Author name cluster

Yinchuan Li

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.

15 papers

2 author rows

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

Personalized Federated Learning with Bidirectional Communication Compression via One-Bit Random Sketching

Jiacheng Cheng
Xu Zhang
Guanghui Qiu
Yifang Zhang
Yinchuan Li
Kaiyuan Feng

Federated Learning (FL) enables collaborative training across decentralized data, but faces key challenges of bidirectional communication overhead and client-side data heterogeneity. To address communication costs while embracing data heterogeneity, we propose pFed1BS, a novel personalized federated learning framework that achieves extreme communication compression through one-bit random sketching. In personalized FL, the goal shifts from training a single global model to creating tailored models for each client. In our framework, clients transmit highly compressed one-bit sketches, and the server aggregates and broadcasts a global one-bit consensus. To enable effective personalization, we introduce a sign-based regularizer that guides local models to align with the global consensus while preserving local data characteristics. To mitigate the computational burden of random sketching, we employ the Fast Hadamard Transform for efficient projection. Theoretical analysis guarantees that our algorithm converges to a stationary neighborhood of the global potential function. Numerical simulations demonstrate that pFed1BS substantially reduces communication costs while achieving competitive performance compared to advanced communication-efficient FL algorithms.

PDF Details DOI

ICLR Conference 2025 Conference Paper

3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds

Hengshuo Chu
Xiang Deng 0002
Qi Lv 0001
Xiaoyang Chen
Yinchuan Li
Jianye Hao
Liqiang Nie

3D Affordance detection is a challenging problem with broad applications on various robotic tasks. Existing methods typically formulate the detection paradigm as a label-based semantic segmentation task. This paradigm relies on predefined labels and lacks the ability to comprehend complex natural language, resulting in limited generalization in open-world scene. To address these limitations, we reformulate the traditional affordance detection paradigm into \textit{Instruction Reasoning Affordance Segmentation} (IRAS) task. This task is designed to output a affordance mask region given a query reasoning text, which avoids fixed categories of input labels. We accordingly propose the \textit{3D-AffordanceLLM} (3D-ADLLM), a framework designed for reasoning affordance detection in 3D open-scene. Specifically, 3D-ADLLM introduces large language models (LLMs) to 3D affordance perception with a custom-designed decoder for generating affordance masks, thus achieving open-world reasoning affordance detection. In addition, given the scarcity of 3D affordance datasets for training large models, we seek to extract knowledge from general segmentation data and transfer it to affordance detection. Thus, we propose a multi-stage training strategy that begins with a novel pre-training task, i.e., \textit{Referring Object Part Segmentation}~(ROPS). This stage is designed to equip the model with general recognition and segmentation capabilities at the object-part level. Then followed by fine-tuning with the IRAS task, 3D-ADLLM obtains the reasoning ability for affordance detection. In summary, 3D-ADLLM leverages the rich world knowledge and human-object interaction reasoning ability of LLMs, achieving approximately an 8\% improvement in mIoU on open-vocabulary affordance detection tasks.

Details

NeurIPS Conference 2025 Conference Paper

Conditioning Matters: Training Diffusion Policies is Faster Than You Think

Zibin Dong
Yicheng Liu
Yinchuan Li
Hang Zhao
Jianye Hao

Diffusion policies have emerged as a mainstream paradigm for building vision-language-action (VLA) models. Although they demonstrate strong robot control capabilities, their training efficiency remains suboptimal. In this work, we identify a fundamental challenge in conditional diffusion policy training: when generative conditions are hard to distinguish, the training objective degenerates into modeling the marginal action distribution, a phenomenon we term loss collapse. To overcome this, we propose Cocos, a simple yet general solution that modifies the source distribution in the conditional flow matching to be condition-dependent. By anchoring the source distribution around semantics extracted from condition inputs, Cocos encourages stronger condition integration and prevents the loss collapse. We provide theoretical justification and extensive empirical results across simulation and real-world benchmarks. Our method achieves faster convergence and higher success rates than existing approaches, matching the performance of large-scale pre-trained VLAs using significantly fewer gradient steps and parameters. Cocos is lightweight, easy to implement, and compatible with diverse policy architectures, offering a general-purpose improvement to diffusion policy training.

PDF Details

ICML Conference 2025 Conference Paper

Ergodic Generative Flows

Leo Maxime Brunswic
Mateo Clémente
Rui Heng Yang
Adam Sigal
Amir Rasouli
Yinchuan Li

Generative Flow Networks (GFNs) were initially introduced on directed non-acyclic graphs to sample from an unnormalized distribution density. Recent works have extended the theoretical framework for generative methods allowing more flexibility and enhancing application range. However, many challenges remain in training GFNs in continuous settings and for imitation learning (IL), including intractability of flow-matching loss, limited tests of non-acyclic training, and the need for a separate reward model in imitation learning. The present work proposes a family of generative flows called Ergodic Generative Flows (EGFs) which are used to address the aforementioned issues. First, we leverage ergodicity to build simple generative flows with finitely many globally defined transformations (diffeomorphisms) with universality guarantees and tractable flow-matching loss (FM loss). Second, we introduce a new loss involving cross-entropy coupled to weak flow-matching control, coined KL-weakFM loss. It is designed for IL training without a separate reward model. We evaluate IL-EGFs on toy 2D tasks and real-world datasets from NASA on the sphere, using the KL-weakFM loss. Additionally, we conduct toy 2D reinforcement learning experiments with a target reward, using the FM loss.

Details

NeurIPS Conference 2025 Conference Paper

Proximalized Preference Optimization for Diverse Feedback Types: A Decomposed Perspective on DPO

Kaiyang Guo
Yinchuan Li
Zhitang Chen

Direct alignment methods typically train large language models (LLMs) by contrasting the likelihoods of preferred and dispreferred responses. While effective at capturing relative preferences, these methods are widely observed to suppress the absolute likelihoods of example responses. As a result, aligned models can deviate from expected patterns, exhibiting reward‑hacking effect even without an explicit reward model. This fundamental limitation of contrastive alignment, termed likelihood underdetermination, motivates us to revisit direct preference optimization (DPO)—the seminal direct alignment method. Interestingly, we show that the DPO loss admits a principled decomposition. The reformulated loss not only extends naturally to a broader range of feedback types, but also unveils the root cause of likelihood underdetermination. Specifically, we identify that standard DPO implicitly oversimplifies a regularizer in the reformulated loss; restoring this full term effectively resolves the underdetermination. Building on these insights, we introduce PRoximalized PReference Optimization (PRO), a unified alignment method that accommodates diverse feedback types while eliminating likelihood underdetermination through an efficient approximation of the full regularizer. Empirical evaluations demonstrate the consistent superiority of PRO over existing methods across pairwise, binary and scalar feedback.

PDF Details

IROS Conference 2025 Conference Paper

RA-DP: Rapid Adaptive Diffusion Policy for Training-Free High-frequency Robotics Replanning

Xi Ye
Rui Heng Yang
Jun Jin
Yinchuan Li
Amir Rasouli

Diffusion models exhibit impressive scalability in robotic task learning, yet they struggle to adapt to novel, highly dynamic environments. This limitation primarily stems from their constrained replanning ability: they either operate at a low frequency due to a time-consuming iterative sampling process, or are unable to adapt to unforeseen feedback in case of rapid replanning. To address these challenges, we propose RA-DP, a novel diffusion policy framework with training-free high-frequency replanning ability that solves the above limitations by adapting to unforeseen dynamic environments. Specifically, our method integrates guidance signals, which are often easily obtained in the new environment during the diffusion sampling process, and utilizes a novel action queue mechanism to generate replanned actions at every denoising step without retraining, thus forming a complete training-free framework for robot motion adaptation in unseen environments. We conduct extensive evaluations in both common simulation benchmarks and real-world environments. Our results indicate that RA-DP outperforms the state-of-the-art diffusion-based methods in terms of replanning frequency and success rate. At the end, we show that our framework is theoretically compatible with any training-free guidance signal, hence increasing its applicability to a wide range of robotics tasks.

Details

ICML Conference 2025 Conference Paper

STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization

Hao Li
Qi Lv 0001
Rui Shao 0001
Xiang Deng 0002
Yinchuan Li
Jianye Hao
Liqiang Nie

Transforming complex actions into discrete skill abstractions has demonstrated strong potential for robotic manipulation. Existing approaches mainly leverage latent variable models, e. g. , VQ-VAE, to learn skill abstractions through learned vectors (codebooks), while they suffer from codebook collapse and modeling the causal relationship between learned skills. To address these limitations, we present S kill T raining with A ugmented R otation ( STAR ), a framework that advances both skill learning and composition to complete complex behaviors. Specifically, to prevent codebook collapse, we devise rotation-augmented residual skill quantization (RaRSQ). It encodes relative angles between encoder outputs into the gradient flow by rotation-based gradient mechanism. Points within the same skill code are forced to be either pushed apart or pulled closer together depending on gradient directions. Further, to capture the casual relationship between skills, we present causal skill transformer (CST) which explicitly models dependencies between skill representations through an autoregressive mechanism for coherent action generation. Extensive experiments demonstrate the superiority of STAR on both LIBERO benchmark and realworld tasks, with around 12% improvement over the baselines.

Details

NeurIPS Conference 2025 Conference Paper

Two-Steps Diffusion Policy for Robotic Manipulation via Genetic Denoising

Mateo Clémente
Leo Brunswic
Yang Yang
Xuan Zhao
Yasser Khalil
Haoyu Lei
Amir Rasouli
Yinchuan Li

Diffusion models, such as diffusion policy, have achieved state-of-the-art results in robotic manipulation by imitating expert demonstrations. While diffusion models were originally developed for vision tasks like image and video generation, many of their inference strategies have been directly transferred to control domains without adaptation. In this work, we show that by tailoring the denoising process to the specific characteristics of embodied AI tasks—particularly the structured, low-dimensional nature of action distributions---diffusion policies can operate effectively with as few as 5 neural function evaluations (NFE). Building on this insight, we propose a population-based sampling strategy, genetic denoising, which enhances both performance and stability by selecting denoising trajectories with low out-of-distribution risk. Our method solves challenging tasks with only 2 NFE while improving or matching performance. We evaluate our approach across 14 robotic manipulation tasks from D4RL and Robomimic, spanning multiple action horizons and inference budgets. In over 2 million evaluations, our method consistently outperforms standard diffusion-based policies, achieving up to 20\% performance gains with significantly fewer inference steps.

PDF Details

AAAI Conference 2024 Conference Paper

A Theory of Non-acyclic Generative Flow Networks

Leo Brunswic
Yinchuan Li
Yushun Xu
Yijun Feng
Shangling Jui
Lizhuang Ma

GFlowNets is a novel flow-based method for learning a stochastic policy to generate objects via a sequence of actions and with probability proportional to a given positive reward. We contribute to relaxing hypotheses limiting the application range of GFlowNets, in particular: acyclicity (or lack thereof). To this end, we extend the theory of GFlowNets on measurable spaces which includes continuous state spaces without cycle restrictions, and provide a generalization of cycles in this generalized context. We show that losses used so far push flows to get stuck into cycles and we define a family of losses solving this issue. Experiments on graphs and continuous tasks validate those principles.

PDF Details DOI

ICLR Conference 2023 Conference Paper

CFlowNets: Continuous Control with Generative Flow Networks

Yinchuan Li
Shuang Luo
Haozhi Wang
Jianye Hao

Generative flow networks (GFlowNets), as an emerging technique, can be used as an alternative to reinforcement learning for exploratory control tasks. GFlowNets aims to sample actions with a probability proportional to the reward, similar to sampling different candidates in an active learning fashion. However, existing GFlowNets cannot adapt to continuous control tasks because GFlowNets need to form a DAG and compute the flow matching loss by traversing the inflows and outflows of each node in the trajectory. In this paper, we propose generative continuous flow networks (CFlowNets) that can be applied to continuous control tasks. First, we present the theoretical formulation of CFlowNets. Then, a training framework for CFlowNets is proposed, including the action selection process, the flow approximation algorithm, and the continuous flow matching loss function. Afterward, we theoretically prove the error bound of the flow approximation. The error decreases rapidly as the number of flow samples increases. Finally, experimental results on continuous control tasks demonstrate the performance advantages of CFlowNets compared to many reinforcement learning methods, especially regarding exploration ability.

Details

ICLR Conference 2023 Conference Paper

DAG Matters! GFlowNets Enhanced Explainer for Graph Neural Networks

Wenqian Li
Yinchuan Li
Zhigang Li
Jianye Hao
Yan Pang

Uncovering rationales behind predictions of graph neural networks (GNNs) has received increasing attention over the years. Existing literature mainly focus on selecting a subgraph, through combinatorial optimization, to provide faithful explanations. However, the exponential size of candidate subgraphs limits the applicability of state-of-the-art methods to large-scale GNNs. We enhance on this through a different approach: by proposing a generative structure – GFlowNets-based GNN Explainer (GFlowExplainer), we turn the optimization problem into a step-by-step generative problem. Our GFlowExplainer aims to learn a policy that generates a distribution of subgraphs for which the probability of a subgraph is proportional to its’ reward. The proposed approach eliminates the influence of node sequence and thus does not need any pre-training strategies. We also propose a new cut vertex matrix to efficiently explore parent states for GFlowNets structure, thus making our approach applicable in a large-scale setting. We conduct extensive experiments on both synthetic and real datasets, and both qualitative and quantitative results show the superiority of our GFlowExplainer.

Details

IJCAI Conference 2023 Conference Paper

Generative Flow Networks for Precise Reward-Oriented Active Learning on Graphs

Yinchuan Li
Zhigang Li
Wenqian Li
Yunfeng Shao
Yan Zheng
Jianye Hao

Many score-based active learning methods have been successfully applied to graph-structured data, aiming to reduce the number of labels and achieve better performance of graph neural networks based on predefined score functions. However, these algorithms struggle to learn policy distributions that are proportional to rewards and have limited exploration capabilities. In this paper, we innovatively formulate the graph active learning problem as a generative process, named GFlowGNN, which generates various samples through sequential actions with probabilities precisely proportional to a predefined reward function. Furthermore, we propose the concept of flow nodes and flow features to efficiently model graphs as flows based on generative flow networks, where the policy network is trained with specially designed rewards. Extensive experiments on real datasets show that the proposed approach has good exploration capability and transferability, outperforming various state-of-the-art methods.

PDF Details DOI

NeurIPS Conference 2022 Conference Paper

Asymmetric Temperature Scaling Makes Larger Networks Teach Well Again

Xin-Chun Li
Wen-shu Fan
Shaoming Song
Yinchuan Li
Bingshuai Li
Shao Yunfeng
De-Chuan Zhan

Knowledge Distillation (KD) aims at transferring the knowledge of a well-performed neural network (the {\it teacher}) to a weaker one (the {\it student}). A peculiar phenomenon is that a more accurate model doesn't necessarily teach better, and temperature adjustment can neither alleviate the mismatched capacity. To explain this, we decompose the efficacy of KD into three parts: {\it correct guidance}, {\it smooth regularization}, and {\it class discriminability}. The last term describes the distinctness of {\it wrong class probabilities} that the teacher provides in KD. Complex teachers tend to be over-confident and traditional temperature scaling limits the efficacy of {\it class discriminability}, resulting in less discriminative wrong class probabilities. Therefore, we propose {\it Asymmetric Temperature Scaling (ATS)}, which separately applies a higher/lower temperature to the correct/wrong class. ATS enlarges the variance of wrong class probabilities in the teacher's label and makes the students grasp the absolute affinities of wrong classes to the target class as discriminative as possible. Both theoretical analysis and extensive experimental results demonstrate the effectiveness of ATS. The demo developed in Mindspore is available at \url{https: //gitee. com/lxcnju/ats-mindspore} and will be available at \url{https: //gitee. com/mindspore/models/tree/master/research/cv/ats}.

PDF Details

ICML Conference 2022 Conference Paper

Personalized Federated Learning via Variational Bayesian Inference

Xu Zhang 0011
Yinchuan Li
Wenpeng Li
Kaiyang Guo
Yunfeng Shao 0001

Federated learning faces huge challenges from model overfitting due to the lack of data and statistical diversity among clients. To address these challenges, this paper proposes a novel personalized federated learning method via Bayesian variational inference named pFedBayes. To alleviate the overfitting, weight uncertainty is introduced to neural networks for clients and the server. To achieve personalization, each client updates its local distribution parameters by balancing its construction error over private data and its KL divergence with global distribution from the server. Theoretical analysis gives an upper bound of averaged generalization error and illustrates that the convergence rate of the generalization error is minimax optimal up to a logarithmic factor. Experiments show that the proposed method outperforms other advanced personalized methods on personalized models, e. g. , pFedBayes respectively outperforms other SOTA algorithms by 1. 25%, 0. 42% and 11. 71% on MNIST, FMNIST and CIFAR-10 under non-i. i. d. limited data.

Details