DINOv2 sees the world well enough to guide robots and segment images, but we still do not know what it sees. We conduct the first comprehensive analysis of DINOv2’s representational structure using overcomplete dictionary learning, extracting over 32,000 visual concepts in what constitutes the largest interpretability demonstration for any vision foundation model to date. This method provides the backbone of our study, which unfolds in three parts. In the first part, we analyze how different downstream tasks recruit concepts from our learned dictionary, revealing functional specialization: classification exploits “Elsewhere” concepts that fire everywhere except on target objects, implementing learned negations; segmentation relies exclusively on boundary detectors forming coherent subspaces; depth estimation draws on three distinct monocular cue families matching visual neuroscience principles. Turning to concept geometry and statistics, we find the learned dictionary deviates from ideal near-orthogonal (Grassmannian) structure, exhibiting higher coherence than random baselines. Concept atoms are not aligned with the neuron basis, confirming distributed encoding. We discover antipodal concept pairs that encode opposite semantics (e.g., “white shirt” vs “black shirt”), creating signed semantic axes. Separately, we identify concepts that activate exclusively on register tokens, revealing these encode global scene properties like motion blur and illumination. Across layers, positional information collapses toward a 2D sheet, yet within single images token geometry remains smooth and clustered even after position is removed, putting into question a purely sparse-coding view of representation. To resolve this paradox, we advance a different view: tokens are formed by combining convex mixtures of a few archetypes (e.g., a rabbit among animals, brown among colors, fluffy among textures). Multi-head attention directly implements this construction, with activations behaving like sums of convex regions. In this picture, concepts are expressed by proximity to landmarks and by regions—not by unbounded linear directions. We call this the Minkowski Representation Hypothesis (MRH), and we examine its empirical signals and consequences for how we study, steer, and interpret vision-transformer representations.
论文检索
输入标题、作者或关键词，从 7,537 篇学术成果中精准定位
Modeling latent character states is crucial for consistent and engaging role-playing (RP) with large language models (LLMs). Yet, existing prompting-based approaches mainly capture surface actions, often failing to track the latent states that drive interaction. We revisit finite-state machines (FSMs), long used in game design to model state transitions. While effective in small, well-specified state spaces, traditional hand-crafted, rule-based FSMs struggle to adapt to the open-ended semantic space of RP. To address this, we introduce Codified Finite-State Machines (CFSMs), a framework that automatically codifies textual character profiles into FSMs using LLM-based coding. CFSMs extract key states and transitions directly from the profile, producing interpretable structures that enforce character consistency. To further capture uncertainty and variability, we extend CFSMs into Codified Probabilistic Finite-State Machines (CPFSMs), where transitions are modeled as probability distributions over states. Through both synthetic evaluations and real-world RP scenarios in established artifacts, we demonstrate that CFSM and CPFSM outperform generally applied baselines, verifying effectiveness not only in structured tasks but also in open-ended stochastic state exploration.
Social Aspects · Accountability, Transparency and Interpretability
The ubiquity of closed-weight language models with public-facing APIs has generated interest in forensic methods, both for extracting hidden model details (e.g., parameters) and identifying models by their outputs. One successful approach to these goals has been to exploit the geometric constraints imposed by the language model architecture and parameters. In this work, we show that a lesser-known geometric constraint—namely that language model outputs lie on the surface of a high-dimensional ellipse—functions as a signature for the model, which be used to identify which model an output came from. This ellipse signature has unique properties that distinguish it from existing model-output association methods like language model watermarks. In particular, the signature is hard to forge: without direct access to model parameters, it is practically infeasible to produce logprobs on the ellipse. Secondly, the signature is naturally occurring, since all language models have these elliptical constraints. Thirdly, the signature is self-contained, in that it is detectable without access to the model input or full weights. Finally, the signature is exceptionally redundant, as it is independently detectable in every single logprob output from the model. We evaluate a novel technique for extracting the ellipse on small models, and discuss the practical hurdles that make it infeasible for production-size models, making the signature hard to forge. Finally, we use ellipse signatures to propose a protocol for language model output verification, which is analogous to cryptographic symmetric-key message authentication systems.
Diagrams represent a form of visual language that encodes abstract concepts and relationships through structured symbols and their spatial arrangements. Unlike natural images, they are inherently symbolic, and entirely artificial. They thus pose unique challenges for Multimodal Large Language Models (MLLMs) distinct from natural image processing. Recent studies have shown that MLLMs often exhibit flawed reasoning and hallucinations when handling diagram inputs. We investigate here whether these limitations stem from shortcomings in the models' ability to interpret diagrams themselves. To this end, we develop a diagnostic test suite that isolates perception from reasoning. Our systematic evaluation reveals that MLLMs perform poorly on basic perceptual tasks, e.g., shape classification, object counting, relationship identification, and object grounding, with near-zero accuracy on fine-grained grounding. Further analysis shows that weak diagram perception leads to ``blind faith in text", where models rely on textual shortcuts rather than visual understanding (that is, they are $\textit{Math Blind}$). We hypothesize that enabling models to capture the inherent structural properties of diagrams, represented as graphs of primitives and their interrelationships, is essential for improving diagram understanding. Experiments with 7B and 32B MLLMs validate this assumption, with models trained on such representations achieving a +79\% gain on the grounding task. Crucially, these gains transfer to reasoning, achieving 3–4\% cross-suite improvements on four public benchmarks even without additional chain-of-thought reasoning data. Our findings demonstrate that low-level perception supports faithful high-level reasoning in mathematical MLLMs. We provide both methodological frameworks and empirical evidence to guide future research in this direction. Our project page is at \href{https://vi-ocean.github.io/projects/MATHEMETRIC/index.html}{\color{blue}{viocean/\ourMethod}}.
This paper presents *the first study of grokking in practical LLM pretraining*. Specifically, we investigate when an LLM memorizes the training data, when its generalization on downstream tasks starts to improve, and what happens if there is a lag between the two. Unlike existing works studying when a small model generalizes to limited and specified tasks during thousands epochs' training on algorithmic data, we focus on a practical setting for LLMs, i.e., near single-pass pretraining of next-token prediction on a cross-domain, large-scale corpus, and generalization on diverse benchmark tasks covering math/commonsense reasoning, code generation, and domain-specific retrieval. Our study, *for the first time, verifies that grokking still emerges in pretraining mixture-of-experts (MoE) LLMs*, though different local data groups may enter their grokking stages asynchronously due to the heterogeneity of their distributions and attributions to others. To find a mechanistic interpretation of this local grokking, we investigate the dynamics of training data's pathways (i.e., expert choices across layers in MoE). Our primary discovery is that *the pathways evolve from random, non-smooth across layers, instance-specific to more structured and transferable across samples*, despite the converged pretraining loss. This depicts a transition from memorization to generalization. Two novel metrics are developed to quantify these patterns: one computes the pathway similarity between samples, while the other measures the consistency of aggregated experts between subsequent layers for each sample. These training data based metrics induce near zero cost but can faithfully track and monitor the generalization of LLMs on downstream tasks, reducing reliance on costly instruction tuning and benchmark evaluations. We also ground our findings in a theoretical analysis of one-layer MoE, showing that more structured pathways improve the generalization bound.
Personalized image preference assessment aims to evaluate an individual user's image preferences by relying only on a small set of reference images as prior information. Existing methods mainly focus on general preference assessment, training models with large-scale data to tackle well-defined tasks such as text-image alignment. However, these approaches struggle to handle personalized preference because user-specific data are scarce and not easily scalable, and individual tastes are often diverse and complex. To overcome these challenges, we introduce a common preference profile that serves as a bridge across users, allowing large-scale user data to be leveraged for training profile prediction and capturing complex personalized preferences. Building on this idea, we propose a reasoning-based personalized image preference assessment framework that follows a \textit{predict-then-assess} paradigm: it first predicts a user's preference profile from reference images, and then provides interpretable, multi-dimensional scores and assessments of candidate images based on the predicted profile. To support this, we first construct a large-scale Chain-of-Thought (CoT)-style personalized assessment dataset annotated with diverse user preference profiles and high-quality CoT-style reasoning, enabling explicit supervision of structured reasoning. Next, we adopt a two-stage training strategy: a cold-start supervised fine-tuning phase to empower the model with structured reasoning capabilities, followed by reinforcement learning to incentivize the model to explore more reasonable assessment paths and enhance generalization. Furthermore, we propose a similarity-aware prediction reward to encourage better prediction of the user's preference profile, which facilitates more reasonable assessments exploration. Extensive experiments demonstrate the superiority of the proposed method. Our code and dataset will be publicly released.
Alpha mining seeks to identify predictive alpha factors that generate excess returns relative to the market from a vast and noisy search space; however, existing evolution-based approaches struggle to facilitate the systematic evolution of alphas. Traditional methods, such as Genetic Programming (GP), cannot interpret natural language instructions and often fail to extract valuable insights from unsuccessful attempts, leading to low interpretability and inefficient exploration. Analogously, without mechanisms for systematic evolution, e.g., long-term planning and reflection, existing multi-agent approaches may easily fall into repetitive evolutionary routines, resulting in inefficient evolution. To overcome these limitations, we introduce AlphaAgentEvo, a self-evolving Agentic Reinforcement Learning (ARL) framework for alpha mining, which moves alpha mining beyond the brittle search-backtest-restart cycle toward a continuous trajectory of evolution. Guided by a hierarchical reward function, our agent engages in self-exploration of the search space, progressively learning basic requirements (e.g., valid tool calls) and then harder objectives (e.g., continuous performance improvements). Through this process, the agent acquires advanced behaviors such as long-horizon planning and reflective reasoning, which enable it to actively react to the underlying state (e.g., market regime shifts) and realize a self-evolving agent, marking a step toward more principled and scalable alpha mining. Extensive experiments demonstrate that AlphaAgentEvo achieves more efficient alpha evolution and generates diverse and transferable alphas, consistently surpassing a wide range of baselines. Notably, with only 4B parameters, it outperforms LLM-driven evolution methods configured with state-of-the-art closed-source reasoning models, highlighting the promise of ARL for next-generation alpha mining.
Recent advancements in Large Multimodal Models (LMMs) have significantly improved multimodal understanding and generation. However, these models still struggle to generate tightly interleaved image-text outputs, primarily due to the limited scale, quality and instructional richness of current training datasets. To address this, we introduce \textbf{InterSyn}, a dataset that features: (1) large scale, comprising 1.8M multimodal samples; (2) high quality, supported by our proposed \textbf{Self-Evaluation with Iterative Refinement (SEIR)} method for rigorous automated quality refinement; (3) rich instructional diversity, ensured through diverse well-designed question templates, based on human preferences and covering a 3500-topic hierarchy. These characteristics make InterSyn particularly well-suited for training LMMs in interactive image–text generation capabilities. To evaluate the capabilities, we propose \textbf{SynJudge}, a reliable automatic evaluator that aligns closely with human judge and outputs four interpretable scores: Text Content Completeness (TCC), Image Content Completeness (ICC), Image Quality (IQ), and Image–Text Synergy (ITS). These scores are complementary, covering both content and quality as well as cross-modal interaction, thereby forming a comprehensive evaluation framework. Experimental results on InterSyn subsets of up to 200K samples show that 25K–50K already yield substantial improvements, while scaling to 100K/200K brings further gains in TCC, ICC, and especially ITS, highlighting InterSyn’s: (1) scalability, as performance consistently improves with more data; (2) efficiency, as significant gains are achievable even with smaller subsets, making it accessible to researchers with varying computational resources.
Large Vision Language Models (LVLMs) have recently emerged as powerful architectures capable of understanding and reasoning over both visual and textual information. These models typically rely on two key components: a Vision Transformer (ViT) and a Large Language Model (LLM). ViT encodes visual content into a sequence of image tokens and serves as the perceptual front-end -- the eyes of the model. In contrast, the LLM interprets these tokens to perform high-level reasoning, generates responses, and functions as the cognitive core -- the brain of the model. However, it remains unclear which visual tokens contribute most significantly to understanding and reasoning, and how effectively these signals are propagated from ViT to the LLM. While most existing works have focused on identifying attention sinks, low-semantic tokens receiving disproportionately high attention, within the LLM, we shift the focus to the vision encoder by identifying a class of high-norm visual tokens from ViT, referred to as ViT attention sinks -- a problem that has been rarely studied but is indeed very important for LVLMs. Our findings show that these ViT sinks encapsulate high-level semantic concepts from images, allowing the LLM to perform more effective understanding and reasoning. Despite their importance, these sink tokens are often overlooked in existing LVLM architectures. To explore their contribution, we present both qualitative and quantitative analyses of the information embedded in these sink tokens. We also propose both training-free and training-based approaches to better leverage how this information is interpreted by the LLM, and to what extent. By explicitly utilizing these tokens, we demonstrate substantial improvements across a range of LVLMs and visual reasoning tasks, including but not limited to mathematical problem solving, logical inference, and geometric understanding, highlighting the untapped potential of ViT attention sinks in enhancing visual reasoning.
The vulnerability of deep neural networks to adversarial examples poses significant challenges to their reliable deployment. Among existing empirical defenses, adversarial training and robust distillation have proven the most effective. In this paper, we identify a property originally associated with model intellectual property, i.e., probability sparsity induced by nasty training, and demonstrate that it can also provide interpretable improvements to adversarial robustness. We begin by analyzing how nasty training induces sparse probability distributions and qualitatively explore the spatial metric preferences this sparsity introduces to the model. Building on these insights, we propose a simple yet effective adversarial training method, nasty adversarial training (NAT), which incorporates probability sparsity as a regularization mechanism to boost adversarial robustness. Both theoretical analysis and experimental results validate the effectiveness of NAT, highlighting its potential to enhance the adversarial robustness of deep neural networks in an interpretable manner.
Controlling the behaviors of large language models (LLMs) is fundamental to their safety alignment and reliable deployment. However, existing steering methods are primarily driven by empirical insights and lack theoretical performance guarantees. In this work, we develop a control-theoretic foundation for activation steering by showing that popular steering methods correspond to the proportional (P) controllers, with the steering vector serving as the feedback signal. Building on this finding, we propose Proportional-Integral-Derivative (PID) Steering, a principled framework that leverages the full PID controller for activation steering in LLMs. The proportional (P) term aligns activations with target semantic directions, the integral (I) term accumulates errors to enforce persistent corrections across layers, and the derivative (D) term mitigates overshoot by counteracting rapid activation changes. This closed-loop design yields interpretable error dynamics and connects activation steering to classical stability guarantees in control theory. Moreover, PID Steering is lightweight, modular, and readily integrates with state-of-the-art steering methods. Extensive experiments across multiple LLM families and benchmarks demonstrate that PID Steering consistently outperforms existing approaches, achieving more robust and reliable behavioral control.
Reinforcement Learning · Inverse
Inverse Reinforcement Learning aims to recover reward models from expert demonstrations, but traditional methods yield black-box models that are difficult to interpret and debug. In this work, we introduce GRACE (**G**enerating **R**ewards **A**s **C**od**E**), a method for using Large Language Models within an evolutionary search to reverse-engineer an interpretable, code-based reward function directly from expert trajectories. The resulting reward function is executable code that can be inspected and verified. We empirically validate GRACE on the MuJoCo, BabyAI and AndroidWorld benchmarks, where it efficiently learns highly accurate rewards, even in complex, multi-task settings. Further, we demonstrate that the resulting reward leads to strong policies, compared to both competitive Imitation Learning and online RL approaches with ground-truth rewards. Finally, we show that GRACE is able to build complex reward APIs in multi-task setups.
Theory · Interpretability and Visualization
Data filtering plays a central role in improving model performance, particularly for vision language models that are pretrained on large, noisy, and redundant image-caption datasets. Existing filtering techniques assess every sample individually and retain those that exceed a certain quality threshold, but such strategies fail to capture higher-order interactions. In this work, we propose a novel submodular framework for data selection that addresses this limitation. Our method, Submodular Distribution Matching (SDM), selects a subset by: (1) training a type of sparse autoencoder to learn disentangled and \emph{monotone} features; (2) estimating a target feature distribution from a target dataset; and (3) selecting a subset of samples whose feature distribution closely matches the target via submodular maximization. Given the DataComp-medium training set and no external models, SDM achieves state-of-the-art accuracy on both ImageNet-1K and average performance across 38 downstream tasks. On the full DataComp-medium benchmark, SDM delivers performance within 1\% of the state-of-the-art results while using over \textbf{\emph{5×}} fewer GPU hours than the leading approach.
Theory · Interpretability and Visualization
Leveraging the intrinsic importance differences among experts, recent research has explored expert-level compression techniques to enhance the efficiency of Mixture-of-Experts (MoE) large language models (LLMs). However, existing approaches often rely on empirical heuristics to identify critical experts, while lacking a deeper understanding into the heterogeneous importance of experts and the inner workings of MoE LLMs. In this study, we report, for the first time, the discovery and systematic investigation of a distinct subset of experts that play a pivotal role in the model's forward inference. These experts are prevalent in open-source MoE LLMs, and despite their extremely limited number, pruning them results in a substantial decline in model performance (e.g., prune just three out of 6,144 causes Qwen3-30B-A3B to generate repetitive and uninformative outputs). We refer to these experts as Super Experts (SEs). Our comprehensive analysis provides progressively deeper insights into SEs: (i) SEs are characterized by rare but extreme activation outliers in the output of the down\_proj, which give rise to massive activations in the hidden states between decoder layers. Moreover, the distribution of SEs is model-specific, data-agnostic, and remains unaffected by post-training processes. (ii) By pruning SEs, we assess their significance across a variety of tasks, revealing their considerable impact on the model's overall performance, particularly in mathematical reasoning. (iii) We further investigate why compressing SEs exerts such a pronounced impact. We show that, in MoE LLMs, SEs serve as the primary source of the systematic outlier mechanism in Transformers, and that compressing them profoundly disrupts this process, ultimately causing the collapse of attention sinks. These findings advance the understanding of the internal dynamics of MoE LLMs, filling an important gap in the current knowledge. In addition, we developed an automated tool for rapid and accurate SE profiling. The code is provided in the supplementary materials.
Theory · Interpretability and Visualization
Sparse autoencoders (SAEs) are widely used to extract sparse, interpretable latents from transformer activations. We test whether commonly used SAE quality metrics and automatic explanation pipelines can distinguish trained transformers from randomly initialized ones (e.g., where parameters are sampled i.i.d. from a Gaussian). Over a wide range of Pythia model sizes and multiple randomization schemes, we find that, in many settings, SAEs trained on randomly initialized transformers produce auto-interpretability scores and reconstruction metrics that are similar to those from trained models. These results show that high aggregate auto-interpretability scores do not, by themselves, guarantee that learned, computationally relevant features have been recovered. We therefore recommend treating common SAE metrics as useful but insufficient proxies for mechanistic interpretability and argue for routine randomized baselines and targeted measures of feature 'abstractness'.
Social Aspects · Accountability, Transparency and Interpretability
Graph Neural Networks (GNNs) achieve strong predictive performance but offer limited transparency in their decision-making. Self-Interpretable GNNs (SI-GNNs) address this by generating built-in explanations, yet their training objectives are misaligned with evaluation criteria such as faithfulness. This raises two key questions: (i) can faithfulness be explicitly optimized during training, and (ii) does such optimization truly improve explanation quality? We show that faithfulness is intrinsically tied to explanation self-consistency and can therefore be optimized directly. Empirical analysis further reveals that self-inconsistency predominantly occurs on unimportant features, linking it to redundancy-driven explanation inconsistency observed in recent work and suggesting untapped potential for improving explanation quality. Building on these insights, we introduce a simple, model-agnostic self-consistency (SC) fine-tuning strategy. Without changing model architectures, SC consistently improves explanation quality across multiple dimensions and benchmarks, offering an effective and scalable pathway to more trustworthy GNN explanations. Our code is publicly available at \url{https://github.com/ICDM-UESTC/SelfConsistencyXGNN}.
Social Aspects · Accountability, Transparency and Interpretability
Contrastive learning, commonly applied in large-scale multimodal models, often relies on data from diverse and often unreliable sources, which can include misaligned or mislabeled text-image pairs. This frequently leads to robustness issues and hallucinations, ultimately causing performance degradation. Data valuation is an efficient way to detect and trace these misalignments. Nevertheless, existing methods are computationally expensive for large-scale models. Although computationally efficient, classical influence functions are inadequate for contrastive learning models, as they were initially designed for pointwise loss. Furthermore, contrastive learning involves minimizing the distance between positive sample modalities while maximizing the distance between negative sample modalities. This necessitates evaluating the influence of samples from both perspectives. To tackle these challenges, we introduce the Extended Influence Function for Contrastive Loss (ECIF), an influence function crafted for contrastive loss. ECIF considers both positive and negative samples and provides a closed-form approximation of contrastive learning models, eliminating the need for retraining. Building upon ECIF, we develop a series of algorithms for data evaluation, misalignment detection, and misprediction trace-back tasks. Experimental results demonstrate that our ECIF advances the transparency and interpretability of CLIP-style embedding models by offering a more accurate assessment of data impact and model alignment compared to traditional baseline methods.
Social Aspects · Accountability, Transparency and Interpretability
As one of the most fundamental models, meta learning aims to effectively address few-shot learning challenges. However, it still faces significant issues related to the training data, such as training inefficiencies due to numerous low-contribution tasks in large datasets and substantial noise from incorrect labels. Thus, training data attribution methods are needed for meta learning. However, the dual-layer structure of meta learning complicates the modeling of training data contributions because of the interdependent influence between meta parameters and task-specific parameters, making existing data influence evaluation tools inapplicable or inaccurate. To address these challenges, based on the influence function, we propose a general data attribution evaluation framework for meta learning within the bilevel optimization framework. Our approach introduces task influence functions (task-IF) and instance influence functions (instance-IF) to accurately assess the impact of specific tasks and individual data points in closed forms. This framework comprehensively models data contributions across both the inner and outer training processes, capturing the direct effects of data points on meta parameters as well as their indirect influence through task-specific parameters. We also provide several strategies to enhance computational efficiency and scalability. Experimental results demonstrate the framework's effectiveness in training data evaluation via several downstream tasks.
Social Aspects · Accountability, Transparency and Interpretability
\textit{Learning to Explain} is a forward-looking paradigm recently proposed in the field of explainable AI, which envisions training explainers capable of producing high-quality explanations for target models efficiently. Although existing studies have made attempts through self-supervised optimization or learning from prior explanation methods, the \textit{Learning to Explain} paradigm still faces three critical challenges: 1) self-supervised objectives rely on assumptions about the target model or task, restricting their generalizability; 2) methods driven by prior explanations struggle to guarantee the quality of the supervisory signals; and 3) depending exclusively on either approach leads to poor convergence or limited explanation quality. To address these challenges, we propose a \textit{faithfulness}-guided amortized explainer that 1) theoretically derives a self-supervised objective free from assumptions about the target model or task, 2) practically generates high-quality supervisory signals by deduplicating and filtering prior explanations, and 3) jointly optimizes both objectives via a dynamic weighting strategy, enabling the amortized explainer to produce more faithful explanations for complex, high-dimensional models. We re-formalize multiple well-validated faithfulness evaluation metrics within a unified notation system and theoretically prove that an explanation mapping can simultaneously achieve optimality across all these metrics. We aggregate prior explanation methods to generate high-quality supervised signals through deduplicating and faithfulness-based filtering. Our amortized explainer leverages dynamic weighting to guide optimization, initially emphasizing pattern consistency with the supervised signals for rapid convergence, and subsequently refining explanation quality by approximating the most faithful explanation mapping. Extensive experiments across various target models and image, text, and tabular tasks demonstrate that the proposed explainer consistently outperforms all prior explanation methods across all faithfulness metrics, highlighting its effectiveness and its potential to offer a systematic solution to the fundamental challenges of the \textit{Learning to Explain} paradigm.
Computer Vision · Vision Models & Multimodal
Hateful memes have emerged as a particularly challenging form of online abuse, motivating the development of automated detection systems. Most prior approaches rely on direct detection, producing only binary predictions. Such models fail to provide the context and explanations that real-world moderation requires. Recent Explain-then-Detect approaches, using Chain-of-Thought prompting or LMM agents, perform worse than simple SFT baselines, and even advanced post-training methods such as GRPO fail to close the gap. Our analysis identifies two key issues of such systems: important policy-relevant cues such as targets and attack types are not hypothesized by the model as a likely explanation; and the binary reward signal is insufficient to guide reasoning. To address these challenges, we propose ExPO-HM (Explain-then-Detect Policy Optimization for Hateful Memes), inspired by the training and evaluation process of human annotators. ExPO-HM combines SFT warmup, GRPO with curriculum learning, and Conditional Decision Entropy (CDE) as both metric and reward for reasoning quality. Across three hateful meme benchmarks, ExPO-HM achieves state-of-the-art performance on binary detection, fine-grained classification, and reasoning quality, with up to 15\% and 17\% F1 improvement over the GRPO and DPO baselines, respectively. By moving hateful meme detection from simple binary alarms to explanation-driven detection, ExPO-HM provides accurate, interpretable, and actionable moderation support. Code available at: https://github.com/JingbiaoMei/ExPO-HM