Jun Wang

Zhe Zhu, Liangliang Nan, Haoran Xie et al.

How will you repair a physical object with some missings? You may imagine its original shape from previously captured images, recover its overall (global) but coarse shape first, and then refine its local details. We are motivated to imitate the physical repair procedure to address point cloud completion. To this end, we propose a cross-modal shape-transfer dual-refinement network (termed CSDN), a coarse-to-fine paradigm with images of full-cycle participation, for quality point cloud completion. CSDN mainly consists of "shape fusion" and "dual-refinement" modules to tackle the cross-modal challenge. The first module transfers the intrinsic shape characteristics from single images to guide the geometry generation of the missing regions of point clouds, in which we propose IPAdaIN to embed the global features of both the image and the partial point cloud into completion. The second module refines the coarse output by adjusting the positions of the generated points, where the local refinement unit exploits the geometric relation between the novel and the input points by graph convolution, and the global constraint unit utilizes the input image to fine-tune the generated offset. Different from most existing approaches, CSDN not only explores the complementary information from images but also effectively exploits cross-modal data in the whole coarse-to-fine completion procedure. Experimental results indicate that CSDN performs favorably against ten competitors on the cross-modal benchmark.

Yali Du, Chengdong Ma, Yuchen Liu et al.

Reinforcement learning algorithms require a large amount of samples; this often limits their real-world applications on even simple tasks. Such a challenge is more outstanding in multi-agent tasks, as each step of operation is more costly requiring communications or shifting or resources. This work aims to improve data efficiency of multi-agent control by model-based learning. We consider networked systems where agents are cooperative and communicate only locally with their neighbors, and propose the decentralized model-based policy optimization framework (DMPO). In our method, each agent learns a dynamic model to predict future states and broadcast their predictions by communication, and then the policies are trained under the model rollouts. To alleviate the bias of model-generated data, we restrain the model usage for generating myopic rollouts, thus reducing the compounding error of model generation. To pertain the independence of policy update, we introduce extended value function and theoretically prove that the resulting policy gradient is a close approximation to true policy gradients. We evaluate our algorithm on several benchmarks for intelligent transportation systems, which are connected autonomous vehicle control tasks (Flow and CACC) and adaptive traffic signal control (ATSC). Empirically results show that our method achieves superior data efficiency and matches the performance of model-free methods using true models.

He Zhu, Tianrui Qin, King Zhu et al.

Recently, Agentic AI has become an increasingly popular research field. However, we argue that current agent research practices lack standardization and scientific rigor, making it hard to conduct fair comparisons among methods. As a result, it is still unclear how different design choices in agent frameworks affect effectiveness, and measuring their progress remains challenging. In this work, we conduct a systematic empirical study on GAIA benchmark and BrowseComp to examine the impact of popular design choices in key agent components in a fair and rigorous manner. We find that the lack of a standard evaluation protocol makes previous works, even open-sourced ones, non-reproducible, with significant variance between random runs. Therefore, we introduce a more robust evaluation protocol to stabilize comparisons. Our study reveals which components and designs are crucial for effective agents, while others are redundant, despite seeming logical. Based on our findings, we build and open-source OAgents, a new foundation agent framework that achieves state-of-the-art performance among open-source projects. OAgents offers a modular design for various agent components, promoting future research in Agentic AI.

Dingfeng Shi, Jingyi Cao, Qianben Chen et al.

Agentic tasks, which require multi-step problem solving with autonomy, tool use, and adaptive reasoning, are becoming increasingly central to the advancement of NLP and AI. However, existing instruction data lacks tool interaction, and current agentic benchmarks rely on costly human annotation, limiting their scalability. We introduce \textsc{TaskCraft}, an automated workflow for generating difficulty-scalable, multi-tool, and verifiable agentic tasks with execution trajectories. TaskCraft expands atomic tasks using depth-based and width-based extensions to create structurally and hierarchically complex challenges. Empirical results show that these tasks improve prompt optimization in the generation workflow and enhance supervised fine-tuning of agentic foundation models. We present a large-scale synthetic dataset of approximately 36,000 tasks with varying difficulty to support future research on agent tuning and evaluation.

Jun Wang

OpenAI o1 has shown that applying reinforcement learning to integrate reasoning steps directly during inference can significantly improve a model's reasoning capabilities. This result is exciting as the field transitions from the conventional autoregressive method of generating answers to a more deliberate approach that models the slow-thinking process through step-by-step reasoning training. Reinforcement learning plays a key role in both the model's training and decoding processes. In this article, we present a comprehensive formulation of reasoning problems and investigate the use of both model-based and model-free approaches to better support this slow-thinking framework.

Yang Cao, Shuo Shang, Jun Wang et al.

This paper explores providing explainability for session-based recommendation (SR) by path reasoning. Current SR models emphasize accuracy but lack explainability, while traditional path reasoning prioritizes knowledge graph exploration, ignoring sequential patterns present in the session history. Therefore, we propose a generalized hierarchical reinforcement learning framework for SR, which improves the explainability of existing SR models via Path Reasoning, namely PR4SR. Considering the different importance of items to the session, we design the session-level agent to select the items in the session as the starting point for path reasoning and the path-level agent to perform path reasoning. In particular, we design a multi-target reward mechanism to adapt to the skip behaviors of sequential patterns in SR, and introduce path midpoint reward to enhance the exploration efficiency in knowledge graphs. To improve the completeness of the knowledge graph and to diversify the paths of explanation, we incorporate extracted feature information from images into the knowledge graph. We instantiate PR4SR in five state-of-the-art SR models (i.e., GRU4REC, NARM, GCSAN, SR-GNN, SASRec) and compare it with other explainable SR frameworks, to demonstrate the effectiveness of PR4SR for recommendation and explanation tasks through extensive experiments with these approaches on four datasets.

Wei Liu, Zhongyu Niu, Lang Gao et al.

This study investigates the self-rationalization framework constructed with a cooperative game, where a generator initially extracts the most informative segment from raw input, and a subsequent predictor utilizes the selected subset for its input. The generator and predictor are trained collaboratively to maximize prediction accuracy. In this paper, we first uncover a potential caveat: such a cooperative game could unintentionally introduce a sampling bias during rationale extraction. Specifically, the generator might inadvertently create an incorrect correlation between the selected rationale candidate and the label, even when they are semantically unrelated in the original dataset. Subsequently, we elucidate the origins of this bias using both detailed theoretical analysis and empirical evidence. Our findings suggest a direction for inspecting these correlations through attacks, based on which we further introduce an instruction to prevent the predictor from learning the correlations. Through experiments on six text classification datasets and two graph classification datasets using three network architectures (GRUs, BERT, and GCN), we show that our method not only significantly outperforms recent rationalization methods, but also achieves comparable or even better results than a representative LLM (llama3.1-8b-instruct).

Wei Liu, Haomei Xu, Bingqing Liu et al.

Large language models (LLMs) inevitably encode outdated or incorrect knowledge. Updating, deleting, and forgetting such knowledge is important for alignment, safety, and other issues. To address this issue, model editing has emerged as a promising paradigm: by precisely editing a small subset of parameters such that a specific fact is updated while preserving other knowledge. Despite its great success reported in previous papers, we find the apparent reliability of editing rests on a fragile foundation and the current literature is largely driven by illusory success. The fundamental goal of steering the model's output toward a target with minimal modification would encourage exploiting hidden shortcuts, rather than utilizing real semantics. This problem directly challenges the feasibility of the current model editing literature at its very foundation, as shortcuts are inherently at odds with robust knowledge integration. Coincidentally, this issue has long been obscured by evaluation frameworks that lack the design of negative examples. To uncover it, we systematically develop a suite of new evaluation methods. Strikingly, we find that state-of-the-art approaches collapse even under the simplest negation queries. Our empirical evidence shows that editing is likely to be based on shortcuts rather than full semantics, calling for an urgent reconsideration of the very basis of model editing before further advancements can be meaningfully pursued.

Vincent Moens, Aivar Sootla, Haitham Bou Ammar et al.

We present a method for conditional sampling for pre-trained normalizing flows when only part of an observation is available. We derive a lower bound to the conditioning variable log-probability using Schur complement properties in the spirit of Gaussian conditional sampling. Our derivation relies on partitioning flow's domain in such a way that the flow restrictions to subdomains remain bijective, which is crucial for the Schur complement application. Simulation from the variational conditional flow then amends to solving an equality constraint. Our contribution is three-fold: a) we provide detailed insights on the choice of variational distributions; b) we discuss how to partition the input space of the flow to preserve bijectivity property; c) we propose a set of methods to optimise the variational distribution. Our numerical results indicate that our sampling method can be successfully applied to invertible residual networks for inference and classification.

Jun Wang, Hefu Zhang, Qi Liu et al.

Recent years have witnessed the increasing interests in research of crowdfunding mechanism. In this area, dynamics tracking is a significant issue but is still under exploration. Existing studies either fit the fluctuations of time-series or employ regularization terms to constrain learned tendencies. However, few of them take into account the inherent decision-making process between investors and crowdfunding dynamics. To address the problem, in this paper, we propose a Trajectory-based Continuous Control for Crowdfunding (TC3) algorithm to predict the funding progress in crowdfunding. Specifically, actor-critic frameworks are employed to model the relationship between investors and campaigns, where all of the investors are viewed as an agent that could interact with the environment derived from the real dynamics of campaigns. Then, to further explore the in-depth implications of patterns (i.e., typical characters) in funding series, we propose to subdivide them into $\textit{fast-growing}$ and $\textit{slow-growing}$ ones. Moreover, for the purpose of switching from different kinds of patterns, the actor component of TC3 is extended with a structure of options, which comes to the TC3-Options. Finally, extensive experiments on the Indiegogo dataset not only demonstrate the effectiveness of our methods, but also validate our assumption that the entire pattern learned by TC3-Options is indeed the U-shaped one.

Shuai Yuan, Ahmad Zainal Abidin, Marc Sloan et al.

Internet advertising is a fast growing business which has proved to be significantly important in digital economics. It is vitally important for both web search engines and online content providers and publishers because web advertising provides them with major sources of revenue. Its presence is increasingly important for the whole media industry due to the influence of the Web. For advertisers, it is a smarter alternative to traditional marketing media such as TVs and newspapers. As the web evolves and data collection continues, the design of methods for more targeted, interactive, and friendly advertising may have a major impact on the way our digital economy evolves, and to aid societal development. Towards this goal mathematically well-grounded Computational Advertising methods are becoming necessary and will continue to develop as a fundamental tool towards the Web. As a vibrant new discipline, Internet advertising requires effort from different research domains including Information Retrieval, Machine Learning, Data Mining and Analytic, Statistics, Economics, and even Psychology to predict and understand user behaviours. In this paper, we provide a comprehensive survey on Internet advertising, discussing and classifying the research issues, identifying the recent technologies, and suggesting its future directions. To have a comprehensive picture, we first start with a brief history, introduction, and classification of the industry and present a schematic view of the new advertising ecosystem. We then introduce four major participants, namely advertisers, online publishers, ad exchanges and web users; and through analysing and discussing the major research problems and existing solutions from their perspectives respectively, we discover and aggregate the fundamental problems that characterise the newly-formed research field and capture its potential future prospects.