论文检索

Theory · Interpretability and Visualization

Jim Maar, Denis Paperno, Callum McDougall, Neel Nanda

Prior work suggests that language models, while trained on next token prediction, show implicit planning behavior: they may select the next token in preparation to a predicted future token, such as a likely rhyming word, as supported by a prior qualitative study of Claude 3.5 Haiku using a cross-layer transcoder. We propose much simpler techniques for assessing implicit planning in language models. With case studies on rhyme poetry generation and question answering, we demonstrate that our methodology easily scales to many models. Across models, we find that the generated rhyme (e.g. "-ight") or answer to a question ("whale") can be manipulated by steering at the end of the preceding line with a vector, affecting the generation of intermediate tokens leading up to the rhyme or answer word. We show that implicit planning is a universal mechanism, present in smaller models than previously thought, starting from 1B parameters. Our methodology offers a widely applicable direct way to study implicit planning abilities of LLMs. More broadly, understanding planning abilities of language models can inform decisions in AI safety and control.

Applications · Chemistry and Drug Discovery

Zhiyu Wang, Bingxin Zhou, Weishu Zhao, Yang Tan, Jing Wang, Pietro Lio, liang hong

Proteins are essential biological macromolecules that execute life functions. Local motifs within protein structures, such as active sites, are the most critical components for linking structure to function and are key to understanding protein evolution and enabling protein engineering. Existing computational methods struggle to identify and compare these local structures, which leaves a significant gap in understanding protein structures and harnessing their functions. This study presents PLASMA, the first deep learning framework for efficient and interpretable residue-level protein substructure alignment. We reformulate the problem as a regularized optimal transport task and leverage differentiable Sinkhorn iterations. For a pair of input protein structures, PLASMA outputs a clear alignment matrix with an interpretable overall similarity score. Through extensive quantitative evaluations and three biological case studies, we demonstrate that PLASMA achieves accurate, lightweight, and interpretable residue-level alignment. Additionally, we introduce PLASMA-PF, a training-free variant that provides a practical alternative when training data are unavailable. Our method addresses a critical gap in protein structure analysis tools and offers new opportunities for functional annotation, evolutionary studies, and structure-based drug design. Reproducibility is ensured via our official implementation at https://github.com/ZW471/PLASMA-Protein-Local-Alignment.git.

Social Aspects · Everything Else

Ruixin Yang, Ethan Mendes, Arthur Wang, James Hays, Sauvik Das, Wei Xu, Alan Ritter

Vision-language models (VLMs) have demonstrated strong performance in image geolocation, a capability further sharpened by frontier multimodal large reasoning models (MLRMs). This poses a significant privacy risk, as these widely accessible models can be exploited to infer sensitive locations from casually shared photos, often at street-level precision, potentially surpassing the level of detail the sharer consented or intended to disclose. While recent work has proposed applying a blanket restriction on geolocation disclosure to combat this risk, these measures fail to distinguish valid geolocation uses from malicious behavior. Instead, VLMs should maintain contextual integrity by reasoning about elements within an image to determine the appropriate level of information disclosure, balancing privacy and utility. To evaluate how well models respect contextual integrity, we introduce VLM-GEOPRIVACY, a benchmark that challenges VLMs to interpret latent social norms and contextual cues in real-world images and determine the appropriate level of location disclosure. Our evaluation of 14 leading VLMs shows that, despite their ability to precisely geolocate images, the models are poorly aligned with human privacy expectations. They often over-disclose in sensitive contexts and are vulnerable to prompt-based attacks. Our results call for new design principles in multimodal systems to incorporate context-conditioned privacy reasoning.

General Machine Learning · Everything Else

Jairo Diaz-Rodriguez

We introduce k-NLPmeans and k-LLMmeans, text-clustering variants of k-means that periodically replace numeric centroids with textual summaries. The key idea—summary-as-centroid—retains k-means assignments in embedding space while producing human-readable, auditable cluster prototypes. The method is LLM-optional: k-NLPmeans uses lightweight, deterministic summarizers, enabling offline, low-cost, and stable operation; k-LLMmeans is a drop-in upgrade that uses an LLM for summaries under a fixed per-iteration budget whose cost does not grow with dataset size. We also present a mini-batch extension for real-time clustering of streaming text. Across diverse datasets, embedding models, and summarization strategies, our approach consistently outperforms classical baselines and approaches the accuracy of recent LLM-based clustering without extensive LLM calls. Finally, we provide a case study on sequential text streams and release a StackExchange-derived benchmark for evaluating streaming text clustering.

Applications · Chemistry and Drug Discovery

Yanke Li, Tianyu Cui, Tommaso Mansi, Mangal Prakash, Rui Liao

Efficient design of genomic perturbation experiments is crucial for accelerating drug discovery and therapeutic target identification, yet exhaustive perturbation of the human genome remains infeasible due to the vast search space of potential genetic interactions and experimental constraints. Bayesian optimization (BO) has emerged as a powerful framework for selecting informative interventions, but existing approaches often fail to exploit domain-specific biological prior knowledge. We propose Biology-Informed Bayesian Optimization (BioBO), a method that integrates Bayesian optimization with multimodal gene embeddings and enrichment analysis, a widely used tool for gene prioritization in biology, to enhance surrogate modeling and acquisition strategies. BioBO combines biologically grounded priors with acquisition functions in a principled framework, which biases the search toward promising genes while maintaining the ability to explore uncertain regions. Through experiments on established public benchmarks and datasets, we demonstrate that BioBO improves labeling efficiency by 25-40\%, and consistently outperforms conventional BO by identifying top-performing perturbations more effectively. Moreover, by incorporating enrichment analysis, BioBO yields pathway-level explanations for selected perturbations, offering mechanistic interpretability that links designs to biologically coherent regulatory circuits.

Social Aspects · Accountability, Transparency and Interpretability

Xu Shen, Song Wang, Zhen Tan, Laura Yao, Xinyu Zhao, Kaidi Xu, Xin Wang, Tianlong Chen

Large language models (LLMs) increasingly rely on Chain-of-Thought (CoT) prompting to improve problem-solving and provide seemingly transparent explanations. However, growing evidence shows that CoT often fail to faithfully represent the underlying reasoning process, raising concerns about their reliability in high-risk applications. Although prior studies have focused on mechanism-level analyses showing that CoTs can be unfaithful, they leave open the practical challenge of deciding whether a specific trajectory is faithful to the internal reasoning of the model. To address this gap, we introduce FaithCoT-Bench, a unified benchmark for instance-level CoT unfaithfulness detection. Our framework establishes a rigorous task formulation that formulates unfaithfulness detection as a discriminative decision problem, and provides FINE-CoT (Faithfulness instance evaluation for Chain-of-Thought), an expert-annotated collection of over 1,000 trajectories generated by four representative LLMs across four domains, including more than 300 unfaithful instances with fine-grained causes and step-level evidence. We further conduct a systematic evaluation of eleven representative detection methods spanning counterfactual, logit-based, and LLM-as-judge paradigms, deriving empirical insights that clarify the strengths and weaknesses of existing approaches and reveal the increased challenges of detection in knowledge-intensive domains and with more advanced models. To the best of our knowledge, FaithCoT-Bench establishes the first comprehensive benchmark for instance-level CoT faithfulness, setting a solid basis for future research toward more interpretable and trustworthy reasoning in LLMs.

Computer Vision · Image and Video Generation

Sina Malakouti, Boqing Gong, Adriana Kovashka

Cultural nuances are best expressed through social interactions, yet current text-to-image (T2I) benchmarks focus largely on object-centric artifacts (e.g., food, landmarks, and attire). In this work, we study the cultural faithfulness of T2I models (i.e., adherence to the target culture) through social activities. To this end, we introduce CULTIVate, a new benchmark of 576 activities across 9 categories (e.g., dancing, greeting, dining) with over 19,000 images from 16 countries. We further propose AHEaD, an explainable framework that measures cultural understanding along four dimensions: cultural Alignment, Hallucination, Exaggeration, and Diversity. Unlike prior work relying on costly human evaluation or image-text alignment (ITA), AHEaD uses culturally-grounded descriptors to provide quantitative, interpretable feedback that enables iterative image refinement. Our analysis shows ITA metrics correlate poorly with human judgments and that alignment alone is insufficient to capture faithfulness. In contrast, FAITH (combining alignment, hallucination, and exaggeration) achieves 27% higher correlation than baselines. Finally, we observe systematic disparities, with generated images being consistently more faithful for Global North than Global South cultures.

Applications · Health

Zonghai Yao, Benlu Wang, Yifan Zhang, Junda Wang, Iris Xia, Zhipeng Tang, Shuo Han, Feiyun, Zhichao Yang, Arman Cohan 等

Large language models perform well on many medical QA benchmarks, but real clinical reasoning is harder because diagnosis often requires integrating evidence across multiple images rather than interpreting a single view. We introduce MedThinkVQA, an expert-annotated benchmark for thinking with multiple images, in which models must interpret each image, combine cross-view evidence, and solve diagnostic questions under intermediate supervision and step-level evaluation. The dataset contains 10,067 cases, including 720 test cases, with an average of 6.68 images per case, substantially denser than prior work (earlier maxima $\leq$ 1.43). On the test set, the best closed-source models, Claude-4.6-opus, Gemini-3-pro, and GPT-5.2-xhigh, achieve only 54.9%--57.2% accuracy, while smaller proprietary variants, GPT-5-mini/nano, drop to 39.7% and 30.8%. Top open-source models perform worse overall, with Qwen3.5-397B-A17B (52.2%) and Qwen3.5-27B (50.6%) leading, followed by Lingshu-32B (43.2%), InternVL3.5-38B (40.7%), and MedGemma-27B (31.8%). Further analysis points to a single-core bottleneck: current models struggle with grounded multi-image reasoning, i.e., reliably extracting, aligning, and composing evidence across views before higher-level inference can help. This is supported by three consistent findings: adding expert-provided single-image cues and integrating cross-image evidence improve performance, whereas replacing them with models’ self-generated intermediates reduces accuracy. Step-level analysis shows that over 70% of errors come from image reading and cross-view integration, with reasoning failures increasing on decisive steps. Scaling results show that while accuracy increases with more images, additional inference-time computation is beneficial only when the underlying visual grounding is already reliable. When early evidence extraction is weak, longer reasoning yields limited or unstable gains and can even amplify misread cues. Together, these results show that the main barrier is not simply insufficient reasoning length or depth, but the lack of reliable mechanisms for grounding, aligning, and composing distributed evidence across real-world, cross-view, multimodal clinical inputs.

Applications · Time Series

Daojun Liang, Qi Li, Yinglong Wang, Jing Chen, Hu Zhang, Xiaoxiao Cui, Qizheng Wang, Shuo Li

Time series forecasting has long been dominated by advances in model architecture, with recent progress driven by deep learning and hybrid statistical techniques. However, as forecasting models approach diminishing returns in accuracy, a critical yet underexplored opportunity emerges: the strategic use of post-processing. In this paper, we address the last-mile gap in time-series forecasting, which is to improve accuracy and uncertainty without retraining or modifying a deployed backbone. We propose $\delta$-Adapter, a lightweight, architecture-agnostic way to boost deployed time series forecasters without retraining. $\delta$-Adapter learns tiny, bounded modules at two interfaces: input nudging (soft edits to covariates) and output residual correction. We provide local descent guarantees, $O(\delta)$ drift bounds, and compositional stability for combined adapters. Meanwhile, it can act as a feature selector by learning a sparse, horizon-aware mask over inputs to select important features, thereby improving interpretability. In addition, it can also be used as a distribution calibrator to measure uncertainty. Thus, we introduce a Quantile Calibrator and a Conformal Corrector that together deliver calibrated, personalized intervals with finite-sample coverage. Our experiments across diverse backbones and datasets show that $\delta$-Adapter improves accuracy and calibration with negligible compute and no interface changes.

Yingdong Shi, Zhiyu Yang, Changming Li, Jingyi Yu, Kan Ren

Vision models have demonstrated remarkable capabilities, yet their decision-making processes remain largely opaque. Mechanistic interpretability (MI) offers a promising avenue to decode these internal workings. However, existing interpretation methods suffer from two key limitations. First, they rely on the flawed activation-magnitude assumption, assuming that the importance of a neuron is directly reflected by the magnitude of its activation, which ignores more nuanced causal roles. Second, they are predominantly input-centric, failing to capture the causal mechanisms that drive a model's output. These shortcomings lead to inaccurate and unreliable internal representation interpretations, especially in cases of incorrect predictions. We propose MICLIP (Mechanism-Interpretability via Contrastive Learning), a novel framework that extends CLIP’s contrastive learning to align internal mechanisms of vision models with general semantic concepts, enabling interpretable and controllable representations. Our approach circumvents previous limitations by performing multimodal alignment between a model's internal representations and both its input concepts and output semantics via contrastive learning. We demonstrate that MICLIP is a general framework applicable to diverse representation unit types, including individual neurons and sparse autoencoder (SAE) features. By enabling precise, causal-aware interpretation, MICLIP not only reveals the semantic properties of a model's internals but also paves the way for effective and targeted manipulation of model behaviors.

Applications · Time Series

SheoYon Jhin, Noseong Park

Anomaly detection in time series is essential for applications from industrial monitoring to financial risk management. Recent methods --- including forecasting error models, representation learning, augmentation, and weak-label learning --- have achieved strong results for specific anomaly types such as sudden point or gradual collective anomalies. While many prior works report window-level metrics that may mask errors, several recent methods evaluate at the point level as well. Our goal is to use a stricter point-wise protocol to make masking effects explicit. We introduce FOLD (Point-wise Anomaly Detection via fold-bifurcation), a framework that reframes detection as tracking a system’s proximity to a critical transition. FOLD extracts stress signals from a forecasting model and integrates them with a fold-bifurcation inspired ODE to produce the risk state, flagging anomalies once it crosses a threshold calibrated on normal data. This requires no anomaly labels and no additional detector training, enabling a parameter-free and efficient detection process. By modeling anomalies as stress accumulation toward a tipping point, FOLD naturally aligns with point-wise detection, providing a unifying and interpretable perspective that complements type-specific methods. Experiments on 40 benchmarks against 34 state-of-the-art baselines show that FOLD achieves competitive or superior performance, with particular strength under strict point-wise evaluation.

Computer Vision · Vision Models & Multimodal

Yikun Ji, Yan Hong, Qi Fan, jun lan, Huijia Zhu, Weiqiang Wang, Liqing Zhang, Jianfu Zhang

The rapid rise of image generation calls for detection methods that are both interpretable and reliable. Existing approaches, though accurate, act as black boxes and fail to generalize to out-of-distribution data, while multi-modal large language models (MLLMs) provide reasoning ability but often hallucinate. To address these issues, we construct \textbf{FakeXplained} dataset of AI-generated images annotated with bounding boxes and descriptive captions that highlight synthesis artifacts, forming the basis for human-aligned, visually grounded reasoning. Leveraging \textbf{FakeXplained}, we develop \textbf{FakeXplainer} which fine-tunes MLLMs with a progressive training pipeline, enabling accurate detection, artifact localization, and coherent textual explanations. Extensive experiments show that \textbf{FakeXplainer} not only sets a new state-of-the-art in detection and localization accuracy ($98.2\%$ accuracy, $36.0\%$ IoU), but also demonstrates strong robustness and out-of-distribution generalization, uniquely delivering spatially grounded, human-aligned rationales. The code and dataset are available at: \href{https://github.com/Gennadiyev/FakeXplain}{https://github.com/Gennadiyev/FakeXplain}.

Deep Learning · Generative Models and Autoencoders

Junn Yong Loo, Leong Yu, Michelle Adeline, Julia Lau, Hwa Hui Tew, Arghya Pal, VISHNU MONN BASKARAN, Chee-Ming Ting, Raphaël Phan

Energy-based models (EBMs) are a powerful class of probabilistic generative models due to their flexibility and interpretability. However, relationships between potential flows and explicit EBMs remain underexplored, while contrastive divergence training via implicit Markov chain Monte Carlo (MCMC) sampling is often unstable and expensive in high-dimensional settings. In this paper, we propose Variational Potential (VAPO) Flow Bayes, a new energy-based generative framework that eliminates the need for implicit MCMC sampling and does not rely on auxiliary networks or cooperative training. VAPO learns an energy-parameterized potential flow by constructing a flow-driven density homotopy that is matched to the data distribution through a variational loss minimizing the Kullback-Leibler divergence between the flow-driven and marginal homotopies. This principled formulation enables robust and efficient generative modeling while preserving the interpretability of EBMs. Experimental results on image generation, interpolation, out-of-distribution detection, and compositional generation confirm the effectiveness of VAPO, showing that our method performs competitively with existing approaches in terms of sample quality and versatility across diverse generative modeling tasks.

Applications · Time Series

Natalia Martinez Gil, Fearghal O'Donncha, Wesley Gifford, Nianjun Zhou, Dhaval Patel, Roman Vaculin

We propose a post-hoc adaptive conformal anomaly detection method for monitoring time series that leverages predictions from pre-trained foundation models without requiring additional fine-tuning. Our method yields an interpretable anomaly score directly interpretable as a false alarm rate (p-value), facilitating transparent and actionable decision-making. It employs weighted quantile conformal prediction bounds and adaptively learns optimal weighting parameters from past predictions, enabling calibration under distribution shifts and stable false alarm control, while preserving out-of-sample guarantees. As a model-agnostic solution, it integrates seamlessly with foundation models and supports rapid deployment in resource-constrained environments. This approach addresses key industrial challenges such as limited data availability, lack of training expertise, and the need for immediate inference, while taking advantage of the growing accessibility of time series foundation models. Experiments on both synthetic and real-world datasets show that the proposed approach delivers strong performance, combining simplicity, interpretability, robustness, and adaptivity.

Applications · Time Series

Ruirui Wang, Yanke Li, Manuel Günther, Diego Paez-Granados

Healthcare data, such as Intensive Care Unit (ICU) records, comprise heterogeneous multivariate time series sampled at irregular intervals with pervasive missingness. However, clinical applications demand predictive models that are both accurate and interpretable. We present our Graph Attention-based Relational Learning for Intensive Care (GARLIC) model, a novel neural network architecture that imputes missing data through a learnable exponential-decay encoder, captures inter-sensor dependencies via time-lagged summary graphs, and fuses global patterns with cross-dimensional sequential attention. All attention weights and graph edges are learned end-to-end to serve as built-in observation-, signal-, and edge-level explanations. To reconcile auxiliary reconstruction and primary classification objectives, we developed an alternating decoupled optimization scheme that stabilizes training. On three ICU benchmarks (PhysioNet 2012 \& 2019, MIMIC-III), GARLIC sets the new state of the art in outcome prediction, significantly improving AUROC and AUPRC over best-performing baselines at comparable computational cost. Ablation studies confirm the contribution of each module, and feature-removal trials validate the fidelity of importance attribution through a monotonic performance drop (full > top 50\% > random 50\% > bottom 50\%). Real-time case studies demonstrate actionable risk warnings with transparent explanations, marking a significant advance toward accurate, explainable deep learning for irregularly sampled ICU time series data. Moreover, we demonstrated GARLIC's superiority in data imputation and classification on various time-series datasets beyond the ICU domain, showing its generalizability and applicability to broader tasks.

Deep Learning · Attention Mechanisms

Yehjin Shin, Seojin Kim, Noseong Park

State-space models (SSMs) offer efficient alternatives to attention with linear-time recurrence. Mamba2, a recent SSM-based language model, uses selective input gating and a multi-head structure, enabling parallel computation and strong benchmark performance. However, its multi-head recurrence operates independently without structured utilization or analysis. In this work, we propose a novel method called **H**ierarchical **AD**aptive filter bank for **E**fficient **S**SMs (*HADES*), a Graph Signal Processing (GSP)-inspired framework that reinterprets Mamba2 as an adaptive filter bank on a line graph. Our hierarchical architecture introduces two filter types: shared filters for global low-pass behavior and expert filters for local high-pass behavior, achieved through structured bias on the parameter $\Delta$. *HADES* achieves comparable performance to baseline models including Mamba2 across various benchmarks in language modeling, commonsense reasoning, and long-context retrieval, while using only **58.9%** of the original parameters. In this regard, *HADES* bridges GSP and neural sequence modeling, enabling efficient, hierarchical, and interpretable filtering within state-space models.

Theory · Interpretability and Visualization

Joshua Melander, Zaki Alaoui, Shenghua Liu, Surya Ganguli, Stephen Baccus

Understanding how neural networks transform inputs into outputs is crucial for interpreting and manipulating their behavior. Most existing approaches analyze internal representations by identifying hidden-layer activation patterns correlated with human-interpretable concepts. Here we take a direct approach to examine how hidden neurons act to drive network outputs. We introduce CODEC ($\textbf{Co}$ntribution $\textbf{Dec}$omposition), a method that uses sparse autoencoders to decompose network behavior into sparse motifs of hidden-neuron contributions, revealing causal processes that cannot be determined by analyzing activations alone. Applying CODEC to benchmark image-classification networks, we find that contributions grow in sparsity and dimensionality across layers and, unexpectedly, that they progressively decorrelate positive and negative effects on network outputs. We further show that decomposing contributions into sparse modes enables greater control and interpretation of intermediate layers, supporting both causal manipulations of network output and human-interpretable visualizations of distinct image components that combine to drive that output. Finally, by analyzing state-of-the-art models of neural activity in the vertebrate retina, we demonstrate that CODEC uncovers combinatorial actions of model interneurons and identifies the sources of dynamic receptive fields. Overall, CODEC provides a rich and interpretable framework for understanding how nonlinear computations evolve across hierarchical layers, establishing contribution modes as an informative unit of analysis for mechanistic insights into artificial neural networks.

Computer Vision · Vision Models & Multimodal

Muhammad Kamran Janjua, Abdul Wahab, Bahador Rashidi

In this work, we introduce a new perspective on comparative image assessment by representing an image pair as a structured composition of its regions. In contrast, existing methods focus on whole image analysis, while implicitly relying on region-level understanding. We extend the intra-image notion of a scene graph to inter-image, and propose a novel task of Distortion Graph (DG). DG treats paired images as a structured topology grounded in regions, and represents dense degradation information such as distortion type, severity, comparison and quality score in a compact interpretable graph structure. To realize the task of learning a distortion graph, we contribute (i) a region-level dataset, PandaSet, (ii) a benchmark suite, PandaBench, with varying region-level difficulty, and (iii) an efficient architecture, Panda, to generate distortion graphs. We demonstrate that PandaBench poses a significant challenge for state-of-the-art multimodal large language models (MLLMs) as they fail to understand region-level degradations even when fed with explicit region cues. We show that training on PandaSet or prompting with DG elicits region-wise distortion understanding, opening a new direction for fine-grained, structured pairwise image assessment.

Applications · Language, Speech and Dialog

Wenbo Shang, Yuxi Sun, Jing Ma, Xin Huang

Humor is a commonly used and intricate human language in daily life. Humor generation, especially in multi-modal scenarios, is a challenging task for large language models (LLMs), which is typically as funny caption generation for images, requiring visual understanding, humor reasoning, creative imagination, and so on. Existing LLM-based approaches rely on reasoning chains or self-improvement, which suffer from limited creativity and interpretability. To address these bottlenecks, we develop a novel LLM-based humor generation mechanism based on a fundamental humor theory, GTVH. To produce funny and script-opposite captions, we introduce a humor-theory-driven multi-role LLM collaboration framework augmented with humor retrieval (HOMER). The framework consists of three LLM-based roles: (1) conflicting-script extractor that grounds humor in key script oppositions, forming the basis of caption generation; (2) retrieval-augmented hierarchical imaginator that identifies key humor targets and expands the creative space of them through diverse associations structured as imagination trees; and (3) caption generator that produces funny and diverse captions conditioned on the obtained knowledge. Extensive experiments on two New Yorker Cartoon benchmarking datasets show that HOMER outperforms state-of-the-art baselines and powerful LLM reasoning strategies on multi-modal humor captioning.

General Machine Learning · Representation Learning

Shujian Gao, Yuan Wang, Chenglong Ma, Xin Gao, Jiangtao Yan, Junzhi Ning, Cheng Tang, Changkai Ji, Huihui Xu, Wei Li 等

Concept Bottleneck Models (CBMs) achieve interpretability by interposing a human-understandable concept layer between perception and label prediction. We first identify that the condition of \textit{many-to-many} mapping is necessary for robust CBMs, a prerequisite that has been largely overlooked in previous approaches. While several recent methods have attempted to establish this relationship, we observe that they suffer from the fundamental issue of \textit{representation collapse}, where visual patch features degenerate into a low-rank subspace during training, severely degrading the quality of learned concept activation vectors, thus hindering both model interpretability and downstream performance. To address these issues, we propose Implicit Vector Quantization (IVQ), a lightweight regularizer that maintains high-rank, diverse representations throughout training. Rather than imposing a hard bottleneck via direct quantization, IVQ learns a codebook prior that anchors semantic information in visual features, allowing it to act as a proxy objective. To further exploit these high-rank concept-aware features, we propose Magnet Attention, which dynamically aggregates patch-level features into visual concept prototypes, explicitly modeling the many-to-many vision–concept correspondence. Extensive experimental results show that our approach effectively prevents representational collapse and achieves state-of-the-art performance on diverse benchmarks. Our experiments further probe the low-rank phenomenon in representational collapse, finding that IVQ mitigates the information bottleneck and yields cross-modal representations with clearer, more interpretable consistency. Code is available at \url{https://github.com/Daryl-GSJ/IVQ-CBM}.