Searcharxiv⌕ Search

arXiv subjects

Junzhe Zhang

Publications and source records attributed to Junzhe Zhang.

At least 19 recordsLinked to original sources
arXiv2026

Differentiable Causal Discovery for Singular Linear Models under Confounding

Score-based causal discovery in the presence of unobserved confounders requires both a consistent scoring criterion and an efficient search over graph structures. Linear causal models with correlated errors are naturally represented by acyclic directed mixed graphs (ADMGs), whose induced model families include singular statistical models for which the standard Bayesian Information Criterion is inconsistent. We develop a score-based framework for causal discovery over linear Gaussian ADMGs grounded in singular learning theory. We first verify that the conditions for consistency of the Widely Applicable Bayesian Information Criterion (WBIC) are satisfied by the linear causal model class. We then propose a scalable approximation of the WBIC via Automatic Differentiation Variational Inference (ADVI). Finally, we introduce a differentiable search over ADMGs through Gumbel-Softmax relaxations of both directed and bidirected adjacency. Experiments on synthetic and real-world benchmarks demonstrate improvements over the BIC-scored baseline on both singular and generic ADMGs under unobserved confounding.

cs.LG↗
arXiv2026

Causal Variational Deep Embedding: A Family of Interventional Generators for Confounded Images

Deep generative models reproduce the observational distribution of their training data, inheriting any spurious associations it contains. A common source is an unobserved confounder that shapes both an attribute the user wants to control at sampling time and an attribute expected to vary in response. Existing causal generative approaches resolve the resulting ambiguity by imposing structural assumptions strong enough to single out one interventional distribution; in image domains, such assumptions are rarely warranted, and the data is generally consistent with a set of distinct causal mechanisms -- a feasible region of interventional distributions. We propose CauVaDE (Causal Variational Deep Embedding), built on a canonical augmented SCM in which the unobserved confounder collapses, without loss of generality, into a discrete latent cluster of bounded support while continuous variation is absorbed into independent noises. We prove that this canonical class is dense, in both observational and interventional Wasserstein distance, in the class of augmented SCMs compatible with a given causal diagram, and instantiate it as a mixture variational autoencoder whose cluster variable plays the role of the canonical confounder. An entropy regularizer with weight $γ$ on the cluster posterior then traces a family of candidate causal effects that fit the observational data to comparable likelihood while spanning the feasible region. Experiments on image data benchmarks show that CauVaDE produces diverse interventional samples and improves FID against an unconfounded reference.

cs.LG↗
arXiv2026

Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation

Recent text-to-video (T2V) diffusion models rely heavily on auxiliary reward signals (e.g., via reward models or DPO) to align generated content with human aesthetics and improve realism. These signals, however, incur substantial computational overhead, require costly human annotations, and often yield limited improvement in fine-grained local details. In this paper, we argue that your data manifold is secretly a reward model. By explicitly modeling the manifold structure of high-quality Supervised Fine-Tuning (SFT) data and encouraging video latents to lie on this manifold, we derive dense, differentiable, and nearly cost-free reward signals that significantly improve video quality, particularly in mitigating low-level distortions. Our modeling builds upon Local Coordinate Coding (LCC), which captures the `skeleton' of the manifold. However, directly applying LCC suffers from mean regression, pulling latents toward the geometric mean and losing high-frequency details. We therefore extend it to Shell Local Coordinate Coding (Shell-LCC), which models the manifold `surface' as an isotropic shell to align with the true high-density region. Experiments demonstrate that our approach improves realism, enhances high-frequency details, reduces over-smoothing artifacts, and alleviates motion blur.

cs.CV↗
arXiv2026

An Introduction to Causal Reinforcement Learning

Causal inference provides a set of principles and tools that allow one to combine data and knowledge about an environment to reason with questions of counterfactual nature, i.e., what would have happened had reality been different, even when no data of this unrealized reality is currently available. Reinforcement learning provides methods to learn a policy that optimizes a specific measure (e.g., reward, regret) when the agent is deployed in an environment and pursues an exploratory, trial-and-error approach. These two disciplines have evolved independently and with virtually no interaction between them. We note that they operate over different aspects of the same building block, counterfactual relations, which makes them umbilically connected. Based on these observations, novel learning opportunities arise when this connection is explicitly acknowledged and mathematized. To realize this potential, we note that any environment where the RL agent is deployed can be decomposed as a collection of autonomous mechanisms with different causal invariances, parsimoniously modeled as a structural causal model; any standard RL setting implicitly encodes such a model. This formalization allows us to put under a unifying treatment different modes of learning, including online, off-policy, and causal calculus learning, which appear unrelated in the literature. However, these modalities are not exhaustive: we introduce several natural and pervasive classes of learning settings that entail novel dimensions of analysis. Specifically, we introduce and discuss through causal lenses generalized policy learning, where to intervene, imitation learning, and counterfactual learning. These tasks lead to a broader view of counterfactual learning and suggest great potential for studying causal inference and reinforcement learning side by side, which we call causal reinforcement learning (CRL).

cs.AI↗
arXiv2026

Causal Gaussian Processes for Robust Treatment Effect Evaluation with Unobserved Confounding

The presence of confounding bias poses a key challenge in policy evaluation, as the target causal effects of actions are not identifiable (i.e., underdetermined) from observational data. On the other hand, existing confounding-robust evaluation strategies require detailed prior knowledge about the environment or apply only to discrete treatments and outcomes. This paper investigates causal effect evaluation over the continuous domain from confounded observations, while requiring only basic temporal ordering between the treatment and the outcome. We introduce a universal discretization of the exogenous domains that approximates the observational and interventional distributions of any causal model with arbitrary accuracy using a finite number of latent states. Building on this newfound universal approximation property, we develop a novel family of Causal Gaussian process (CGP) models that effectively approximate the observational and interventional distributions of any causal model with confounded observations.

cs.LG↗
arXiv2026

Constrained Optimization Algorithms for Orbital Optimization in Quantum Chemistry

We present a modular constrained-orbital-optimization framework for quantum chemistry. The formulation separates the correlated electronic-structure solver from the orbital optimizer: the solver supplies one- and two-particle reduced density matrices, while the molecular orbitals are updated on the orthonormality-constrained Stiefel manifold with an implicit steepest-descent algorithm. Because the orbital optimizer only requires reduced density matrices, MP2, CASCI, and DMRG can be treated within the same interface. For CASCI solvers, the approach is closely related to optimal-orbital full configuration interaction and CASSCF\cite{helgaker_MulticonfigurationalSelfConsistentField_2000a}, but uses a solver-independent constrained-optimization update rather than CAS-specific orbital-rotation equations. When conventional CASSCF orbital-rotation iterations converge to higher-energy local solutions, CO-CAS can recover lower-energy stationary solutions. We also introduce a modified direct inversion in the iterative subspace procedure to accelerate macro-iteration convergence and a dynamical-weighting scheme to improve state-averaged excited-state calculations. Applications to LiF, H$_2$O, and pyrazine show that orbital optimization lowers energies relative to fixed-orbital MP2, CASCI, and DMRG references while improving convergence and potential-energy-curve smoothness.

physics.chem-ph↗
arXiv2026

DMC-CF: Dynamic Multimodal CounterFactual QA benchmark for Causal Reasoning

With the rapid advancement of multimodal large language models (MLLMs), models have demonstrated increasingly powerful multimodal capabilities. However, whether MLLMs trained through statistical learning can truly understand the causal relationships underlying the real world remains a key research question. In recent years, numerous multimodal causal reasoning datasets have been proposed. Nevertheless, these datasets are either limited in scale or constructed from synthetic images and videos, cartoon-based content, or other non-realistic multimodal sources. To address these limitations, we collect real-world videos and construct DMC-CF-Static, a large-scale benchmark for multimodal causal counterfactual reasoning. Furthermore, to mitigate issues such as data contamination in traditional static evaluation, we represent causal events using causal graphs and propose the Dynamic Graph Intervention (DGI) framework to build the dynamic evaluation benchmark DMC-CF-Dynamic from DMC-CF-Static. Experimental results on the overall DMC-CF, which includes both static and dynamic evaluation benchmarks, demonstrate that the multimodal causal reasoning capabilities of current multimodal large language models in real-world scenarios still require substantial improvement.

cs.CV↗
arXiv2026

Lagrangian Flow Matching: A Least-Action Framework for Principled Path Design

Flow matching trains a neural velocity field by regression against a target velocity associated with a prescribed probability path connecting a simple initial distribution to the data distribution. A central design choice is the path itself. Existing constructions, including rectified and optimal-transport-based paths, transport samples along straight lines between coupled endpoints and thus cover only a narrow class of dynamics. We observe that this corresponds to the simplest case of the least-action principle in classical mechanics, in which the kinetic Lagrangian yields free-particle straight-line trajectories. Building on this observation, we propose Lagrangian flow matching, a physics-based framework in which the probability path and velocity field are determined by minimizing the action of a general Lagrangian subject to the continuity equation and the prescribed endpoints. We show that this dynamic problem admits an equivalent static optimal transport (OT) formulation, yielding a family of simulation-free training objectives that recover OT-based flow matching as the kinetic special case and the trigonometric variance-preserving diffusion path as the harmonic-oscillator case. More general Lagrangians give rise to new probability paths and velocity fields, and numerical experiments show that they induce meaningful changes in the learned dynamics while remaining competitive with existing conditional flow matching models.

cs.LG↗
arXiv2026

MINOS: A Multimodal Evaluation Model for Bidirectional Generation Between Image and Text

Evaluation is important for multimodal generation tasks, while traditional multimodal evaluation metrics suffer from several limitations. With the rapid progress of MLLMs, there is growing interest in applying MLLMs to build general evaluation systems. However, existing researches often simply collect large-scale evaluation data for training, while overlooking the quality of evaluation data. What's more, current proposed evaluation models often struggle to achieve consistently strong performance across both image-to-text (I2T) and text-to-image (T2I) tasks. In this paper, through rigorous quality control strategies, we construct a comprehensive multimodal evaluation dataset, Minos-57K, with evaluation samples across 15 datasets, for developing the multimodal evaluation model Minos with SFT and preference alignment training strategies. Notably, despite using less than half the scale of the training data of prior work, our model achieves state-of-the-art evaluation performance across 16 out-of-domain datasets covering both I2T and T2I tasks among all open-source multimodal evaluation models and remain competitive with closed-source models. Extensive experiments demonstrate the importance of leveraging quality control process, jointly training on evaluation data from both I2T and T2I generation tasks and further preference alignment.

cs.CL↗
arXiv2026

Causal Flow Q-Learning for Robust Offline Reinforcement Learning

Expressive policies based on flow-matching have been successfully applied in reinforcement learning (RL) more recently due to their ability to model complex action distributions from offline data. These algorithms build on standard policy gradients, which assume that there is no unmeasured confounding in the data. However, this condition does not necessarily hold for pixel-based demonstrations when a mismatch exists between the demonstrator's and the learner's sensory capabilities, leading to implicit confounding biases in offline data. We address the challenge by investigating the problem of confounded observations in offline RL from a causal perspective. We develop a novel causal offline RL objective that optimizes policies' worst-case performance that may arise due to confounding biases. Based on this new objective, we introduce a practical implementation that learns expressive flow-matching policies from confounded demonstrations, employing a deep discriminator to assess the discrepancy between the target policy and the nominal behavioral policy. Experiments across 25 pixel-based tasks demonstrate that our proposed confounding-robust augmentation procedure achieves a success rate 120\% that of confounding-unaware, state-of-the-art offline RL methods.

cs.LG↗
arXiv2026

KBE-DME: Dynamic Multimodal Evaluation via Knowledge Enhanced Benchmark Evolution

The rapid progress of multimodal large language models (MLLMs) calls for more reliable evaluation protocols. Existing static benchmarks suffer from the potential risk of data contamination and saturation, leading to inflated or misleading performance evaluations. To address these issues, we first apply Graph formulation to represent a static or dynamic VQA sample. With the formulation, we propose Knowledge-enhanced Benchmark Evolution(KBE), a dynamic multimodal evaluation framework. KBE first analyzes the original static benchmark, then expands it by integrating multimodal knowledge, transforming the static benchmark into a controllable, dynamic evolving version. Crucially, KBE can both reconstruct questions by Re-selecting visual information in the original image and expand existing questions with external textual knowledge. It enables difficulty-controllable evaluation by adjusting the degree of question exploration. Extensive experiments demonstrate that KBE alleviates the risk of data contamination, data saturation, and provides a more comprehensive assessment of MLLM capabilities.

cs.CV↗
arXiv2026

YODA: Yet Another One-step Diffusion-based Video Compressor

While one-step diffusion models have recently excelled in perceptual image compression, their application to video remains limited. Prior efforts typically rely on pretrained 2D autoencoders that generate per-frame latent representations independently, thereby neglecting temporal dependencies. We present YODA--Yet Another One-step Diffusion-based Video Compressor--which embeds multiscale features from temporal references for both latent generation and latent coding to better exploit spatial-temporal correlations for more compact representation, and employs a linear Diffusion Transformer (DiT) for efficient one-step denoising. YODA achieves state-of-the-art perceptual performance, consistently outperforming traditional and deep-learning baselines on LPIPS, DISTS, FID, and KID. Source code will be publicly available at https://github.com/NJUVISION/YODA.

eess.IV↗
arXiv2025

Confounding Robust Deep Reinforcement Learning: A Causal Approach

A key task in Artificial Intelligence is learning effective policies for controlling agents in unknown environments to optimize performance measures. Off-policy learning methods, like Q-learning, allow learners to make optimal decisions based on past experiences. This paper studies off-policy learning from biased data in complex and high-dimensional domains where \emph{unobserved confounding} cannot be ruled out a priori. Building on the well-celebrated Deep Q-Network (DQN), we propose a novel deep reinforcement learning algorithm robust to confounding biases in observed data. Specifically, our algorithm attempts to find a safe policy for the worst-case environment compatible with the observations. We apply our method to twelve confounded Atari games, and find that it consistently dominates the standard DQN in all games where the observed input to the behavioral and target policies mismatch and unobserved confounders exist.

cs.AI↗
arXiv2025

Partial Identification Approach to Counterfactual Fairness Assessment

The wide adoption of AI decision-making systems in critical domains such as criminal justice, loan approval, and hiring processes has heightened concerns about algorithmic fairness. As we often only have access to the output of algorithms without insights into their internal mechanisms, it was natural to examine how decisions would alter when auxiliary sensitive attributes (such as race) change. This led the research community to come up with counterfactual fairness measures, but how to evaluate the measure from available data remains a challenging task. In many practical applications, the target counterfactual measure is not identifiable, i.e., it cannot be uniquely determined from the combination of quantitative data and qualitative knowledge. This paper addresses this challenge using partial identification, which derives informative bounds over counterfactual fairness measures from observational data. We introduce a Bayesian approach to bound unknown counterfactual fairness measures with high confidence. We demonstrate our algorithm on the COMPAS dataset, examining fairness in recidivism risk scores with respect to race, age, and sex. Our results reveal a positive (spurious) effect on the COMPAS score when changing race to African-American (from all others) and a negative (direct causal) effect when transitioning from young to old age.

cs.LG↗
arXiv2025

Automatic Reward Shaping from Confounded Offline Data

A key task in Artificial Intelligence is learning effective policies for controlling agents in unknown environments to optimize performance measures. Off-policy learning methods, like Q-learning, allow learners to make optimal decisions based on past experiences. This paper studies off-policy learning from biased data in complex and high-dimensional domains where \emph{unobserved confounding} cannot be ruled out a priori. Building on the well-celebrated Deep Q-Network (DQN), we propose a novel deep reinforcement learning algorithm robust to confounding biases in observed data. Specifically, our algorithm attempts to find a safe policy for the worst-case environment compatible with the observations. We apply our method to twelve confounded Atari games, and find that it consistently dominates the standard DQN in all games where the observed input to the behavioral and target policies mismatch and unobserved confounders exist.

cs.AI↗
arXiv2025

Exploring Causal Effect of Social Bias on Faithfulness Hallucinations in Large Language Models

Large language models (LLMs) have achieved remarkable success in various tasks, yet they remain vulnerable to faithfulness hallucinations, where the output does not align with the input. In this study, we investigate whether social bias contributes to these hallucinations, a causal relationship that has not been explored. A key challenge is controlling confounders within the context, which complicates the isolation of causality between bias states and hallucinations. To address this, we utilize the Structural Causal Model (SCM) to establish and validate the causality and design bias interventions to control confounders. In addition, we develop the Bias Intervention Dataset (BID), which includes various social biases, enabling precise measurement of causal effects. Experiments on mainstream LLMs reveal that biases are significant causes of faithfulness hallucinations, and the effect of each bias state differs in direction. We further analyze the scope of these causal effects across various models, specifically focusing on unfairness hallucinations, which are primarily targeted by social bias, revealing the subtle yet significant causal effect of bias on hallucination generation.

cs.CL↗
arXiv2025

ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs

Large language models (LLMs) excel at various natural language processing tasks, but their tendency to generate hallucinations undermines their reliability. Existing hallucination detection methods leveraging hidden states predominantly focus on static and isolated representations, overlooking their dynamic evolution across layers, which limits efficacy. To address this limitation, we shift the focus to the hidden state update process and introduce a novel metric, the ICR Score (Information Contribution to Residual Stream), which quantifies the contribution of modules to the hidden states' update. We empirically validate that the ICR Score is effective and reliable in distinguishing hallucinations. Building on these insights, we propose a hallucination detection method, the ICR Probe, which captures the cross-layer evolution of hidden states. Experimental results show that the ICR Probe achieves superior performance with significantly fewer parameters. Furthermore, ablation studies and case analyses offer deeper insights into the underlying mechanism of this method, improving its interpretability.

cs.CL↗
arXiv2025

How Much To Guide: Revisiting Adaptive Guidance in Classifier-Free Guidance Text-to-Vision Diffusion Models

With the rapid development of text-to-vision generation diffusion models, classifier-free guidance has emerged as the most prevalent method for conditioning. However, this approach inherently requires twice as many steps for model forwarding compared to unconditional generation, resulting in significantly higher costs. While previous study has introduced the concept of adaptive guidance, it lacks solid analysis and empirical results, making previous method unable to be applied to general diffusion models. In this work, we present another perspective of applying adaptive guidance and propose Step AG, which is a simple, universally applicable adaptive guidance strategy. Our evaluations focus on both image quality and image-text alignment. whose results indicate that restricting classifier-free guidance to the first several denoising steps is sufficient for generating high-quality, well-conditioned images, achieving an average speedup of 20% to 30%. Such improvement is consistent across different settings such as inference steps, and various models including video generation models, highlighting the superiority of our method.

cs.CV↗