论文检索

Applications · Neuroscience, Cognitive Science

Mo WANG, Kaining Peng, Jingsheng Tang, Hongkai Wen, Quanying Liu

Brain atlases are essential for reducing the dimensionality of neuroimaging data and enabling interpretable analysis. However, most existing atlases are predefined, group-level templates with limited flexibility and resolution. We present Deep Cluster Atlas (DCA), a graph-guided deep embedding clustering framework for generating individualized, voxel-wise brain parcellations. DCA combines a pretrained autoencoder with spatially regularized deep clustering to produce functionally coherent and spatially contiguous regions. Our method supports flexible control over resolution and anatomical scope, and generalizes to arbitrary brain structures. We further introduce a standardized benchmarking platform for atlas evaluation, using multiple large-scale fMRI datasets. Across multiple datasets and scales, DCA outperforms state-of-the-art atlases, improving functional homogeneity by 98.8% and silhouette coefficient by 29%, and achieves superior performance in downstream tasks such as autism diagnosis and cognitive decoding. We also observe that a fine-tuned pretrained model achieves superior results on the corresponding task. Codes and models are available at https://github.com/ncclab-sustech/DCA.

Reinforcement Learning · Multi-agent

Qinyu Xu, Yuanyang Zhu, Xuefei Wu, Chunlin Chen

The ability to model interactions among agents is crucial for effective coordination and understanding their cooperation mechanisms in multi-agent reinforcement learning (MARL). However, previous efforts to model high-order interactions have been primarily hindered by the combinatorial explosion or the opaque nature of their black-box network structures. In this paper, we propose a novel value decomposition framework, called Continued Fraction Q-Learning (QCoFr), which can flexibly capture arbitrary-order agent interactions with only linear complexity $\mathcal{O}\left({n}\right)$ in the number of agents, thus avoiding the combinatorial explosion when modeling rich cooperation. Furthermore, we introduce the variational information bottleneck to extract latent information for estimating credits. This latent information helps agents filter out noisy interactions, thereby significantly enhancing both cooperation and interpretability. Extensive experiments demonstrate that QCoFr not only consistently achieves better performance but also provides interpretability that aligns with our theoretical analysis.

Social Aspects · Accountability, Transparency and Interpretability

Thummaluru Siddartha Reddy, Vempalli Naga Sai Saketh, Mahesh Chandran

Graph Neural Networks \texttt{(GNNs)} excel at jointly modeling node features and topology, yet their \emph{black-box} nature limits their adoption in real-world applications where interpretability is desired. Inspired by the success of interpretable Neural Additive Models \texttt{(NAM)} for tabular data, Graph Neural Additive Network \texttt{(GNAN)} extends the additive modeling approach to graph data to overcome limitations of GNNs. While being interpretable, \texttt{GNAN} representation learning overlooks the importance of local aggregation and more importantly suffers from parameter complexity. To mitigate the above challenges, we introduce Graph Neural Additive Model with Random Fourier Features (\texttt{G-NAMRFF}), a lightweight, self‐interpretable graph additive architecture. \texttt{G-NAMRFF} represents each node embedding as the sum of feature‐wise contributions where contributions are modeled via a \emph{Gaussian process} \texttt{(GP)} with a graph- and feature-aware kernel. Specifically, we construct a kernel using Radial Basis Function (\texttt{RBF}) with graph structure induced by Laplacian and learnable Finite Impulse Response (\texttt{FIR}) filter. We approximate the kernel using Random Fourier Features (\texttt{RFFs}) which transforms the \texttt{GP} prior to a Bayesian formulation, which are subsequently learnt using a single layer neural network with size equal to number of \texttt{RFF} features. \texttt{G-NAMRFF} is light weight with $168\times$ fewer parameters compared to \texttt{GNAN}. Despite its compact size, \texttt{G-NAMRFF} matches or outperforms state-of-the-art \texttt{GNNs} and \texttt{GNAN} on node and graph classification tasks, delivering real-time interpretability without sacrificing accuracy.

Deep Learning · Everything Else

Xueqi Ma, Jun Wang, Yanbei Jiang, Sarah Erfani, Tongliang Liu, James Bailey

Large language models (LLMs) have achieved state-of-the-art performance in a variety of tasks, but remain largely opaque in terms of their internal mechanisms. Understanding these mechanisms is crucial to improve their reasoning abilities. Drawing inspiration from the interplay between neural processes and human cognition, we propose a novel interpretability framework to systematically analyze the roles and behaviors of attention heads, which are key components of LLMs. We introduce CogQA, a dataset that decomposes complex questions into step-by-step subquestions with a chain-of-thought design, each associated with specific cognitive functions such as retrieval or logical reasoning. By applying a multi-label probing method, we identify the attention heads responsible for these functions. Our analysis across multiple LLM families reveals that attention heads exhibit functional specialization, characterized as cognitive heads. These cognitive heads exhibit several key properties: they are universally sparse, and vary in number and distribution across different cognitive functions, and they display interactive and hierarchical structures. We further show that cognitive heads play a vital role in reasoning tasks—removing them leads to performance degradation, while augmenting them enhances reasoning accuracy. These insights offer a deeper understanding of LLM reasoning and suggest important implications for model design, training and fine-tuning strategies.

Theory · Learning Theory

Vicky Kouni

Unfolding networks are interpretable networks emerging from iterative algorithms, incorporate prior knowledge of data structure, and are designed to solve inverse problems like compressed sensing, which deals with recovering data from noisy, missing observations. Compressed sensing finds applications in critical domains, from medical imaging to cryptography, where adversarial robustness is crucial to prevent catastrophic failures. However, a solid theoretical understanding of the performance of unfolding networks in the presence of adversarial attacks is still in its infancy. In this paper, we study the adversarial generalization of unfolding networks when perturbed with $l_2$-norm constrained attacks, generated by the fast gradient sign method. Particularly, we choose a family of state-of-the-art overaparameterized unfolding networks and deploy a new framework to estimate their adversarial Rademacher complexity. Given this estimate, we provide adversarial generalization error bounds for the networks under study, which are tight with respect to the attack level. To our knowledge, this is the first theoretical analysis on the adversarial generalization of unfolding networks. We further present a series of experiments on real-world data, with results corroborating our derived theory, consistently for all data. Finally, we observe that the family's overparameterization can be exploited to promote adversarial robustness, shedding light on how to efficiently robustify neural networks.

Computer Vision · Image and Video Generation

Kaibo Wang, Jianda Mao, Tong Wu, Yang Xiang

Classifier-Free Guidance (CFG) is an essential component of text-to-image diffusion models, and understanding and advancing its operational mechanisms remains a central focus of research. Existing approaches stem from divergent theoretical interpretations, thereby limiting the design space and obscuring key design choices. To address this, we propose a unified perspective that reframes conditional guidance as fixed point iterations, seeking to identify a golden path where latents produce consistent outputs under both conditional and unconditional generation. We demonstrate that CFG and its variants constitute a special case of single-step short-interval iteration, which is theoretically proven to exhibit inefficiency. To this end, we introduce Foresight Guidance (FSG), which prioritizes solving longer-interval subproblems in early diffusion stages with increased iterations. Extensive experiments across diverse datasets and model architectures validate the superiority of FSG over state-of-the-art methods in both image quality and computational efficiency. Our work offers novel perspectives for conditional guidance and unlocks the potential of adaptive design.

Deep Learning · Everything Else

Xiaowei Zhu, Yubing Ren, Fang Fang, Qingfeng Tan, Shi Wang, Yanan Cao

The rapid advancement of large language models (LLMs) has blurred the line between AI-generated and human-written text. This progress brings societal risks such as misinformation, authorship ambiguity, and intellectual property concerns, highlighting the urgent need for reliable AI-generated text detection methods. However, recent advances in generative language modeling have resulted in significant overlap between the feature distributions of human-written and AI-generated text, blurring classification boundaries and making accurate detection increasingly challenging. To address the above challenges, we propose a DNA-inspired perspective, leveraging a repair-based process to directly and interpretably capture the intrinsic differences between human-written and AI-generated text. Building on this perspective, we introduce **DNA-DetectLLM**, a zero-shot detection method for distinguishing AI-generated and human-written text. The method constructs an ideal AI-generated sequence for each input, iteratively repairs non-optimal tokens, and quantifies the cumulative repair effort as an interpretable detection signal. Empirical evaluations demonstrate that our method achieves state-of-the-art detection performance and exhibits strong robustness against various adversarial attacks and input lengths. Specifically, DNA-DetectLLM achieves relative improvements of **5.55\%** in AUROC and **2.08\%** in F1 score across multiple public benchmark datasets. Code and data are available at https://github.com/Xiaoweizhu57/DNA-DetectLLM.

Computer Vision · Classification and Understanding

Thibaut Loiseau, Guillaume Bourmaud, Vincent Lepetit

Pre-training techniques have greatly advanced computer vision, with CroCo’s cross-view completion approach yielding impressive results in tasks like 3D reconstruction and pose regression. However, cross-view completion is ill-posed in non-covisible regions, limiting its effectiveness. We introduce Alligat0R, a novel pre-training approach that replaces cross-view learning with a covisibility segmentation task. Our method predicts whether each pixel in one image is covisible in the second image, occluded, or outside the field of view, making the pre-training effective in both covisible and non-covisible regions, and provides interpretable predictions. To support this, we present Cub3, a large-scale dataset with 5M image pairs and dense covisibility annotations derived from the nuScenes and ScanNet datasets. Cub3 includes diverse scenarios with varying degrees of overlap. The experiments show that our novel pre-training method Alligat0R significantly outperforms CroCo in relative pose regression. Alligat0R and Cub3 will be made publicly available.

Social Aspects · Accountability, Transparency and Interpretability

Julian Minder, Clément Dumas, Caden Juang, Bilal Chughtai, Neel Nanda

Model diffing is the study of how fine-tuning changes a model's representations and internal algorithms. Many behaviors of interest are introduced during fine-tuning, and model diffing offers a promising lens to interpret such behaviors. Crosscoders are a recent model diffing method that learns a shared dictionary of interpretable concepts represented as latent directions in both the base and fine-tuned models, allowing us to track how concepts shift or emerge during fine-tuning. Notably, prior work has observed concepts with no direction in the base model, and it was hypothesized that these model-specific latents were concepts introduced during fine-tuning. However, we identify two issues which stem from the crosscoders L1 training loss that can misattribute concepts as unique to the fine-tuned model, when they really exist in both models. We develop Latent Scaling to flag these issues by more accurately measuring each latent's presence across models. In experiments comparing Gemma 2 2B base and chat models, we observe that the standard crosscoder suffers heavily from these issues. Building on these insights, we train a crosscoder with BatchTopK loss and show that it substantially mitigates these issues, finding more genuinely chat-specific and highly interpretable concepts. We recommend practitioners adopt similar techniques. Using the BatchTopK crosscoder, we successfully identify a set of chat-specific latents that are both interpretable and causally effective, representing concepts such as false information and personal question, along with multiple refusal-related latents that show nuanced preferences for different refusal triggers. Overall, our work advances best practices for the crosscoder-based methodology for model diffing and demonstrates that it can provide concrete insights into how chat-tuning modifies model behavior.

Computer Vision · Image and Video Generation

Zhenyuan Qin, Xincheng Shuai, Henghui Ding

Controllable image generation has attracted increasing attention in recent years, enabling users to manipulate visual content such as identity and style. However, achieving simultaneous control over the 9D poses (location, size, and orientation) of multiple objects remains an open challenge. Despite recent progress, existing methods often suffer from limited controllability and degraded quality, falling short of comprehensive multi-object 9D pose control. To address these limitations, we propose ***SceneDesigner***, a method for accurate and flexible multi-object 9-DoF pose manipulation. ***SceneDesigner*** incorporates a branched network to the pre-trained base model and leverages a new representation, ***CNOCS map***, which encodes 9D pose information from the camera view. This representation exhibits strong geometric interpretation properties, leading to more efficient and stable training. To support training, we construct a new dataset, ***ObjectPose9D***, which aggregates images from diverse sources along with 9D pose annotations. To further address data imbalance issues, particularly performance degradation on low-frequency poses, we introduce a two-stage training strategy with reinforcement learning, where the second stage fine-tunes the model using a reward-based objective on rebalanced data. At inference time, we propose ***Disentangled Object Sampling***, a technique that mitigates insufficient object generation and concept confusion in complex multi-object scenes. Moreover, by integrating user-specific personalization weights, ***SceneDesigner*** enables customized pose control for reference subjects. Extensive qualitative and quantitative experiments demonstrate that ***SceneDesigner*** significantly outperforms existing approaches in both controllability and quality.

Applications · Neuroscience, Cognitive Science

Sara Cammarota, Matteo Ferrante, Nicola Toschi

Decoding of visual stimuli from noninvasive neuroimaging techniques such as functional magnetic resonance (fMRI) has advanced rapidly in the last years; yet, most high-performing brain decoding models rely on complicated, non-interpretable latent spaces. In this study we present an interpretable brain decoding framework that inserts a semantic bottleneck into BrainDiffuser, a well established, simple and linear decoding pipeline. We firstly produce a $214-\text{dimensional}$ binary interpretable space $\mathcal{L}$ for images, in which each dimension answers to a specific question about the image (e.g., "Is there a person?", "Is it outdoors?"). A first ridge regression maps voxel activity to this semantic space. Because this mapping is linear, its weight matrix can be visualized as maps of voxel importance for each dimension of $\mathcal{L}$, revealing which cortical regions influence mostly each semantic dimension. A second regression then transforms these concept vectors into CLIP embeddings required to produce the final decoded image, conditioning the BrainDiffuser model. We found that voxel-wise weight maps for individual questions are highly consistent with canonical category-selective regions in the visual cortex (face, bodies, places, words), simultaneously revealing that activation distributions, not merely location, bear semantic meaning in the brain. Visual brain decoding performances are only slightly lower compared to the original BrainDiffuser metrics (e.g., the CLIP similarity is decreased by $\leq 4$% for the four subjects), yet offering substantial gains in interpretability and neuroscientific insights. These results show that our interpretable brain decoding pipeline enables voxel-level analysis of semantic representations in the human brain without sacrificing decoding accuracy.

Social Aspects · Accountability, Transparency and Interpretability

Guy Davidson, Todd Gureckis, Brenden Lake, Adina Williams

Demonstrations and instructions are two primary approaches for prompting language models to perform in-context learning (ICL) tasks. Do identical tasks elicited in different ways result in similar representations of the task? An improved understanding of task representation mechanisms would offer interpretability insights and may aid in steering models. We study this through function vectors (FVs), recently proposed as a mechanism to extract few-shot ICL task representations. We generalize FVs to alternative task presentations, focusing on short textual instruction prompts, and successfully extract instruction function vectors that promote zero-shot task accuracy. We find evidence that demonstration- and instruction-based function vectors leverage different model components, and offer several controls to dissociate their contributions to task performance. Our results suggest that different task prompting forms do not induce a common task representation through FVs but elicit different, partly overlapping mechanisms. Our findings offer principled support to the practice of combining instructions and task demonstrations, imply challenges in universally monitoring task inference across presentation forms, and encourage further examinations of LLM task inference mechanisms.

Computer Vision · Vision Models & Multimodal

Tianyi Bai, Zengjie Hu, Fupeng Sun, Qiu Jiantao, Yizhen Jiang, Guangxin He, Bohan Zeng, Conghui He, Binhang Yuan, Wentao Zhang

Multi-modal large language models (MLLMs) have achieved remarkable capabilities by integrating visual perception with language understanding, enabling applications such as image-grounded dialogue, visual question answering, and scientific analysis. However, most MLLMs adopt a static inference paradigm, encoding the entire image into fixed visual tokens upfront, which limits their ability to iteratively refine understanding or adapt to context during inference. This contrasts sharply with human perception, which is dynamic, selective, and feedback-driven. In this work, we introduce a novel framework for inference-time visual token scaling that enables MLLMs to perform iterative, verifier-guided reasoning over visual content. We formulate the problem as a Markov Decision Process, involving a reasoner that proposes visual actions and a verifier—trained via multi-step Direct Preference Optimization (DPO)—that evaluates these actions and determines when reasoning should terminate. To support this, we present a new dataset, VTS, comprising supervised reasoning trajectories (VTS-SFT) and preference-labeled reasoning comparisons (VTS-DPO). Our method significantly outperforms existing approaches across diverse visual reasoning benchmarks, offering not only improved accuracy but also more interpretable and grounded reasoning processes. These results demonstrate the promise of dynamic inference mechanisms for enabling fine-grained, context-aware visual reasoning in next-generation MLLMs. Code and datasets are publicly released at https://vts-v.github.io/.

Deep Learning · Everything Else

Luke Darlow, Ciaran Regan, Sebastian Risi, Jeffrey Seely, Llion Jones

Biological brains demonstrate complex neural activity, where neural dynamics are critical to how brains process information. Most artificial neural networks ignore the complexity of individual neurons. We challenge that paradigm. By incorporating neuron-level processing and synchronization, we reintroduce neural timing as a foundational element. We present the Continuous Thought Machine (CTM), a model designed to leverage neural dynamics as its core representation. The CTM has two innovations: (1) neuron-level temporal processing}, where each neuron uses unique weight parameters to process incoming histories; and (2) neural synchronization as a latent representation. The CTM aims to strike a balance between neuron abstractions and biological realism. It operates at a level of abstraction that effectively captures essential temporal dynamics while remaining computationally tractable. We demonstrate the CTM's performance and versatility across a range of tasks, including solving 2D mazes, ImageNet-1K classification, parity computation, and more. Beyond displaying rich internal representations and offering a natural avenue for interpretation owing to its internal process, the CTM is able to perform tasks that require complex sequential reasoning. The CTM can also leverage adaptive compute, where it can stop earlier for simpler tasks, or keep computing when faced with more challenging instances. The goal of this work is to share the CTM and its associated innovations, rather than pushing for new state-of-the-art results. To that end, we believe the CTM represents a significant step toward developing more biologically plausible and powerful artificial intelligence systems. We provide an accompanying [interactive online demonstration](https://pub.sakana.ai/ctm/) and an [extended technical report](https://pub.sakana.ai/ctm/paper).

Applications · Genetics, Cell Biology, etc

Mehdi Yazdani-Jahromi, Ali Khodabandeh Yalabadi, Ozlem Garibay

The growing importance of mRNA therapeutics and synthetic biology highlights the need for models that capture the latent structure of synonymous codon (different triplets encoding the same amino acid) usage, which subtly modulates translation efficiency and gene expression. While recent efforts incorporate codon-level inductive biases through auxiliary objectives, they often fall short of explicitly modeling the structured relationships that arise from the genetic code’s inherent symmetries. We introduce Equi‑mRNA, the first codon‑level equivariant mRNA language model that explicitly encodes synonymous codon symmetries as cyclic subgroups of 2D Special Orthogonal matrix ($\mathrm{SO}(2)$). By combining group‑theoretic priors with an auxiliary equivariance loss and symmetry‑aware pooling, Equi‑mRNA learns biologically grounded representations that outperform vanilla baselines across multiple axes. On downstream property‑prediction tasks including expression, stability, and riboswitch switching Equi‑mRNA delivers up to $\approx$ 10\% improvements in accuracy. In sequence generation, it produces mRNA constructs that are up to $\approx$ 4$\times$ more realistic under Fréchet BioDistance metrics and $\approx$ 28\% better preserve functional properties compared to vanilla baseline. Interpretability analyses further reveal that learned codon‑rotation distributions recapitulate known GC‑content biases and tRNA abundance patterns, offering novel insights into codon usage. Equi‑mRNA establishes a new biologically principled paradigm for mRNA modeling, with significant implications for the design of next‑generation therapeutics.

Social Aspects · Accountability, Transparency and Interpretability

Gunnar König, Hidde Fokkema, Timo Freiesleben, Celestine Mendler-Dünner, Ulrike Luxburg

When applicants get rejected by a high-stakes algorithmic decision system, recourse explanations provide actionable suggestions for applicants on how to change their input features to get a positive evaluation. A crucial yet overlooked phenomenon is that recourse explanations are *performative*: When many applicants act according to their recommendations, their collective behavior may shift the data distribution and, once the model is refitted, also the decision boundary. Consequently, the recourse algorithm may render its own recommendations *invalid*, such that applicants who make the effort of implementing their recommendations may be rejected again when they reapply. In this work, we formally characterize the conditions under which recourse explanations remain valid under their own performative effects. In particular, we prove that recourse actions may become invalid if they are influenced by or if they intervene on non-causal variables. Based on this analysis, we caution against the use of standard counterfactual explanations and causal recourse methods, and instead advocate for recourse methods that recommend actions exclusively on causal variables.

Applications · Neuroscience, Cognitive Science

Arthur Pellegrino, Angus Chadwick

Analysing how neural networks represent data features in their activations can help interpret how they perform tasks. Hence, a long line of work has focused on mathematically characterising the geometry of such "neural representations." In parallel, machine learning has seen a surge of interest in understanding how dynamical systems perform computations on time-varying input data. Yet, the link between computation-through-dynamics and representational geometry remains poorly understood. Here, we hypothesise that recurrent neural networks (RNNs) perform computations by dynamically warping their representations of task variables. To test this hypothesis, we develop a Riemannian geometric framework that enables the derivation of the manifold topology and geometry of a dynamical system from the manifold of its inputs. By characterising the time-varying geometry of RNNs, we show that dynamic warping is a fundamental feature of their computations.

Applications · Neuroscience, Cognitive Science

Shuhan Zhang, Zhi Wang, Rui Gao, Shuang Li

Modeling human decision-making is central to applications such as recommendation, preference learning, and human-AI alignment. While many classic models assume context-independent choice behavior, a large body of behavioral research shows that preferences are often influenced by the composition of the choice set itself---a phenomenon known as the context effect or Halo effect. These effects can manifest as pairwise (first-order) or even higher-order interactions among the available alternatives. Recent models that attempt to capture such effects either focus on the featureless setting or, in the feature-based setting, rely on restrictive interaction structures or entangle interactions across all orders, which limits interpretability. In this work, we propose DeepHalo, a neural modeling framework that incorporates features while enabling explicit control over interaction order and principled interpretation of context effects. Our model enables systematic identification of interaction effects by order and serves as a universal approximator of context-dependent choice functions when specialized to a featureless setting. Experiments on synthetic and real-world datasets demonstrate strong predictive performance while providing greater transparency into the drivers of choice.

Social Aspects

Mengru Wang, Xingyu Chen, Yue Wang, Zhiwei He, Jiahao Xu, Tian Liang, Qiuzhi Liu, Yunzhi Yao, Wenxuan Wang, Ruotian Ma 等

Mixture-of-Experts (MoE) architectures within Large Reasoning Models (LRMs) have achieved impressive reasoning capabilities by selectively activating experts to facilitate structured cognitive processes. Despite notable advances, existing reasoning models often suffer from cognitive inefficiencies like overthinking and underthinking. To address these limitations, we introduce a novel inference-time steering methodology called Reinforcing Cognitive Experts (RICE), designed to improve reasoning depth and efficiency without additional training or complex heuristics. Leveraging normalized Pointwise Mutual Information (nPMI), we systematically identify specialized experts, termed cognitive experts that orchestrate meta-level reasoning operations characterized by tokens like . Empirical evaluations with leading MoE-based LRMs (DeepSeek-R1 and Qwen3-235B) on rigorous quantitative and scientific reasoning benchmarks (AIME and GPQA Diamond) demonstrate noticeable and consistent improvements in reasoning accuracy, cognitive efficiency, and cross-domain generalization. Crucially, our lightweight approach substantially outperforms prevalent reasoning-steering techniques, such as prompt design and decoding constraints, while preserving the model's general instruction-following skills. These results highlight reinforcing cognitive experts as a promising, practical, and interpretable direction to enhance cognitive efficiency within advanced reasoning models.

Deep Learning · Attention Mechanisms

Yotam Erel, Olaf Dünkel, Rishabh Dabral, Vladislav Golyanik, Christian Theobalt, Amit Bermano

We introduce a new interpretation of the attention matrix as a discrete-time Markov chain. Our interpretation sheds light on common operations involving attention scores such as selection, summation, and averaging in a unified framework. It further extends them by considering indirect attention, propagated through the Markov chain, as opposed to previous studies that only model immediate effects. Our key observation is that tokens linked to semantically similar regions form metastable states, i.e., regions where attention tends to concentrate, while noisy attention scores dissipate. Metastable states and their prevalence can be easily computed through simple matrix multiplication and eigenanalysis, respectively. Using these lightweight tools, we demonstrate state-of-the-art zero-shot segmentation. Lastly, we define TokenRank---the steady state vector of the Markov chain, which measures global token importance. We show that TokenRank enhances unconditional image generation, improving both quality (IS) and diversity (FID), and can also be incorporated into existing segmentation techniques to improve their performance over existing benchmarks. We believe our framework offers a fresh view of how tokens are being attended in modern visual transformers.