Author name cluster

Kaiwen Zhou

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.

11 papers

1 author row

AAAI Conference 2026 Conference Paper

A²Flow: Automating Agentic Workflow Generation via Self-Adaptive Abstraction Operators

Mingming Zhao
Xiaokang Wei
Yuanqi Shao
Kaiwen Zhou
Lin Yang
Siwei Rao
Junhui Zhan
Zhitang Chen

Large language models (LLMs) have shown strong potential in automating the design of agentic workflows. However, existing methods still rely heavily on manually predefined operators, limiting generalization and scalability. To address this issue, we propose A²Flow, a fully automated framework for agentic workflow generation based on self-adaptive abstraction operators. A²Flow employs a three-stage operator extraction process: 1) Case-based Initial Operator Generation: leveraging expert demonstrations and LLM reasoning to generate case-specific operators; 2) Operator Clustering and Preliminary Abstraction: grouping similar operators across tasks to form preliminary abstractions; and 3) Deep Extraction for Abstract Execution Operators: applying long chain-of-thought prompting and multi-path reasoning to derive compact and generalizable execution operators. These operators serve as reusable building blocks for workflow construction without manual predefinition. Furthermore, we enhance node-level workflow search with an operator memory mechanism, which retains historical outputs to enrich context and improve decision-making. Experiments on general and embodied benchmarks show that A²Flow achieves a 2.4% and 19.3% average performance improvement and reduces resource usage by 37% over state-of-the-art baselines.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Boosting Cross-problem Generalization in Diffusion-Based Neural Combinatorial Solver via Inference Time Adaptation

Haoyu Lei
Kaiwen Zhou
Yinchuan Li
Zhitang Chen
Farzan Farnia

Diffusion-based Neural Combinatorial Optimization (NCO) has demonstrated effectiveness in solving NP-complete (NPC) problems by learning discrete diffusion models for solution generation, eliminating hand-crafted domain knowledge. Despite their success, existing NCO methods face significant challenges in both cross-scale and cross-problem generalization, and high training costs compared to traditional solvers. While recent studies on diffusion models have introduced training-free guidance approaches that leverage pre-defined guidance functions for conditional generation, such methodologies have not been extensively explored in combinatorial optimization. To bridge this gap, we propose a training-free inference time adaptation framework (DIFU-Ada) that enables both the zero-shot cross-problem transfer and cross-scale generalization capabilities of diffusion-based NCO solvers without requiring additional training. We provide theoretical analysis that helps understanding the cross-problem transfer capability. Our experimental results demonstrate that a diffusion solver, trained exclusively on the Traveling Salesman Problem (TSP), can achieve competitive zero-shot transfer performance across different problem scales on TSP variants, such as Prize Collecting TSP (PCTSP) and the Orienteering Problem (OP), through inference time adaptation.

PDF Details DOI

AAAI Conference 2026 Conference Paper

SemanticVLA: Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation

Wei Li
Renshan Zhang
Rui Shao
Zhijian Fang
Kaiwen Zhou
Zhuotao Tian
Liqiang Nie

Vision-Language-Action (VLA) models have advanced in robotic manipulation, yet practical deployment remains hindered by two key limitations: **1) perceptual redundancy**, where irrelevant visual inputs are processed inefficiently, and **2) superficial instruction-vision alignment**, which hampers semantic grounding of actions. In this paper, we propose **SemanticVLA**, a novel VLA framework that performs Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation. Specifically: **1)** To sparsify redundant perception while preserving semantic alignment, **Semantic-guided Dual Visual Pruner (SD-Pruner)** performs: Instruction-driven Pruner (ID-Pruner) extracts global action cues and local semantic anchors in SigLIP; Spatial-aggregation Pruner (SA-Pruner) compacts geometry-rich features into task-adaptive tokens in DINOv2. **2)** To exploit sparsified features and integrate semantics with spatial geometry, **Semantic-complementary Hierarchical Fuser (SH-Fuser)** fuses dense patches and sparse tokens across SigLIP and DINOv2 for coherent representation. **3)** To enhance the transformation from perception to action, **Semantic-conditioned Action Coupler (SA-Coupler)** replaces the conventional observation-to-DoF approach, yielding more efficient and interpretable behavior modeling for manipulation tasks. Extensive experiments on simulation and real-world tasks show that SemanticVLA sets a new SOTA in both performance and efficiency. SemanticVLA surpasses OpenVLA on LIBERO benchmark by **21.1%** in success rate, while reducing training cost and inference latency by **3.0×** and **2.7×**.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents

Yuqi Zhou
Sunhao Dai
Shuai Wang
Kaiwen Zhou
Qinglin Jia
Jun Xu

Recent Graphical User Interface (GUI) agents replicate the R1-Zero paradigm, coupling online Reinforcement Learning (RL) with explicit chain-of-thought reasoning prior to object grounding and thereby achieving substantial performance gains. In this paper, we first conduct extensive analysis experiments of three key components of that training pipeline: input design, output evaluation, and policy update—each revealing distinct challenges arising from blindly applying general-purpose RL without adapting to GUI grounding tasks. Input design: Current templates encourage the model to generate chain-of-thought reasoning, but longer chains unexpectedly lead to worse grounding performance. Output evaluation: Reward functions based on hit signals or box area allow models to exploit box size, leading to reward hacking and poor localization quality. Policy update: Online RL tends to overfit easy examples due to biases in length and sample difficulty, leading to under-optimization on harder cases. To address these issues, we propose three targeted solutions. First, we adopt a $\textbf{Fast Thinking Template}$ that encourages direct answer generation, reducing excessive reasoning during training. Second, we incorporate a box size constraint into the reward function to mitigate reward hacking. Third, we revise the RL objective by adjusting length normalization and adding a difficulty-aware scaling factor, enabling better optimization on hard samples. Our $\textbf{GUI-G1-3B}$, trained on 17K public samples with Qwen2. 5-VL-3B-Instruct, achieves $\textbf{90. 3\%}$ accuracy on ScreenSpot and $\textbf{37. 1\%}$ on ScreenSpot-Pro. This surpasses all prior models of similar size and even outperforms the larger UI-TARS-7B, establishing a new state-of-the-art in GUI agent grounding.

PDF Details

AAAI Conference 2024 Conference Paper

Enhancing Evolving Domain Generalization through Dynamic Latent Representations

Binghui Xie
Yongqiang Chen
Jiaqi Wang
Kaiwen Zhou
Bo Han
Wei Meng
James Cheng

Domain generalization is a critical challenge for machine learning systems. Prior domain generalization methods focus on extracting domain-invariant features across several stationary domains to enable generalization to new domains. However, in non-stationary tasks where new domains evolve in an underlying continuous structure, such as time, merely extracting the invariant features is insufficient for generalization to the evolving new domains. Nevertheless, it is non-trivial to learn both evolving and invariant features within a single model due to their conflicts. To bridge this gap, we build causal models to characterize the distribution shifts concerning the two patterns, and propose to learn both dynamic and invariant features via a new framework called Mutual Information-Based Sequential Autoencoders (MISTS). MISTS adopts information theoretic constraints onto sequential autoencoders to disentangle the dynamic and invariant features, and leverage an adaptive classifier to make predictions based on both evolving and invariant information. Our experimental results on both synthetic and real-world datasets demonstrate that MISTS succeeds in capturing both evolving and invariant information, and present promising results in evolving domain generalization tasks.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

HORSE: Hierarchical Representation for Large-Scale Neural Subset Selection

Binghui Xie
Yixuan Wang
Yongqiang Chen
Kaiwen Zhou
Yu Li
Wei Meng
James Cheng

Subset selection tasks, such as anomaly detection and compound selection in AI-assisted drug discovery, are crucial for a wide range of applications. Learning subset-valued functions with neural networks has achieved great success by incorporating permutation invariance symmetry into the architecture. However, existing neural set architectures often struggle to either capture comprehensive information from the superset or address complex interactions within the input. Additionally, they often fail to perform in scenarios where superset sizes surpass available memory capacity. To address these challenges, we introduce the novel concept of the Identity Property, which requires models to integrate information from the originating set, resulting in the development of neural networks that excel at performing effective subset selection from large supersets. Moreover, we present the Hierarchical Representation of Neural Subset Selection (HORSE), an attention-based method that learns complex interactions and retains information from both the input set and the optimal subset supervision signal. Specifically, HORSE enables the partitioning of the input ground set into manageable chunks that can be processed independently and then aggregated, ensuring consistent outcomes across different partitions. Through extensive experimentation, we demonstrate that HORSE significantly enhances neural subset selection performance by capturing more complex information and surpasses state-of-the-art methods in handling large-scale inputs by a margin of up to 20%.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models

Haoyu Chen
Wenbo Li
Jinjin Gu
Jingjing Ren
Sixiang Chen
Tian Ye
Renjing Pei
Kaiwen Zhou

Natural images captured by mobile devices often suffer from multiple types of degradation, such as noise, blur, and low light. Traditional image restoration methods require manual selection of specific tasks, algorithms, and execution sequences, which is time-consuming and may yield suboptimal results. All-in-one models, though capable of handling multiple tasks, typically support only a limited range and often produce overly smooth, low-fidelity outcomes due to their broad data distribution fitting. To address these challenges, we first define a new pipeline for restoring images with multiple degradations, and then introduce RestoreAgent, an intelligent image restoration system leveraging multimodal large language models. RestoreAgent autonomously assesses the type and extent of degradation in input images and performs restoration through (1) determining the appropriate restoration tasks, (2) optimizing the task sequence, (3) selecting the most suitable models, and (4) executing the restoration. Experimental results demonstrate the superior performance of RestoreAgent in handling complex degradation, surpassing human experts. Furthermore, the system’s modular design facilitates the fast integration of new tasks and models.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Does Invariant Graph Learning via Environment Augmentation Learn Invariance?

Yongqiang Chen
Yatao Bian
Kaiwen Zhou
Binghui Xie
Bo Han
James Cheng

Invariant graph representation learning aims to learn the invariance among data from different environments for out-of-distribution generalization on graphs. As the graph environment partitions are usually expensive to obtain, augmenting the environment information has become the de facto approach. However, the usefulness of the augmented environment information has never been verified. In this work, we find that it is fundamentally impossible to learn invariant graph representations via environment augmentation without additional assumptions. Therefore, we develop a set of minimal assumptions, including variation sufficiency and variation consistency, for feasible invariant graph learning. We then propose a new framework Graph invAriant Learning Assistant (GALA). GALA incorporates an assistant model that needs to be sensitive to graph environment changes or distribution shifts. The correctness of the proxy predictions by the assistant model hence can differentiate the variations in spurious subgraphs. We show that extracting the maximally invariant subgraph to the proxy predictions provably identifies the underlying invariant subgraph for successful OOD generalization under the established minimal assumptions. Extensive experiments on datasets including DrugOOD with various graph distribution shifts confirm the effectiveness of GALA.

PDF Details

NeurIPS Conference 2023 Conference Paper

Understanding and Improving Feature Learning for Out-of-Distribution Generalization

Yongqiang Chen
Wei Huang
Kaiwen Zhou
Yatao Bian
Bo Han
James Cheng

A common explanation for the failure of out-of-distribution (OOD) generalization is that the model trained with empirical risk minimization (ERM) learns spurious features instead of invariant features. However, several recent studies challenged this explanation and found that deep networks may have already learned sufficiently good features for OOD generalization. Despite the contradictions at first glance, we theoretically show that ERM essentially learns both spurious and invariant features, while ERM tends to learn spurious features faster if the spurious correlation is stronger. Moreover, when fed the ERM learned features to the OOD objectives, the invariant feature learning quality significantly affects the final OOD performance, as OOD objectives rarely learn new features. Therefore, ERM feature learning can be a bottleneck to OOD generalization. To alleviate the reliance, we propose Feature Augmented Training (FeAT), to enforce the model to learn richer features ready for OOD generalization. FeAT iteratively augments the model to learn new features while retaining the already learned features. In each round, the retention and augmentation operations are performed on different subsets of the training data that capture distinct features. Extensive experiments show that FeAT effectively learns richer features thus boosting the performance of various OOD objectives.

PDF Details

NeurIPS Conference 2020 Conference Paper

Boosting First-Order Methods by Shifting Objective: New Schemes with Faster Worst-Case Rates

Kaiwen Zhou
Anthony Man-Cho So
James Cheng

We propose a new methodology to design first-order methods for unconstrained strongly convex problems. Specifically, instead of tackling the original objective directly, we construct a shifted objective function that has the same minimizer as the original objective and encodes both the smoothness and strong convexity of the original objective in an interpolation condition. We then propose an algorithmic template for tackling the shifted objective, which can exploit such a condition. Following this template, we derive several new accelerated schemes for problems that are equipped with various first-order oracles and show that the interpolation condition allows us to vastly simplify and tighten the analysis of the derived methods. In particular, all the derived methods have faster worst-case convergence rates than their existing counterparts. Experiments on machine learning tasks are conducted to evaluate the new methods.

PDF Details

IJCAI Conference 2020 Conference Paper

Tight Convergence Rate of Gradient Descent for Eigenvalue Computation

Qinghua Ding
Kaiwen Zhou
James Cheng

Riemannian gradient descent (RGD) is a simple, popular and efficient algorithm for leading eigenvector computation [AMS08]. However, the existing analysis of RGD for eigenproblem is still not tight, which is O(log(n/epsilon)/Delta^2) due to [Xu et al. , 2018]. In this paper, we show that RGD in fact converges at rate O(log(n/epsilon)/Delta), and give instances to shows the tightness of our result. This improves the best prior analysis by a quadratic factor. Besides, we also give tight convergence analysis of a deterministic variant of Oja's rule due to [Oja, 1982]. We show that it also enjoys fast convergence rate of O(log(n/epsilon)/Delta). Previous papers only gave asymptotic characterizations [Oja, 1982; Oja, 1989; Yi et al. , 2005]. Our tools for proving convergence results include an innovative reduction and chaining technique, and a noisy fixed point iteration argument. Besides, we also give empirical justifications of our convergence rates over synthetic and real data.

PDF Details DOI