Author name cluster

Junyu Zhang

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.

20 papers

2 author rows

AAAI Conference 2026 Conference Paper

Counterfactual Planning for Generalizable Agents’ Actions

Jiarun Fu
Lizhong Ding
Qiuning Wei
Yuhan Guo
Yurong Cheng
Junyu Zhang

Large language models have revolutionized agent planning by serving as the engine of heuristic guidance. However, LLM-based agents often struggle to generalize across complex environments and to adapt to stochastic feedback arising from environment–action interactions. We propose Counterfactual Planning—a method designed to improve the generalizability and adaptability of agents' actions by inferring causal representations of environmental confounders and performing counterfactual reasoning over planned actions. We formalize the agent planning process as a structural causal model, providing a mathematical formulation for causal analysis of how environmental states influence action generation and how actions affect future state transitions. To support generalizable action planning, we introduce the State Causality Evaluator (SCE), which dynamically infers task-conditioned causal representations from complex environment states; and to enhance adaptability under stochastic feedback, we propose the What-If-Not (WIN) reward, which performs counterfactual interventions to refine actions through causal evaluation. We validate our framework in an open-world environment, where experiments demonstrate improvements in both action generalization and planning adaptability.

PDF Details DOI

ICLR Conference 2025 Conference Paper

Anti-Exposure Bias in Diffusion Models

Junyu Zhang
Daochang Liu
Eunbyung Park
Shichao Zhang 0001
Chang Xu 0002

Diffusion models (DMs) have achieved record-breaking performance in image generation tasks. Nevertheless, in practice, the training-sampling discrepancy, caused by score estimation error and discretization error, limits the modeling ability of DMs, a phenomenon known as exposure bias. To alleviate such exposure bias and further improve the generative performance, we put forward a prompt learning framework built upon a lightweight prompt prediction model. Concretely, our model learns an anti-bias prompt for the generated sample at each sampling step, aiming to compensate for the exposure bias that arises. Following this design philosophy, our framework rectifies the sampling trajectory to match the training trajectory, thereby reducing the divergence between the target data distribution and the modeling distribution. To train the prompt prediction model, we simulate exposure bias by constructing training data and introduce a time-dependent weighting function for optimization. Empirical results on various DMs demonstrate the superiority of our prompt learning framework across three benchmark datasets. Importantly, the optimized prompt prediction model effectively improves image quality with only a 5\% increase in sampling overhead, which remains negligible.

Details

AAAI Conference 2025 Conference Paper

DiffuseHigh: Training-Free Progressive High-Resolution Image Synthesis Through Structure Guidance

Younghyun Kim
Geunmin Hwang
Junyu Zhang
Eunbyung Park

Large-scale generative models, such as text-to-image diffusion models, have garnered widespread attention across diverse domains due to their creative and high-fidelity image generation. Nonetheless, existing large-scale diffusion models are confined to generating images of up to 1K resolution, which is far from meeting the demands of contemporary commercial applications. Directly sampling higher-resolution images often yields results marred by artifacts such as object repetition and distorted shapes. Addressing the aforementioned issues typically necessitates training or fine-tuning models on higher-resolution datasets. However, this poses a formidable challenge due to the difficulty in collecting large-scale high-resolution images and substantial computational resources. While several preceding works have proposed alternatives to bypass the cumbersome training process, they often fail to produce convincing results. In this work, we probe the generative ability of diffusion models at higher resolution beyond their original capability and propose a novel progressive approach that fully utilizes generated low-resolution images to guide the generation of higher-resolution images. Additionally, we integrate an image sharpening operation into our pipeline, further enhancing image quality. Our method obviates the need for additional training or fine-tuning which significantly lowers the burden of computational costs. Extensive experiments and results validate the efficiency and efficacy of our method.

PDF Details DOI

ICLR Conference 2025 Conference Paper

DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Models

Chengke Zou
Xingang Guo
Rui Yang
Junyu Zhang
Bin Hu
Huan Zhang

The rapid advancements in Vision-Language Models (VLMs) have shown great potential in tackling mathematical reasoning tasks that involve visual context. Unlike humans who can reliably apply solution steps to similar problems with minor modifications, we found that state-of-the-art VLMs like GPT-4o can consistently fail in these scenarios, revealing limitations in their mathematical reasoning capabilities. In this paper, we investigate the **mathematical reasoning robustness** in VLMs and evaluate how well these models perform under different variants of the same question, such as changes in visual numerical values or function graphs. While several vision-based math benchmarks have been developed to assess VLMs' problem-solving capabilities, these benchmarks contain only static sets of problems and cannot easily evaluate mathematical reasoning robustness. To fill this gap, we introduce **DynaMath**, a dynamic visual math benchmark designed for in-depth assessment of VLMs. **DynaMath** includes 501 high-quality, multi-topic *seed* questions, *each represented as a Python program*. Those programs are carefully designed and annotated to enable the automatic generation of a much larger set of *concrete* questions, including many different types of visual and textual variations. **DynaMath** allows us to evaluate the generalization ability of VLMs, by assessing their performance under varying input conditions of a seed question. We evaluated 14 state-of-the-art VLMs with 5,010 generated concrete questions (10 per seed question). Our results show that the worst-case model accuracy, defined as the percentage of correctly answered seed questions in all 10 variants, is significantly lower than the average-case accuracy. In addition, many models show high consistency in answering these questions -- the incorrectness of a certain variant of a seed question is not only due to inherent randomness. Our analysis emphasizes the need to study the robustness of VLMs' reasoning abilities, and **DynaMath** provides valuable insights to guide the development of more reliable models for mathematical reasoning.

Details

ICML Conference 2025 Conference Paper

EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents

Rui Yang 0010
Hanyang Chen
Junyu Zhang
Mark Zhao
Cheng Qian 0008
Kangrui Wang
Qineng Wang
Teja Venkat Koripella

Leveraging Multi-modal Large Language Models (MLLMs) to create embodied agents offers a promising avenue for tackling real-world tasks. While language-centric embodied agents have garnered substantial attention, MLLM-based embodied agents remain underexplored due to the lack of comprehensive evaluation frameworks. To bridge this gap, we introduce EmbodiedBench, an extensive benchmark designed to evaluate vision-driven embodied agents. EmbodiedBench features: (1) a diverse set of 1, 128 testing tasks across four environments, ranging from high-level semantic tasks (e. g. , household) to low-level tasks involving atomic actions (e. g. , navigation and manipulation); and (2) six meticulously curated subsets evaluating essential agent capabilities like commonsense reasoning, complex instruction understanding, spatial awareness, visual perception, and long-term planning. Through extensive experiments, we evaluated 24 leading proprietary and open-source MLLMs within EmbodiedBench. Our findings reveal that: MLLMs excel at high-level tasks but struggle with low-level manipulation, with the best model, GPT-4o, scoring only $28. 9\%$ on average. EmbodiedBench provides a multifaceted standardized evaluation platform that not only highlights existing challenges but also offers valuable insights to advance MLLM-based embodied agents. Our code and dataset are available at [https: //embodiedbench. github. io](https: //embodiedbench. github. io).

Details

AAMAS Conference 2025 Conference Paper

Incentives for Early Arrival in Cost Sharing

Junyu Zhang
Yao Zhang
Yaoxin Ge
Dengji Zhao
Hu Fu
Zhihao Gavin Tang
Pinyan Lu

In cooperative games, we study how values created or costs incurred by a coalition are shared among the members within it, and the players may join the coalition in a online manner such as investors invest a startup. Recently, Ge et al. [10] proposed a new property called incentives for early arrival (I4EA) in such games, which says that the online allocation of values or costs should incentivize agents to join early in order to prevent mutual strategic waiting. Ideally, the allocation should also be fair, so that agents arriving in an order uniformly at random should expect to get/pay their Shapley values. Ge et al. [10] showed that not all monotone value functions admit such mechanisms in online value sharing games. In this work, we show a sharp contrast in online cost sharing games. We construct a mechanism with all the properties mentioned above, for every monotone cost function. To achieve this, we first solve 0-1 valued cost sharing games with a novel mechanism called Shapley-fair shuffle cost sharing mechanism (SFS-CS), and then extend SFS-CS to a family called generalized Shapley-fair shuffle cost sharing mechanisms (GSFS-CS). The critical technique we invented here is a mapping from one arrival order to another order so that we can directly apply marginal cost allocation on the shuffled orders to satisfy the properties. Finally, we solve general valued cost functions, by decomposing them into 0-1 valued functions in an online fashion.

PDF

ICML Conference 2024 Conference Paper

An Improved Finite-time Analysis of Temporal Difference Learning with Deep Neural Networks

Zhifa Ke
Zaiwen Wen
Junyu Zhang

Temporal difference (TD) learning algorithms with neural network function parameterization have well-established empirical success in many practical large-scale reinforcement learning tasks. However, theoretical understanding of these algorithms remains challenging due to the nonlinearity of the action-value approximation. In this paper, we develop an improved non-asymptotic analysis of the neural TD method with a general $L$-layer neural network. New proof techniques are developed and an improved new $\tilde{\mathcal{O}}(\epsilon^{-1})$ sample complexity is derived. To our best knowledge, this is the first finite-time analysis of neural TD that achieves an $\tilde{\mathcal{O}}(\epsilon^{-1})$ complexity under the Markovian sampling, as opposed to the best known $\tilde{\mathcal{O}}(\epsilon^{-2})$ complexity in the existing literature.

Details

ICLR Conference 2024 Conference Paper

Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design

Heng Dong 0001
Junyu Zhang
Chongjie Zhang

Multi-cellular robot design aims to create robots comprised of numerous cells that can be efficiently controlled to perform diverse tasks. Previous research has demonstrated the ability to generate robots for various tasks, but these approaches often optimize robots directly in the vast design space, resulting in robots with complicated morphologies that are hard to control. In response, this paper presents a novel coarse-to-fine method for designing multi-cellular robots. Initially, this strategy seeks optimal coarse-grained robots and progressively refines them. To mitigate the challenge of determining the precise refinement juncture during the coarse-to-fine transition, we introduce the Hyperbolic Embeddings for Robot Design (HERD) framework. HERD unifies robots of various granularity within a shared hyperbolic space and leverages a refined Cross-Entropy Method for optimization. This framework enables our method to autonomously identify areas of exploration in hyperbolic space and concentrate on regions demonstrating promise. Finally, the extensive empirical studies on various challenging tasks sourced from EvoGym show our approach's superior efficiency and generalization capability.

Details

JMLR Journal 2024 Journal Article

On the Sample Complexity and Metastability of Heavy-tailed Policy Search in Continuous Control

Amrit Singh Bedi
Anjaly Parayil
Junyu Zhang
Mengdi Wang
Alec Koppel

Reinforcement learning is a framework for interactive decision-making with incentives sequentially revealed across time without a system dynamics model. Due to its scaling to continuous spaces, we focus on policy search where one iteratively improves a parameterized policy with stochastic policy gradient (PG) updates. In tabular Markov Decision Problems (MDPs), under persistent exploration and suitable parameterization, global optimality may be obtained. By contrast, in continuous space, the non-convexity poses a pathological challenge as evidenced by existing convergence results being mostly limited to stationarity or arbitrary local extrema. To close this gap, we step towards persistent exploration in continuous space through policy parameterizations defined by distributions of heavier tails defined by tail-index parameter $\alpha$, which increases the likelihood of jumping in state space. Doing so invalidates smoothness conditions of the score function common to PG. Thus, we establish how the convergence rate to stationarity depends on the policy's tail index $\alpha$, a Hölder continuity parameter, integrability conditions, and an exploration tolerance parameter introduced here for the first time. Further, we characterize the dependence of the set of local maxima on the tail index through an exit and transition time analysis of a suitably defined Markov chain, identifying that policies associated with Lévy Processes of a heavier tail converge to wider peaks. This phenomenon yields improved stability to perturbations in supervised learning, which we corroborate also manifests in improved performance of policy search, especially when myopic and farsighted incentives are misaligned. [abs] [ pdf ][ bib ] &copy JMLR 2024. ( edit, beta )

PDF Details

NeurIPS Conference 2023 Conference Paper

Contrastive Sampling Chains in Diffusion Models

Junyu Zhang
Daochang Liu
Shichao Zhang
Chang Xu

The past few years have witnessed great success in the use of diffusion models (DMs) to generate high-fidelity images with the help of stochastic differential equations (SDEs). However, discretization error is an inevitable limitation when utilizing numerical solvers to solve SDEs. To address this limitation, we provide a theoretical analysis demonstrating that an appropriate combination of the contrastive loss and score matching serves as an upper bound of the KL divergence between the true data distribution and the model distribution. To obtain this bound, we utilize a contrastive loss to construct a contrastive sampling chain to fine-tuning the pre-trained DM. In this manner, our method reduces the discretization error and thus yields a smaller gap between the true data distribution and our model distribution. Moreover, the presented method can be applied to fine-tuning various pre-trained DMs, both with or without fast sampling algorithms, contributing to better sample quality or slightly faster sampling speeds. To validate the efficacy of our method, we conduct comprehensive experiments. For example, on CIFAR10, when applied to a pre-trained EDM, our method improves the FID from 2. 04 to 1. 88 with 35 neural function evaluations (NFEs), and reduces NFEs from 35 to 25 to achieve the same 2. 04 FID.

PDF Details

AAMAS Conference 2023 Conference Paper

Cost Sharing under Private Valuation and Connection Control

Tianyi Zhang
Junyu Zhang
Sizhe Gu
Dengji Zhao

We consider a cost sharing problem on a weighted undirected graph, where all the nodes want to connect to a special node called source, and they need to share the total cost (weights) of the used edges. Each node except for the source has a private valuation of the connection, and it may block others’ connections by strategically cutting its adjacent edges to reduce its cost share, which may increase the total cost. We aim to design mechanisms to prevent the nodes from misreporting their valuations and cutting their adjacent edges. We first show that it is impossible for such a mechanism to further satisfy budget balance (cover the total cost) and efficiency (maximize social welfare). Then, we design two feasible cost sharing mechanisms that incentivize each node to offer all its adjacent edges and truthfully report its valuation, and also satisfy either budget balance or efficiency.

PDF

ICML Conference 2023 Conference Paper

Offline Meta Reinforcement Learning with In-Distribution Online Adaptation

Jianhao Wang
Jin Zhang 0016
Haozhe Jiang
Junyu Zhang
Liwei Wang
Chongjie Zhang

Recent offline meta-reinforcement learning (meta-RL) methods typically utilize task-dependent behavior policies (e. g. , training RL agents on each individual task) to collect a multi-task dataset. However, these methods always require extra information for fast adaptation, such as offline context for testing tasks. To address this problem, we first formally characterize a unique challenge in offline meta-RL: transition-reward distribution shift between offline datasets and online adaptation. Our theory finds that out-of-distribution adaptation episodes may lead to unreliable policy evaluation and that online adaptation with in-distribution episodes can ensure adaptation performance guarantee. Based on these theoretical insights, we propose a novel adaptation framework, called In-Distribution online Adaptation with uncertainty Quantification (IDAQ), which generates in-distribution context using a given uncertainty quantification and performs effective task belief inference to address new tasks. We find a return-based uncertainty quantification for IDAQ that performs effectively. Experiments show that IDAQ achieves state-of-the-art performance on the Meta-World ML1 benchmark compared to baselines with/without offline adaptation.

Details

ICML Conference 2023 Conference Paper

Symmetry-Aware Robot Design with Structured Subgroups

Heng Dong 0001
Junyu Zhang
Tonghan Wang 0001
Chongjie Zhang

Robot design aims at learning to create robots that can be easily controlled and perform tasks efficiently. Previous works on robot design have proven its ability to generate robots for various tasks. However, these works searched the robots directly from the vast design space and ignored common structures, resulting in abnormal robots and poor performance. To tackle this problem, we propose a Symmetry-Aware Robot Design (SARD) framework that exploits the structure of the design space by incorporating symmetry searching into the robot design process. Specifically, we represent symmetries with the subgroups of the dihedral group and search for the optimal symmetry in structured subgroups. Then robots are designed under the searched symmetry. In this way, SARD can design efficient symmetric robots while covering the original design space, which is theoretically analyzed. We further empirically evaluate SARD on various tasks, and the results show its superior efficiency and generalizability.

Details

NeurIPS Conference 2022 Conference Paper

A Near-Optimal Primal-Dual Method for Off-Policy Learning in CMDP

Fan Chen
Junyu Zhang
Zaiwen Wen

As an important framework for safe Reinforcement Learning, the Constrained Markov Decision Process (CMDP) has been extensively studied in the recent literature. However, despite the rich results under various on-policy learning settings, there still lacks some essential understanding of the offline CMDP problems, in terms of both the algorithm design and the information theoretic sample complexity lower bound. In this paper, we focus on solving the CMDP problems where only offline data are available. By adopting the concept of the single-policy concentrability coefficient $C^*$, we establish an $\Omega\left(\frac{\min\left\{|\mathcal{S}||\mathcal{A}|, |\mathcal{S}|+I\right\} C^*}{(1-\gamma)^3\epsilon^2}\right)$ sample complexity lower bound for the offline CMDP problem, where $I$ stands for the number of constraints. By introducing a simple but novel deviation control mechanism, we propose a near-optimal primal-dual learning algorithm called DPDL. This algorithm provably guarantees zero constraint violation and its sample complexity matches the above lower bound except for an $\tilde{\mathcal{O}}((1-\gamma)^{-1})$ factor. Comprehensive discussion on how to deal with the unknown constant $C^*$ and the potential asynchronous structure on the offline dataset are also included.

PDF Details

AAAI Conference 2022 Conference Paper

Multi-Agent Reinforcement Learning with General Utilities via Decentralized Shadow Reward Actor-Critic

Junyu Zhang
Amrit Singh Bedi
Mengdi Wang
Alec Koppel

We posit a new mechanism for cooperation in multi-agent reinforcement learning (MARL) based upon any nonlinear function of the team’s long-term state-action occupancy measure, i. e. , a general utility. This subsumes the cumulative return but also allows one to incorporate risk-sensitivity, exploration, and priors. We derive the Decentralized Shadow Reward Actor-Critic (DSAC) in which agents alternate between policy evaluation (critic), weighted averaging with neighbors (information mixing), and local gradient updates for their policy parameters (actor). DSAC augments the classic critic step by requiring agents to (i) estimate their local occupancy measure in order to (ii) estimate the derivative of the local utility with respect to their occupancy measure, i. e. , the “shadow reward”. DSAC converges to a stationary point in sublinear rate with high probability, depending on the amount of communications. Under proper conditions, we further establish the non-existence of spurious stationary points for this problem, that is, DSAC finds the globally optimal policy. Experiments demonstrate the merits of goals beyond the cumulative return in cooperative MARL.

PDF Details

JMLR Journal 2021 Journal Article

From Low Probability to High Confidence in Stochastic Convex Optimization

Damek Davis
Dmitriy Drusvyatskiy
Lin Xiao
Junyu Zhang

Standard results in stochastic convex optimization bound the number of samples that an algorithm needs to generate a point with small function value in expectation. More nuanced high probability guarantees are rare, and typically either rely on light-tail noise assumptions or exhibit worse sample complexity. In this work, we show that a wide class of stochastic optimization algorithms for strongly convex problems can be augmented with high confidence bounds at an overhead cost that is only logarithmic in the confidence level and polylogarithmic in the condition number. The procedure we propose, called proxBoost, is elementary and builds on two well-known ingredients: robust distance estimation and the proximal point method. We discuss consequences for both streaming (online) algorithms and offline algorithms based on empirical risk minimization. [abs] [ pdf ][ bib ] &copy JMLR 2021. ( edit, beta )

PDF Details

NeurIPS Conference 2021 Conference Paper

On the Convergence and Sample Efficiency of Variance-Reduced Policy Gradient Method

Junyu Zhang
Chengzhuo Ni
Zheng Yu
Csaba Szepesvari
Mengdi Wang

Policy gradient (PG) gives rise to a rich class of reinforcement learning (RL) methods. Recently, there has been an emerging trend to augment the existing PG methods such as REINFORCE by the \emph{variance reduction} techniques. However, all existing variance-reduced PG methods heavily rely on an uncheckable importance weight assumption made for every single iteration of the algorithms. In this paper, a simple gradient truncation mechanism is proposed to address this issue. Moreover, we design a Truncated Stochastic Incremental Variance-Reduced Policy Gradient (TSIVR-PG) method, which is able to maximize not only a cumulative sum of rewards but also a general utility function over a policy's long-term visiting distribution. We show an $\tilde{\mathcal{O}}(\epsilon^{-3})$ sample complexity for TSIVR-PG to find an $\epsilon$-stationary policy. By assuming the \emph{overparameterization} of policy and exploiting the \emph{hidden convexity} of the problem, we further show that TSIVR-PG converges to global $\epsilon$-optimal policy with $\tilde{\mathcal{O}}(\epsilon^{-2})$ samples.

PDF Details

NeurIPS Conference 2020 Conference Paper

Variational Policy Gradient Method for Reinforcement Learning with General Utilities

Junyu Zhang
Alec Koppel
Amrit Singh Bedi
Csaba Szepesvari
Mengdi Wang

In recent years, reinforcement learning systems with general goals beyond a cumulative sum of rewards have gained traction, such as in constrained problems, exploration, and acting upon prior experiences. In this paper, we consider policy optimization in Markov Decision Problems, where the objective is a general utility function of the state-action occupancy measure, which subsumes several of the aforementioned examples as special cases. Such generality invalidates the Bellman equation. As this means that dynamic programming no longer works, we focus on direct policy search. Analogously to the Policy Gradient Theorem \cite{sutton2000policy} available for RL with cumulative rewards, we derive a new Variational Policy Gradient Theorem for RL with general utilities, which establishes that the gradient may be obtained as the solution of a stochastic saddle point problem involving the Fenchel dual of the utility function. We develop a variational Monte Carlo gradient estimation algorithm to compute the policy gradient based on sample paths. Further, we prove that the variational policy gradient scheme converges globally to the optimal policy for the general objective, and we also establish its rate of convergence that matches or improves the convergence rate available in the case of RL with cumulative rewards.

PDF Details

ICML Conference 2019 Conference Paper

A Composite Randomized Incremental Gradient Method

Junyu Zhang
Lin Xiao

We consider the problem of minimizing the composition of a smooth function (which can be nonconvex) and a smooth vector mapping, where both of them can be express as the average of a large number of components. We propose a composite randomized incremental gradient method by extending the SAGA framework. The gradient sample complexity of our method matches that of several recently developed methods based on SVRG in the general case. However, for structured problems where linear convergence rates can be obtained, our method can be much better for ill-conditioned problems. In addition, when the finite-sum structure only appear for the inner mapping, the sample complexity of our method is the same as that of SAGA for minimizing finite sum of smooth nonconvex functions, despite the additional outer composition and the stochastic composite gradients being biased in our case.

Details

NeurIPS Conference 2019 Conference Paper

A Stochastic Composite Gradient Method with Incremental Variance Reduction

Junyu Zhang
Lin Xiao

We consider the problem of minimizing the composition of a smooth (nonconvex) function and a smooth vector mapping, where the inner mapping is in the form of an expectation over some random variable or a finite sum. We propose a stochastic composite gradient method that employs incremental variance-reduced estimators for both the inner vector mapping and its Jacobian. We show that this method achieves the same orders of complexity as the best known first-order methods for minimizing expected-value and finite-sum nonconvex functions, despite the additional outer composition which renders the composite gradient estimator biased. This finding enables a much broader range of applications in machine learning to benefit from the low complexity of incremental variance-reduction methods.

PDF Details