for deploying these models on mobile devices. Recently, tensor decompositions have been used for speeding up CNNs. In this paper, we further develop the tensor decomposition technique. We propose a new algorithm for computing the low-rank tensor decomposition for removing the redundancy in the convolution kernels. The algorithm finds the exact global optimizer of the decomposition and is more effective than iterative methods. Based on the decomposition, we further propose a new method for training low-rank constrained CNNs from scratch. Interestingly, while achieving a significant speedup, sometimes the low-rank constrained CNNs delivers significantly better performance than their non-constrained counterparts. On the CIFAR-10 dataset, the proposed low-rank NIN model achieves $91.31\%$ accuracy (without data augmentation), which also improves upon state-of-the-art result. We evaluated the proposed method on CIFAR-10 and ILSVRC12 datasets for a variety of modern CNNs, including AlexNet, NIN, VGG and GoogleNet with success. For example, the forward time of VGG-16 is reduced by half while the performance is still comparable. Empirical success suggests that low-rank tensor decompositions can be a very useful tool for speeding up large CNNs.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Crafting GBD-Net for Object Detection

The visual cues from multiple support regions of different sizes and resolutions are complementary in classifying a candidate box in object detection. Effective integration of local and contextual visual cues from these regions has become a fundamental problem in object detection. In this paper, we propose a gated bi-directional CNN (GBD-Net) to pass messages among features from different support regions during both feature learning and feature extraction. Such message passing can be implemented through convolution between neighboring support regions in two directions and can be conducted in various layers. Therefore, local and contextual visual patterns can validate the existence of each other by learning their nonlinear relationships and their close interactions are modeled in a more complex way. It is also shown that message passing is not always helpful but dependent on individual samples. Gated functions are therefore needed to control message transmission, whose on-or-offs are controlled by extra visual evidence from the input sample. The effectiveness of GBD-Net is shown through experiments on three object detection datasets, ImageNet, Pascal VOC2007 and Microsoft COCO. This paper also shows the details of our approach in wining the ImageNet object detection challenge of 2016, with source code provided on \url{https://github.com/craftGBD/craftGBD}.

0 citations0 reviewsNo code linkedOpen access
preprint2016arXiv

Learning Deep Feature Representations with Domain Guided Dropout for Person Re-identification

Learning generic and robust feature representations with data from multiple domains for the same problem is of great value, especially for the problems that have multiple datasets but none of them are large enough to provide abundant data variations. In this work, we present a pipeline for learning deep feature representations from multiple domains with Convolutional Neural Networks (CNNs). When training a CNN with data from all the domains, some neurons learn representations shared across several domains, while some others are effective only for a specific one. Based on this important observation, we propose a Domain Guided Dropout algorithm to improve the feature learning procedure. Experiments show the effectiveness of our pipeline and the proposed algorithm. Our methods on the person re-identification problem outperform state-of-the-art methods on multiple datasets by large margins.

0 citations0 reviewsNo code linkedOpen access
preprint2008arXiv

Eccentricity modulation of a close-in planet by a companion - application to GJ 436 system

GJ 436b is a Neptune-size planet with 23.2 Earth masses in an elliptical orbit of period 2.64 days and eccentricity 0.16. With a typical tidal dissipation factor (Q' ~ 10^6) as that of a giant planet with convective envelope, its orbital circularization timescale under internal tidal dissipation is around 1 Gyr, at least two times less than the stellar age (>3 Gyr). A plausible mechanism is that the eccentricity of GJ 436b is modulated by a planetary companion due to their mutual perturbation. Here we investigate this possibility from the dynamical viewpoint. A general method is given to predict the possible locations of the dynamically coupled companions, including in nearby/distance non-resonant or mean motion resonance orbits with the first planet. Applying the method to GJ 436 system, we find it is very unlikely that the eccentricity of GJ 436b is maintained at the present location by a nearby/distance companion through secular perturbation or mean motion resonance. In fact, in all these simulated cases, GJ 436b will undergo eccentricity damp and orbital decay, leaving the present location within the stellar age. However, these results do not rule out the possible existence of planet companions in nearby/distance orbits, although they are not able to maintain the eccentricity of GJ 436b.

0 citations0 reviewsNo code linkedOpen access