Author name cluster

Hongxia Yang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

36 papers

2 author rows

AAAI Conference 2026 Conference Paper

Benchmarking LLMs’ Mathematical Reasoning with Unseen Random Variables Questions

Zijin Hong
Hao Wu
Su Dong
Junnan Dong
Yilin Xiao
Yujing Zhang
Zhu Wang
Feiran Huang

Recent studies have raised significant concerns regarding the reliability of current mathematical benchmarks, highlighting key limitations such as simplistic design and potential data contamination that undermine evaluation accuracy. Consequently, developing a reliable benchmark that effectively evaluates large language models' (LLMs) genuine capabilities in mathematical reasoning remains a critical challenge. To address these concerns, we propose RV-Bench, a novel evaluation methodology for Benchmarking LLMs with Random Variables in mathematical reasoning. Specifically, we develop question-generating functions to produce random variable questions (RVQs), whose background content mirrors the original benchmark problems, but with randomized variable combinations, rendering them "unseen" to LLMs. Models must completely understand the inherent question pattern to correctly answer RVQs with diverse variable combinations. Thus, an LLMs' genuine reasoning capability is reflected through its accuracy and robustness on RV-Bench. We conducted extensive experiments on over 30 representative LLMs across more than 1,000 RVQs. Our findings reveal that LLMs exhibit a proficiency imbalance between encountered and "unseen" data distributions. Furthermore, RV-Bench reveals that proficiency generalization across similar mathematical reasoning tasks is limited, but we verified that it can still be effectively elicited through test-time scaling.

PDF Details DOI

AAAI Conference 2026 Conference Paper

EcoAgent: An Efficient Device-Cloud Collaborative Multi-Agent Framework for Mobile Automation

Biao Yi
Xueyu Hu
Yurun Chen
Shengyu Zhang
Hongxia Yang
Fan Wu

To tackle increasingly complex tasks, recent research on mobile agents has shifted towards multi-agent collaboration. Current mobile multi-agent systems are primarily deployed in the cloud, leading to high latency and operational costs. A straightforward idea is to deploy a device–cloud collaborative multi-agent system, which is nontrivial, as directly extending existing systems introduces new challenges: (1) reliance on cloud-side verification requires uploading mobile screenshots, compromising user privacy; and (2) open-loop cooperation lacking device-to-cloud feedback, underutilizing device resources and increasing latency. To overcome these limitations, we propose EcoAgent, a closed-loop device-cloud collaborative multi-agent framework designed for privacy-aware, efficient, and responsive mobile automation. EcoAgent integrates a novel reasoning approach, Dual-ReACT, into the cloud-based Planning Agent, fully exploiting cloud reasoning to compensate for limited on-device capacity, thereby enabling device-side verification and lightweight feedback. Furthermore, the device-based Observation Agent leverages a Pre-understanding Module to summarize screen content into concise textual descriptions, significantly reducing token usage and device-cloud communication overhead while preserving privacy. Experiments on AndroidWorld demonstrate that EcoAgent matches the task success rates of fully cloud-based agents, while reducing resource consumption and response latency.

PDF Details DOI

AAAI Conference 2026 Conference Paper

InfiGUI-G1: Advancing GUI Grounding with Adaptive Exploration Policy Optimization

Yuhang Liu
Zeyu Liu
Shuanghe Zhu
Pengxiang Li
Congkai Xie
Jiasheng Wang
Xueyu Hu
Xiaotian Han

The emergence of Multimodal Large Language Models (MLLMs) has propelled the development of autonomous agents that operate on Graphical User Interfaces (GUIs) using pure visual input. A fundamental challenge is robustly grounding natural language instructions. This requires a precise spatial alignment, which accurately locates the coordinates of each element, and, more critically, a correct semantic alignment, which matches the instructions to the functionally appropriate UI element. Although Reinforcement Learning with Verifiable Rewards (RLVR) has proven to be effective at improving spatial alignment for these MLLMs, we find that inefficient exploration bottlenecks semantic alignment, which prevents models from learning difficult semantic associations. To address this exploration problem, we present Adaptive Exploration Policy Optimization (AEPO), a new policy optimization framework. AEPO employs a multi-answer generation strategy to enforce broader exploration, which is then guided by a theoretically grounded Adaptive Exploration Reward (AER) function derived from first principles of efficiency η=U/C. Our AEPO-trained models, InfiGUI-G1-3B and InfiGUI-G1-7B, establish new state-of-the-art results across multiple challenging GUI grounding benchmarks, achieving significant relative improvements of up to 9.0% against the naive RLVR baseline on benchmarks designed to test generalization and semantic understanding.

PDF Details DOI

TMLR Journal 2025 Journal Article

Autoregressive Models in Vision: A Survey

Jing Xiong
Gongye Liu
Lun Huang
Chengyue Wu
Taiqiang Wu
Yao Mu
Yuan Yao
Hui Shen

Autoregressive modeling has been a huge success in the field of natural language processing (NLP). Recently, autoregressive models have emerged as a significant area of focus in computer vision, where they excel in producing high-quality visual content. Autoregressive models in NLP typically operate on subword tokens. However, the representation strategy in computer vision can vary in different levels, i.e., pixel-level, token-level, or scale-level, reflecting the diverse and hierarchical nature of visual data compared to the sequential structure of language. This survey comprehensively examines the literature on autoregressive models applied to vision. To improve readability for researchers from diverse research backgrounds, we start with preliminary sequence representation and modeling in vision. Next, we divide the fundamental frameworks of visual autoregressive models into three general sub-categories, including pixel-based, token-based, and scale-based models based on the representation strategy. We then explore the interconnections between autoregressive models and other generative models. Furthermore, we present a multifaceted categorization of autoregressive models in computer vision, including image generation, video generation, 3D generation, and multimodal generation. We also elaborate on their applications in diverse domains, including emerging domains such as embodied AI and 3D medical AI, with about 250 related references. Finally, we highlight the current challenges to autoregressive models in vision with suggestions about potential research directions. We have also set up a Github repository to organize the papers included in this survey at: https://github.com/ChaofanTao/Autoregressive-Models-in-Vision-Survey.

PDF Details

NeurIPS Conference 2025 Conference Paper

InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models

Yanggan Gu
Yuanyi Wang
Zhaoyi Yan
Yiming Zhang
Qi Zhou
Fei Wu
Hongxia Yang

Model fusion combines multiple Large Language Models (LLMs) with different strengths into a more powerful, integrated model through lightweight training methods. Existing works on model fusion focus primarily on supervised fine-tuning (SFT), leaving preference alignment (PA) —a critical phase for enhancing LLM performance—largely unexplored. The current few fusion methods on PA phase, like WRPO, simplify the process by utilizing only response outputs from source models while discarding their probability information. To address this limitation, we propose InfiFPO, a preference optimization method for implicit model fusion. InfiFPO replaces the reference model in Direct Preference Optimization (DPO) with a fused source model that synthesizes multi-source probabilities at the sequence level, circumventing complex vocabulary alignment challenges in previous works and meanwhile maintaining the probability information. By introducing probability clipping and max-margin fusion strategies, InfiFPO enables the pivot model to align with human preferences while effectively distilling knowledge from source models. Comprehensive experiments on 11 widely-used benchmarks demonstrate that InfiFPO consistently outperforms existing model fusion and preference optimization methods. When using Phi-4 as the pivot model, InfiFPO improves its average performance from 79. 95 to 83. 33 on 11 benchmarks, significantly improving its capabilities in mathematics, coding, and reasoning tasks.

PDF Details

NeurIPS Conference 2025 Conference Paper

InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion

Yuanyi Wang
Zhaoyi Yan
Yiming Zhang
Qi Zhou
Yanggan Gu
Fei Wu
Hongxia Yang

Recent advances in large language models (LLMs) have intensified efforts to fuse heterogeneous open-source models into a unified system that inherits their complementary strengths. Existing logit-based fusion methods maintain inference efficiency but treat vocabulary dimensions independently, overlooking semantic dependencies encoded by cross-dimension interactions. These dependencies reflect how token types interact under a model's internal reasoning and are essential for aligning models with diverse generation behaviors. To explicitly model these dependencies, we propose \textbf{InfiGFusion}, the first structure-aware fusion framework with a novel \textit{Graph-on-Logits Distillation} (GLD) loss. Specifically, we retain the top-$k$ logits per output and aggregate their outer products across sequence positions to form a global co-activation graph, where nodes represent vocabulary channels and edges quantify their joint activations. To ensure scalability and efficiency, we design a sorting-based closed-form approximation that reduces the original $O(n^4)$ cost of Gromov-Wasserstein distance to $O(n \log n)$, with provable approximation guarantees. Experiments across multiple fusion settings show that GLD consistently improves fusion quality and stability. InfiGFusion outperforms SOTA models and fusion baselines across 11 benchmarks spanning reasoning, coding, and mathematics. It shows particular strength in complex reasoning tasks, with +35. 6 improvement on Multistep Arithmetic and +37. 06 on Causal Judgement over SFT, demonstrating superior multi-step and relational inference.

PDF Details

ICML Conference 2025 Conference Paper

ParallelComp: Parallel Long-Context Compressor for Length Extrapolation

Jing Xiong
Jianghan Shen
Chuanyang Zheng
Zhongwei Wan
Chenyang Zhao
Chiwun Yang
Fanghua Ye 0001
Hongxia Yang

Extrapolating ultra-long contexts (text length $>$128K) remains a major challenge for large language models (LLMs), as most training-free extrapolation methods are not only severely limited by memory bottlenecks, but also suffer from the attention sink, which restricts their scalability and effectiveness in practice. In this work, we propose ParallelComp, a parallel long-context compression method that effectively overcomes the memory bottleneck, enabling 8B-parameter LLMs to extrapolate from 8K to 128K tokens on a single A100 80GB GPU in a training-free setting. ParallelComp splits the input into chunks, dynamically evicting redundant chunks and irrelevant tokens, supported by a parallel KV cache eviction mechanism. Importantly, we present a systematic theoretical and empirical analysis of attention biases in parallel attention—including the attention sink, recency bias, and middle bias—and reveal that these biases exhibit distinctive patterns under ultra-long context settings. We further design a KV cache eviction technique to mitigate this phenomenon. Experimental results show that ParallelComp enables an 8B model (trained on 8K context) to achieve 91. 17% of GPT-4’s performance under ultra-long contexts, outperforming closed-source models such as Claude-2 and Kimi-Chat. We achieve a 1. 76x improvement in chunk throughput, thereby achieving a 23. 50x acceleration in the prefill stage with negligible performance loss and pave the way for scalable and robust ultra-long contexts extrapolation in LLMs. We release the code at https: //github. com/menik1126/ParallelComp.

Details

ICLR Conference 2024 Conference Paper

B-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis

Zishun Yu
Yunzhe Tao
Liyu Chen
Tao Sun
Hongxia Yang

Program synthesis aims to create accurate, executable programs from problem specifications, specifically from natural language descriptions in our context. Recent studies have leveraged the power of reinforcement learning (RL) in conjunction with large language models (LLMs), significantly enhancing code generation capabilities. The application of RL focuses on directly optimizing for functional correctness, offering an advantage over conventional supervised methods. Despite policy-based RL methods dominating the literature on RL for program synthesis, the nature of program synthesis tasks hints at a natural alignment with value-based methods. This stems from the rich collection of off-policy programs, including those developed by human programmers and also historical samples, coupled with the straightforward verification of generated programs through automated unit testing, meaning rewards are easy to obtain. Diverging from the dominant use of policy-based algorithms, our work explores the feasibility of value-based approaches, leading to the development of our $\mathcal{B}$-Coder (pronounced Bellman coder). Yet, training value-based methods presents challenges due to the enormous search space inherent to program synthesis. To this end, we introduce an initialization protocol for RL agents utilizing pre-trained LMs and a conservative Bellman operator to reduce training complexities. Moreover, we demonstrate how to leverage the learned value functions as a dual strategy to post-process generated programs. Our empirical evaluations demonstrated $\mathcal{B}$-Coder's capability in achieving state-of-the-art performance when compared to policy-based methods. Remarkably, this achievement is reached with minimal reward engineering effort, highlighting the effectiveness of value-based RL, independent of reward designs.

Details

NeurIPS Conference 2024 Conference Paper

DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation

Yuang Ai
Xiaoqiang Zhou
Huaibo Huang
Xiaotian Han
Zhengyu Chen
Quanzeng You
Hongxia Yang

Image restoration (IR) in real-world scenarios presents significant challenges due to the lack of high-capacity models and comprehensive datasets. To tackle these issues, we present a dual strategy: GenIR, an innovative data curation pipeline, and DreamClear, a cutting-edge Diffusion Transformer (DiT)-based image restoration model. GenIR, our pioneering contribution, is a dual-prompt learning pipeline that overcomes the limitations of existing datasets, which typically comprise only a few thousand images and thus offer limited generalizability for larger models. GenIR streamlines the process into three stages: image-text pair construction, dual-prompt based fine-tuning, and data generation & filtering. This approach circumvents the laborious data crawling process, ensuring copyright compliance and providing a cost-effective, privacy-safe solution for IR dataset construction. The result is a large-scale dataset of one million high-quality images. Our second contribution, DreamClear, is a DiT-based image restoration model. It utilizes the generative priors of text-to-image (T2I) diffusion models and the robust perceptual capabilities of multi-modal large language models (MLLMs) to achieve photorealistic restoration. To boost the model's adaptability to diverse real-world degradations, we introduce the Mixture of Adaptive Modulator (MoAM). It employs token-wise degradation priors to dynamically integrate various restoration experts, thereby expanding the range of degradations the model can address. Our exhaustive experiments confirm DreamClear's superior performance, underlining the efficacy of our dual strategy for real-world image restoration. Code and pre-trained models are available at: https: //github. com/shallowdream204/DreamClear.

PDF Details DOI

ICML Conference 2024 Conference Paper

InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks

Xueyu Hu
Ziyu Zhao 0001
Shuang Wei
Ziwei Chai
Qianli Ma
Guoyin Wang 0002
Xuwu Wang
Jing Su

In this paper, we introduce InfiAgent-DABench, the first benchmark specifically designed to evaluate LLM-based agents on data analysis tasks. Agents need to solve these tasks end-to-end by interacting with an execution environment. This benchmark contains DAEval, a dataset consisting of 603 data analysis questions derived from 124 CSV files, and an agent framework which incorporates LLMs to serve as data analysis agents for both serving and evaluating. Since data analysis questions are often open-ended and hard to evaluate without human supervision, we adopt a format-prompting technique to convert each question into a closed-form format so that they can be automatically evaluated. Our extensive benchmarking of 34 LLMs uncovers the current challenges encountered in data analysis tasks. In addition, building upon our agent framework, we develop a specialized agent, DAAgent, which surpasses GPT-3. 5 by 3. 9% on DABench. Evaluation datasets and toolkits for InfiAgent-DABench are released at https: //github. com/InfiAgent/InfiAgent.

Details

NeurIPS Conference 2024 Conference Paper

InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models

Linyi Li
Shijie Geng
Zhenwen Li
Yibo He
Hao Yu
Ziyue Hua
Guanghan Ning
Siwei Wang

Large Language Models for code (code LLMs) have witnessed tremendous progress in recent years. With the rapid development of code LLMs, many popular evaluation benchmarks, such as HumanEval, DS-1000, and MBPP, have emerged to measure the performance of code LLMs with a particular focus on code generation tasks. However, they are insufficient to cover the full range of expected capabilities of code LLMs, which span beyond code generation to answering diverse coding-related questions. To fill this gap, we propose InfiBench, the first large-scale freeform question-answering (QA) benchmark for code to our knowledge, comprising 234 carefully selected high-quality Stack Overflow questions that span across 15 programming languages. InfiBench uses four types of model-free automatic metrics to evaluate response correctness where domain experts carefully concretize the criterion for each question. We conduct a systematic evaluation for over 100 latest code LLMs on InfiBench, leading to a series of novel and insightful findings. Our detailed analyses showcase potential directions for further advancement of code LLMs. InfiBench is fully open source at https: //infi-coder. github. io/infibench and continuously expanding to foster more scientific and systematic practices for code LLM evaluation.

PDF Details DOI

ICLR Conference 2024 Conference Paper

Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling

Huangjie Zheng
Zhendong Wang 0005
Jianbo Yuan
Guanghan Ning
Pengcheng He
Quanzeng You
Hongxia Yang
Mingyuan Zhou

Diffusion models excel at generating photo-realistic images but come with significant computational costs in both training and sampling. While various techniques address these computational challenges, a less-explored issue is designing an efficient and adaptable network backbone for iterative refinement. Current options like U-Net and Vision Transformer often rely on resource-intensive deep networks and lack the flexibility needed for generating images at variable resolutions or with a smaller network than used in training. This study introduces LEGO bricks, which seamlessly integrate Local-feature Enrichment and Global-content Orchestration. These bricks can be stacked to create a test-time reconfigurable diffusion backbone, allowing selective skipping of bricks to reduce sampling costs and generate higher-resolution images than the training data. LEGO bricks enrich local regions with an MLP and transform them using a Transformer block while maintaining a consistent full-resolution image across all bricks. Experimental results demonstrate that LEGO bricks enhance training efficiency, expedite convergence, and facilitate variable-resolution image generation while maintaining strong generative performance. Moreover, LEGO significantly reduces sampling time compared to other methods, establishing it as a valuable enhancement for diffusion models. Our code and project page are available at https://jegzheng.github.io/LEGODiffusion.

Details

AAAI Conference 2024 Conference Paper

Graph Neural Networks (GNNs) show promising results for graph tasks. However, existing GNNs' generalization ability will degrade when there exist distribution shifts between testing and training graph data. The fundamental reason for the severe degeneration is that most GNNs are designed based on the I.I.D hypothesis. In such a setting, GNNs tend to exploit subtle statistical correlations existing in the training set for predictions, even though it is a spurious correlation. In this paper, we study the problem of the generalization ability of GNNs on Out-Of-Distribution (OOD) settings. To solve this problem, we propose the Learning to Reweight for Generalizable Graph Neural Network (L2R-GNN) to enhance the generalization ability for achieving satisfactory performance on unseen testing graphs that have different distributions with training graphs. We propose a novel nonlinear graph decorrelation method, which can substantially improve the out-of-distribution generalization ability and compares favorably to previous methods in restraining the over-reduced sample size. The variables of graph representation are clustered based on the stability of their correlations, and graph decorrelation method learns weights to remove correlations between the variables of different clusters rather than any two variables. Besides, we introduce an effective stochastic algorithm based on bi-level optimization for the L2R-GNN framework, which enables simultaneously learning the optimal weights and GNN parameters, and avoids the over-fitting issue. Experiments show that L2R-GNN greatly outperforms baselines on various graph prediction benchmarks under distribution shifts.

PDF Details DOI

ICLR Conference 2024 Conference Paper

LEMON: Lossless model expansion

Yite Wang
Jiahao Su
Hanlin Lu
Cong Xie
Tianyi Liu
Jianbo Yuan
Haibin Lin
Ruoyu Sun 0001

Scaling of deep neural networks, especially Transformers, is pivotal for their surging performance and has further led to the emergence of sophisticated reasoning capabilities in foundation models. Such scaling generally requires training large models from scratch with random initialization, failing to leverage the knowledge acquired by their smaller counterparts, which are already resource-intensive to obtain. To tackle this inefficiency, we present $\textbf{L}$ossl$\textbf{E}$ss $\textbf{MO}$del Expansio$\textbf{N}$ (LEMON), a recipe to initialize scaled models using the weights of their smaller but pre-trained counterparts. This is followed by model training with an optimized learning rate scheduler tailored explicitly for the scaled models, substantially reducing the training time compared to training from scratch. Notably, LEMON is versatile, ensuring compatibility with various network structures, including models like Vision Transformers and BERT. Our empirical results demonstrate that LEMON reduces computational costs by 56.7\% for Vision Transformers and 33.2\% for BERT when compared to training from scratch.

Details

ICLR Conference 2024 Conference Paper

Let Models Speak Ciphers: Multiagent Debate through Embeddings

Chau Pham 0001
Boyi Liu 0001
Yingxiang Yang
Zhengyu Chen 0001
Tianyi Liu
Jianbo Yuan
Bryan A. Plummer
Zhaoran Wang 0001

Discussion and debate among Large Language Models (LLMs) have gained considerable attention due to their potential to enhance the reasoning ability of LLMs. Although natural language is an obvious choice for communication due to LLM's language understanding capability, the token sampling step needed when generating natural language poses a potential risk of information loss, as it uses only one token to represent the model's belief across the entire vocabulary. In this paper, we introduce a communication regime named CIPHER (Communicative Inter-Model Protocol Through Embedding Representation) to address this issue. Specifically, we remove the token sampling step from LLMs and let them communicate their beliefs across the vocabulary through the expectation of the raw transformer output embeddings. Remarkably, by deviating from natural language, CIPHER offers an advantage of encoding a broader spectrum of information without any modification to the model weights, outperforming the state-of-the-art LLM debate methods using natural language by 0.5-5.0% across five reasoning tasks and multiple open-source LLMs of varying sizes. This showcases the superiority and robustness of embeddings as an alternative "language" for communication among LLMs. We anticipate that CIPHER will inspire further exploration for the design of interactions within LLM agent systems, offering a new direction that could significantly influence future developments in the field.

Details

ICML Conference 2024 Conference Paper

Self-Infilling Code Generation

Lin Zheng
Jianbo Yuan
Zhi Zhang 0005
Hongxia Yang
Lingpeng Kong

In this work, we introduce self-infilling code generation, a general framework that incorporates infilling operations into auto-regressive decoding. Our approach capitalizes on the observation that recent infilling-capable code language models can perform self-infilling: whereas conventional infilling is designed to fill in the middle based on a predefined prefix and suffix, self-infilling sequentially generates both such surrounding context and the infilled content. We utilize self-infilling to introduce novel interruption and looping mechanisms in conventional decoding, evolving it into a non-monotonic process. Interruptions allow for postponing the generation of specific code until a definitive suffix is established, enhancing control during decoding. Meanwhile, the looping mechanism, which leverages the complementary nature of self-infilling and left-to-right decoding, can iteratively update and synchronize each piece of generation cyclically. Extensive experiments across a variety of code generation benchmarks demonstrate that decoding with self-infilling not only improves the output quality but also regularizes the overall generation, which effectively mitigates potential degeneration and scaffolds code to be more consistent with intended functionality.

Details

ICML Conference 2024 Conference Paper

Two Stones Hit One Bird: Bilevel Positional Encoding for Better Length Extrapolation

Zhenyu He 0012
Guhao Feng
Shengjie Luo
Kai Yang
Liwei Wang 0001
Jingjing Xu
Zhi Zhang 0005
Hongxia Yang

In this work, we leverage the intrinsic segmentation of language sequences and design a new positional encoding method called Bilevel Positional Encoding (BiPE). For each position, our BiPE blends an intra-segment encoding and an inter-segment encoding. The intra-segment encoding identifies the locations within a segment and helps the model capture the semantic information therein via absolute positional encoding. The inter-segment encoding specifies the segment index, models the relationships between segments, and aims to improve extrapolation capabilities via relative positional encoding. Theoretical analysis shows this disentanglement of positional information makes learning more effective. The empirical results also show that our BiPE has superior length extrapolation capabilities across a wide range of tasks in diverse text modalities.

Details

NeurIPS Conference 2024 Conference Paper

Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model

Haogeng Liu
Quanzeng You
Xiaotian Han
Yongfei Liu
Huaibo Huang
Ran He
Hongxia Yang

In the realm of Multimodal Large Language Models (MLLMs), vision-language connector plays a crucial role to link the pre-trained vision encoders with Large Language Models (LLMs). Despite its importance, the vision-language connector has been relatively less explored. In this study, we aim to propose a strong vision-language connector that enables MLLM to simultaneously achieve high accuracy and low computation cost. We first reveal the existence of the visual anchors in Vision Transformer and propose a cost-effective search algorithm to progressively extract them. Building on these findings, we introduce the Anchor Former (AcFormer), a novel vision-language connector designed to leverage the rich prior knowledge obtained from these visual anchors during pretraining, guiding the aggregation of information. Through extensive experimentation, we demonstrate that the proposed method significantly reduces computational costs by nearly two-thirds, while simultaneously outperforming baseline methods. This highlights the effectiveness and efficiency of AcFormer.

PDF Details DOI

TMLR Journal 2023 Journal Article

Contrastive Attraction and Contrastive Repulsion for Representation Learning

Huangjie Zheng
Xu Chen
Jiangchao Yao
Hongxia Yang
Chunyuan Li
Ya Zhang
Hao Zhang
Ivor Tsang

Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples via a one-vs-many softmax cross-entropy loss. By leveraging large amounts of unlabeled image data, recent CL methods have achieved promising results when pretrained on large-scale datasets, such as ImageNet. However, most of them consider the augmented views from the same instance are positive pairs, while views from other instances are negative ones. Such binary partition insufficiently considers the relation between samples and tends to yield worse performance when generalized on images in the wild. In this paper, to further improve the performance of CL and enhance its robustness on various datasets, we propose a doubly CL strategy that contrasts positive samples and negative ones within themselves separately. We realize this strategy with contrastive attraction and contrastive repulsion (CACR), which makes the query not only exert a greater force to attract more distant positive samples but also do so to repel closer negative samples. Theoretical analysis reveals that CACR generalizes CL's behavior by positive attraction and negative repulsion. It further considers the intra-contrastive relation within the positive and negative pairs to narrow the gap between the sampled and true distribution, which is important when datasets are less curated. Extensive large-scale experiments on standard vision tasks show that CACR not only consistently outperforms existing CL methods on benchmark datasets, but also shows better robustness when generalized on imbalanced image datasets.

PDF Details

ICML Conference 2022 Conference Paper

Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably)

Yu Huang 0023
Junyang Lin
Chang Zhou
Hongxia Yang
Longbo Huang

Despite the remarkable success of deep multi-modal learning in practice, it has not been well-explained in theory. Recently, it has been observed that the best uni-modal network outperforms the jointly trained multi-modal network across different combinations of modalities on various tasks, which is counter-intuitive since multiple signals would bring more information (Wang et al. , 2020). This work provides a theoretical explanation for the emergence of such performance gap in neural networks for the prevalent joint training framework. Based on a simplified data distribution that captures the realistic property of multi-modal data, we prove that for multi-modal late-fusion network with (smoothed) ReLU activation trained jointly by gradient descent, different modalities will compete with each other and only a subset of modalities will be learned by its corresponding encoder networks. We refer to this phenomenon as modality competition, and the losing modalities, which fail to be discovered, are the origins where the sub-optimality of joint training comes from. In contrast, for uni-modal networks with similar learning settings, we provably show that the networks will focus on learning modality-associated features. Experimentally, we illustrate that modality competition matches the intrinsic behavior of late-fusion joint training to supplement our theoretical results. To the best of our knowledge, our work is the first theoretical treatment towards the degenerating aspect of multi-modal learning in neural networks.

Details

ICML Conference 2022 Conference Paper

OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework

Peng Wang 0028
An Yang
Rui Men
Junyang Lin
Shuai Bai
Zhikang Li
Jianxin Ma
Chang Zhou 0005

In this work, we pursue a unified paradigm for multimodal pretraining to break the shackles of complex task/modality-specific customization. We propose OFA, a Task-Agnostic and Modality-Agnostic framework that supports Task Comprehensiveness. OFA unifies a diverse set of cross-modal and unimodal tasks, including image generation, visual grounding, image captioning, image classification, language modeling, etc. , in a simple sequence-to-sequence learning framework. OFA follows the instruction-based learning in both pretraining and finetuning stages, requiring no extra task-specific layers for downstream tasks. In comparison with the recent state-of-the-art vision & language models that rely on extremely large cross-modal datasets, OFA is pretrained on only 20M publicly available image-text pairs. Despite its simplicity and relatively small-scale training data, OFA achieves new SOTAs in a series of cross-modal tasks while attaining highly competitive performances on uni-modal tasks. Our further analysis indicates that OFA can also effectively transfer to unseen tasks and unseen domains. Our code and models are publicly available at https: //github. com/OFA-Sys/OFA.

Details

ICLR Conference 2022 Conference Paper

Reliable Adversarial Distillation with Unreliable Teachers

Jianing Zhu
Jiangchao Yao
Bo Han 0003
Jingfeng Zhang
Tongliang Liu
Gang Niu 0001
Jingren Zhou 0001
Jianliang Xu

In ordinary distillation, student networks are trained with soft labels (SLs) given by pretrained teacher networks, and students are expected to improve upon teachers since SLs are stronger supervision than the original hard labels. However, when considering adversarial robustness, teachers may become unreliable and adversarial distillation may not work: teachers are pretrained on their own adversarial data, and it is too demanding to require that teachers are also good at every adversarial data queried by students. Therefore, in this paper, we propose reliable introspective adversarial distillation (IAD) where students partially instead of fully trust their teachers. Specifically, IAD distinguishes between three cases given a query of a natural data (ND) and the corresponding adversarial data (AD): (a) if a teacher is good at AD, its SL is fully trusted; (b) if a teacher is good at ND but not AD, its SL is partially trusted and the student also takes its own SL into account; (c) otherwise, the student only relies on its own SL. Experiments demonstrate the effectiveness of IAD for improving upon teachers in terms of adversarial robustness.

Details

NeurIPS Conference 2021 Conference Paper

CogView: Mastering Text-to-Image Generation via Transformers

Ming Ding
Zhuoyi Yang
Wenyi Hong
Wendi Zheng
Chang Zhou
Da Yin
Junyang Lin
Xu Zou

Text-to-Image generation in the general domain has long been an open problem, which requires both a powerful generative model and cross-modal understanding. We propose CogView, a 4-billion-parameter Transformer with VQ-VAE tokenizer to advance this problem. We also demonstrate the finetuning strategies for various downstream tasks, e. g. style learning, super-resolution, text-image ranking and fashion design, and methods to stabilize pretraining, e. g. eliminating NaN losses. CogView achieves the state-of-the-art FID on the blurred MS COCO dataset, outperforming previous GAN-based models and a recent similar work DALL-E.

PDF Details

AAAI Conference 2021 Conference Paper

Dynamic Memory based Attention Network for Sequential Recommendation

Qiaoyu Tan
Jianwei Zhang
Ninghao Liu
Xiao Huang
Hongxia Yang
Jingren Zhou
Xia Hu

Sequential recommendation has become increasingly essential in various online services. It aims to model the dynamic preferences of users from their historical interactions and predict their next items. The accumulated user behavior records on real systems could be very long. This rich data brings opportunities to track actual interests of users. Prior efforts mainly focus on making recommendations based on relatively recent behaviors. However, the overall sequential data may not be effectively utilized, as early interactions might affect users’ current choices. Also, it has become intolerable to scan the entire behavior sequence when performing inference for each user, since real-world system requires short response time. To bridge the gap, we propose a novel long sequential recommendation model, called Dynamic Memory-based Attention Network (DMAN). It segments the overall long behavior sequence into a series of sub-sequences, then trains the model and maintains a set of memory blocks to preserve longterm interests of users. To improve memory fidelity, DMAN dynamically abstracts each user’s long-term interest into its own memory blocks by minimizing an auxiliary reconstruction loss. Based on the dynamic memory, the user’s shortterm and long-term interests can be explicitly extracted and combined for efficient joint recommendation. Empirical results over four benchmark datasets demonstrate the superiority of our model in capturing long-term dependency over various state-of-the-art sequential models.

PDF Details

ICML Conference 2021 Conference Paper

KNAS: Green Neural Architecture Search

Jingjing Xu 0001
Liang Zhao
Junyang Lin
Rundong Gao
Xu Sun 0001
Hongxia Yang

Many existing neural architecture search (NAS) solutions rely on downstream training for architecture evaluation, which takes enormous computations. Considering that these computations bring a large carbon footprint, this paper aims to explore a green (namely environmental-friendly) NAS solution that evaluates architectures without training. Intuitively, gradients, induced by the architecture itself, directly decide the convergence and generalization results. It motivates us to propose the gradient kernel hypothesis: Gradients can be used as a coarse-grained proxy of downstream training to evaluate random-initialized networks. To support the hypothesis, we conduct a theoretical analysis and find a practical gradient kernel that has good correlations with training loss and validation performance. According to this hypothesis, we propose a new kernel based architecture search approach KNAS. Experiments show that KNAS achieves competitive results with orders of magnitude faster than “train-then-test” paradigms on image classification tasks. Furthermore, the extremely low search cost enables its wide applications. The searched network also outperforms strong baseline RoBERTA-large on two text classification tasks.

Details

ICML Conference 2021 Conference Paper

Learning to Rehearse in Long Sequence Memorization

Zhu Zhang
Chang Zhou 0005
Jianxin Ma
Zhijie Lin 0001
Jingren Zhou 0001
Hongxia Yang
Zhou Zhao 0001

Existing reasoning tasks often have an important assumption that the input contents can be always accessed while reasoning, requiring unlimited storage resources and suffering from severe time delay on long sequences. To achieve efficient reasoning on long sequences with limited storage resources, memory augmented neural networks introduce a human-like write-read memory to compress and memorize the long input sequence in one pass, trying to answer subsequent queries only based on the memory. But they have two serious drawbacks: 1) they continually update the memory from current information and inevitably forget the early contents; 2) they do not distinguish what information is important and treat all contents equally. In this paper, we propose the Rehearsal Memory (RM) to enhance long-sequence memorization by self-supervised rehearsal with a history sampler. To alleviate the gradual forgetting of early information, we design self-supervised rehearsal training with recollection and familiarity tasks. Further, we design a history sampler to select informative fragments for rehearsal training, making the memory focus on the crucial information. We evaluate the performance of our rehearsal memory by the synthetic bAbI task and several downstream tasks, including text/video question answering and recommendation on long sequences.

Details

AAAI Conference 2021 Conference Paper

Learning with Group Noise

Qizhou Wang
Jiangchao Yao
Chen Gong
Tongliang Liu
Mingming Gong
Hongxia Yang
Bo Han

Machine learning in the context of noise is a challenging but practical setting to plenty of real-world applications. Most of the previous approaches in this area focus on the pairwise relation (casual or correlational relationship) with noise, such as learning with noisy labels. However, the group noise, which is parasitic on the coarse-grained accurate relation with the fine-grained uncertainty, is also universal and has not been well investigated. The challenge under this setting is how to discover true pairwise connections concealed by the group relation with its fine-grained noise. To overcome this issue, we propose a novel Max-Matching method for learning with group noise. Specifically, it utilizes a matching mechanism to evaluate the relation confidence of each object (cf. Figure 1) w. r. t. the target, meanwhile considering the Non-IID characteristics among objects in the group. Only the most confident object is considered to learn the model, so that the fine-grained noise is mostly dropped. The performance on a range of real-world datasets in the area of several learning paradigms demonstrates the effectiveness of Max-Matching.

PDF Details

NeurIPS Conference 2021 Conference Paper

UFC-BERT: Unifying Multi-Modal Controls for Conditional Image Synthesis

Zhu Zhang
Jianxin Ma
Chang Zhou
Rui Men
Zhikang Li
Ming Ding
Jie Tang
Jingren Zhou

Conditional image synthesis aims to create an image according to some multi-modal guidance in the forms of textual descriptions, reference images, and image blocks to preserve, as well as their combinations. In this paper, instead of investigating these control signals separately, we propose a new two-stage architecture, UFC-BERT, to unify any number of multi-modal controls. In UFC-BERT, both the diverse control signals and the synthesized image are uniformly represented as a sequence of discrete tokens to be processed by Transformer. Different from existing two-stage autoregressive approaches such as DALL-E and VQGAN, UFC-BERT adopts non-autoregressive generation (NAR) at the second stage to enhance the holistic consistency of the synthesized image, to support preserving specified image blocks, and to improve the synthesis speed. Further, we design a progressive algorithm that iteratively improves the non-autoregressively generated image, with the help of two estimators developed for evaluating the compliance with the controls and evaluating the fidelity of the synthesized image, respectively. Extensive experiments on a newly collected large-scale clothing dataset M2C-Fashion and a facial dataset Multi-Modal CelebA-HQ verify that UFC-BERT can synthesize high-fidelity images that comply with flexible multi-modal controls.

PDF Details

NeurIPS Conference 2020 Conference Paper

CogLTX: Applying BERT to Long Texts

Ming Ding
Chang Zhou
Hongxia Yang
Jie Tang

BERTs are incapable of processing long texts due to its quadratically increasing memory and time consumption. The straightforward thoughts to address this problem, such as slicing the text by a sliding window or simplifying transformers, suffer from insufficient long-range attentions or need customized CUDA kernels. The limited text length of BERT reminds us the limited capacity (5∼ 9 chunks) of the working memory of humans – then how do human beings Cognize Long TeXts? Founded on the cognitive theory stemming from Baddeley, our CogLTX framework identifies key sentences by training a judge model, concatenates them for reasoning and enables multi-step reasoning via rehearsal and decay. Since relevance annotations are usually unavailable, we propose to use treatment experiments to create supervision. As a general algorithm, CogLTX outperforms or gets comparable results to SOTA models on NewsQA, HotpotQA, multi-class and multi-label long-text classification tasks with memory overheads independent of the text length.

PDF Details

NeurIPS Conference 2020 Conference Paper

Counterfactual Prediction for Bundle Treatment

Hao Zou
Peng Cui
Bo Li
Zheyan Shen
Jianxin Ma
Hongxia Yang
Yue He

Estimating counterfactual outcome of different treatments from observational data is an important problem to assist decision making in a variety of fields. Among the various forms of treatment specification, bundle treatment has been widely adopted in many scenarios, such as recommendation systems and online marketing. The bundle treatment usually can be abstracted as a high dimensional binary vector, which makes it more challenging for researchers to remove the confounding bias in observational data. In this work, we assume the existence of low dimensional latent structure underlying bundle treatment. Via the learned latent representations of treatments, we propose a novel variational sample re-weighting (VSR) method to eliminate confounding bias by decorrelating the treatments and confounders. Finally, we conduct extensive experiments to demonstrate that the predictive model trained on this re-weighted dataset can achieve more accurate counterfactual outcome prediction.

PDF Details

IJCAI Conference 2020 Conference Paper

Dress like an Internet Celebrity: Fashion Retrieval in Videos

Hongrui Zhao
Jin Yu
Yanan Li
Donghui Wang
Jie Liu
Hongxia Yang
Fei Wu

Nowadays, both online shopping and video sharing have grown exponentially. Although internet celebrities in videos are ideal exhibition for fashion corporations to sell their products, audiences do not always know where to buy fashion products in videos, which is a cross-domain problem called video-to-shop. In this paper, we propose a novel deep neural network, called Detect, Pick, and Retrieval Network (DPRNet), to break the gap between fashion products from videos and audiences. For the video side, we have modified the traditional object detector, which automatically picks out the best object proposals for every commodity in videos without duplication, to promote the performance of the video-to-shop task. For the fashion retrieval side, a simple but effective multi-task loss network obtains new state-of-the-art results on DeepFashion. Extensive experiments conducted on a new large-scale cross-domain video-to-shop dataset shows that DPRNet is efficient and outperforms the state-of-the-art methods on video-to-shop task.

PDF Details DOI

ICLR Conference 2020 Conference Paper

Variational Autoencoders for Highly Multivariate Spatial Point Processes Intensities

Baichuan Yuan
Xiaowei Wang
Jianxin Ma
Chang Zhou
Andrea L. Bertozzi
Hongxia Yang

Multivariate spatial point process models can describe heterotopic data over space. However, highly multivariate intensities are computationally challenging due to the curse of dimensionality. To bridge this gap, we introduce a declustering based hidden variable model that leads to an efficient inference procedure via a variational autoencoder (VAE). We also prove that this model is a generalization of the VAE-based model for collaborative filtering. This leads to an interesting application of spatial point process models to recommender systems. Experimental results show the method's utility on both synthetic data and real-world data sets.

Details

IJCAI Conference 2019 Conference Paper

Hierarchical Representation Learning for Bipartite Graphs

Chong Li
Kunyang Jia
Dan Shen
C. J. Richard Shi
Hongxia Yang

Recommender systems on E-Commerce platforms track users' online behaviors and recommend relevant items according to each user’s interests and needs. Bipartite graphs that capture both user/item feature and use-item interactions have been demonstrated to be highly effective for this purpose. Recently, graph neural network (GNN) has been successfully applied in representation of bipartite graphs in industrial recommender systems. Providing individualized recommendation on a dynamic platform with billions of users is extremely challenging. A key observation is that the users of an online E-Commerce platform can be naturally clustered into a set of communities. We propose to cluster the users into a set of communities and make recommendations based on the information of the users in the community collectively. More specifically, embeddings are assigned to the communities and the user embedding is decomposed into two parts, each of which captures the community-level generalizations and individualized preferences respectively. The community embedding can be considered as an enhancement to the GNN methods that are inherently flat and do not learn hierarchical representations of graphs. The performance of the proposed algorithm is demonstrated on a public dataset and a world-leading E-Commerce company dataset.

PDF Details

IJCAI Conference 2019 Conference Paper

Large Scale Evolving Graphs with Burst Detection

Yifeng Zhao
Xiangwei Wang
Hongxia Yang
Le Song
Jie Tang

Analyzing large-scale evolving graphs are crucial for understanding the dynamic and evolutionary nature of social networks. Most existing works focus on discovering repeated and consistent temporal patterns, however, such patterns cannot fully explain the complexity observed in dynamic networks. For example, in recommendation scenarios, users sometimes purchase products on a whim during a window shopping. Thus, in this paper, we design and implement a novel framework called BurstGraph which can capture both recurrent and consistent patterns, and especially unexpected bursty network changes. The performance of the proposed algorithm is demonstrated on both a simulated dataset and a world-leading E-Commerce company dataset, showing that they are able to discriminate recurrent events from extremely bursty events in terms of action propensity.

PDF Details

NeurIPS Conference 2019 Conference Paper

Learning Disentangled Representations for Recommendation

Jianxin Ma
Chang Zhou
Peng Cui
Hongxia Yang
Wenwu Zhu

User behavior data in recommender systems are driven by the complex interactions of many latent factors behind the users’ decision making processes. The factors are highly entangled, and may range from high-level ones that govern user intentions, to low-level ones that characterize a user’s preference when executing an intention. Learning representations that uncover and disentangle these latent factors can bring enhanced robustness, interpretability, and controllability. However, learning such disentangled representations from user behavior is challenging, and remains largely neglected by the existing literature. In this paper, we present the MACRo-mIcro Disentangled Variational Auto-Encoder (MacridVAE) for learning disentangled representations from user behavior. Our approach achieves macro disentanglement by inferring the high-level concepts associated with user intentions (e. g. , to buy a shirt or a cellphone), while capturing the preference of a user regarding the different concepts separately. A micro-disentanglement regularizer, stemming from an information-theoretic interpretation of VAEs, then forces each dimension of the representations to independently reflect an isolated low-level factor (e. g. , the size or the color of a shirt). Empirical results show that our approach can achieve substantial improvement over the state-of-the-art baselines. We further demonstrate that the learned representations are interpretable and controllable, which can potentially lead to a new paradigm for recommendation where users are given fine-grained control over targeted aspects of the recommendation lists.

PDF Details

IJCAI Conference 2018 Conference Paper

ANRL: Attributed Network Representation Learning via Deep Neural Networks

Zhen Zhang
Hongxia Yang
Jiajun Bu
Sheng Zhou
Pinggang Yu
Jianwei Zhang
Martin Ester
Can Wang

Network representation learning (RL) aims to transform the nodes in a network into low-dimensional vector spaces while preserving the inherent properties of the network. Though network RL has been intensively studied, most existing works focus on either network structure or node attribute information. In this paper, we propose a novel framework, named ANRL, to incorporate both the network structure and node attribute information in a principled way. Specifically, we propose a neighbor enhancement autoencoder to model the node attribute information, which reconstructs its target neighbors instead of itself. To capture the network structure, attribute-aware skip-gram model is designed based on the attribute encoder to formulate the correlations between each node and its direct or indirect neighbors. We conduct extensive experiments on six real-world networks, including two social networks, two citation networks and two user behavior networks. The results empirically show that ANRL can achieve relatively significant gains in node classification and link prediction tasks.

PDF Details