论文检索

Social Aspects · Accountability, Transparency and Interpretability

Ahmad-Reza Ehyaei, Ali Shirali, Samira Samadi

Counterfactual explanations provide individuals with cost-optimal recommendations to achieve their desired outcomes. However, when a significant number of individuals seek similar state modifications, this individual-centric approach can inadvertently create competition and introduce unforeseen costs. Additionally, disregarding the underlying data distribution may lead to recommendations that individuals perceive as unusual or impractical. To address these challenges, we propose a novel framework that extends standard counterfactual explanations by incorporating a population dynamics model. This framework penalizes deviations from equilibrium after individuals follow the recommendations, effectively mitigating externalities caused by correlated changes across the population. By balancing individual modification costs with their impact on others, our method ensures a more equitable and efficient outcome. We show how this approach reframes the counterfactual explanation problem from an individual-centric task to a collective optimization problem. Augmenting our theoretical insights, we design and implement scalable algorithms for computing collective counterfactuals, showcasing their effectiveness and advantages over existing recourse methods, particularly in aligning with collective objectives.

Social Aspects · Accountability, Transparency and Interpretability

Gouki Minegishi, Hiroki Furuta, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

Recent large-scale reasoning models have achieved state-of-the-art performance on challenging mathematical benchmarks, yet the internal mechanisms underlying their success remain poorly understood. In this work, we introduce the notion of a reasoning graph, extracted by clustering hidden‐state representations at each reasoning step, and systematically analyze three key graph-theoretic properties: cyclicity, diameter, and small-world index, across multiple tasks (GSM8K, MATH500, AIME~2024). Our findings reveal that distilled reasoning models (e.g., DeepSeek-R1-Distill-Qwen-32B) exhibit significantly more recurrent cycles (about 5 per sample), substantially larger graph diameters, and pronounced small-world characteristics (about 6x) compared to their base counterparts. Notably, these structural advantages grow with task difficulty and model capacity, with cycle detection peaking at the 14B scale and exploration diameter maximized in the 32B variant, correlating positively with accuracy. Furthermore, we show that supervised fine-tuning on an improved dataset systematically expands reasoning graph diameters in tandem with performance gains, offering concrete guidelines for dataset design aimed at boosting reasoning capabilities. By bridging theoretical insights into reasoning graph structures with practical recommendations for data construction, our work advances both the interpretability and the efficacy of large reasoning models.

Applications · Time Series

Fares Mehouachi, Saif Eddin Jabari

We introduce FlowMixer, a single-layer neural architecture that leverages constrained matrix operations to model structured spatiotemporal patterns with enhanced interpretability. FlowMixer incorporates non-negative matrix mixing layers within a reversible mapping framework—applying transforms before mixing and their inverses afterward. This shape-preserving design enables a Kronecker-Koopman eigenmodes framework that bridges statistical learning with dynamical systems theory, providing interpretable spatiotemporal patterns and facilitating direct algebraic manipulation of prediction horizons without retraining. The architecture's semi-group property enables this single layer to mathematically represent any depth through composition, eliminating depth search entirely. Extensive experiments across diverse domains demonstrate FlowMixer's long-horizon forecasting capabilities while effectively modeling physical phenomena such as chaotic attractors and turbulent flows. Our results achieve performance matching state-of-the-art methods while offering superior interpretability through directly extractable eigenmodes. This work suggests that architectural constraints can simultaneously maintain competitive performance and enhance mathematical interpretability in neural forecasting systems.

Social Aspects · Accountability, Transparency and Interpretability

Mengyu Ye, Jun Suzuki, Tatsuro Inaba, Tatsuki Kuribayashi

Recent interpretability work on large language models (LLMs) has been increasingly dominated by a feature-discovery approach with the help of proxy modules. Then, the quality of features learned by, e.g., sparse auto-encoders (SAEs), is evaluated. This paradigm naturally raises a critical question: do such learned features have better properties than those already represented within the original model parameters, and unfortunately, only a few studies have made such comparisons systematically so far. In this work, we revisit the interpretability of feature vectors stored in feed-forward (FF) layers, given the perspective of FF as key-value memories, with modern interpretability benchmarks. Our extensive evaluation revealed that SAE and FFs exhibits a similar range of interpretability, although SAEs displayed an observable but minimal improvement in some aspects. Furthermore, in certain aspects, surprisingly, even vanilla FFs yielded better interpretability than the SAEs, and features discovered in SAEs and FFs diverged. These bring questions about the advantage of SAEs from both perspectives of feature quality and faithfulness, compared to directly interpreting FF feature vectors, and FF key-value parameters serve as a strong baseline in modern interpretability research.

Applications · Robotics

Pei Zhou, Wanting Yao, Qian Luo, Xunzhe Zhou, Yanchao Yang

Goal-conditioned policy learning for robotic manipulation presents significant challenges in maintaining performance across diverse objectives and environments. We introduce *Hyper-GoalNet*, a framework that generates task-specific policy network parameters from goal specifications using hypernetworks. Unlike conventional methods that simply condition fixed networks on goal-state pairs, our approach separates goal interpretation from state processing -- the former determines network parameters while the latter applies these parameters to current observations. To enhance representation quality for effective policy generation, we implement two complementary constraints on the latent space: (1) a forward dynamics model that promotes state transition predictability, and (2) a distance-based constraint ensuring monotonic progression toward goal states. We evaluate our method on a comprehensive suite of manipulation tasks with varying environmental randomization. Results demonstrate significant performance improvements over state-of-the-art methods, particularly in high-variability conditions. Real-world robotic experiments further validate our method's robustness to sensor noise and physical uncertainties. Our code and trained models will be made publicly available.

Social Aspects · Trustworthy Machine Learning

Yedi Zhang, Sun Emma, Annabelle En, Jin Song Dong

Large language models (LLMs) have emerged as a dominant AI paradigm due to their exceptional text understanding and generation capabilities. However, their tendency to generate inconsistent or erroneous outputs challenges their reliability, especially in high-stakes domains requiring accuracy and trustworthiness. Existing research primarily focuses on detecting and mitigating model misbehavior in general-purpose scenarios, often overlooking the potential of integrating domain-specific knowledge. In this work, we advance misbehavior detection by incorporating domain knowledge. The core idea is to design a general specification language that enables domain experts to customize domain-specific constraints in a lightweight and intuitive manner, supporting later runtime monitoring of LLM outputs. To achieve this, we design a novel specification language ESL, and introduce a runtime verification framework RvLLM to validate LLM output against domain-specific constraints defined in ESL. RvLLM operates in two main stages: interpretation and reasoning. During interpretation, it derives interpretations of the specification based on the context, which then guide the reasoning process to identify inconsistencies. When new knowledge is derived, RvLLM issues a follow-up query to the LLM to further verify the consistency. We evaluate RvLLM on three representative tasks: violation detection against Singapore Rapid Transit Systems Act, numerical comparison, and inequality solving. Experimental results show that RvLLM effectively detects erroneous outputs across various LLMs in a lightweight and flexible manner. The results reveal that despite their impressive capabilities, LLMs remain prone to low-level errors due to a lack of formal guarantees during inference, and our framework offers a potential long-term solution by leveraging expert domain knowledge to rigorously and efficiently verify LLM outputs.

General Machine Learning · Everything Else

Kwan Ho Ryan Chan, Yuyan Ge, Edgar Dobriban, Hamed Hassani, Rene Vidal

A significant use case of instruction-finetuned Large Language Models (LLMs) is to solve question-answering tasks interactively. In this setting, an LLM agent is tasked with making a prediction by sequentially querying relevant information from the user, as opposed to a single-turn conversation. This paper explores sequential querying strategies that aim to minimize the expected number of queries. One such strategy is Information Pursuit (IP), a greedy algorithm that at each iteration selects the query that maximizes information gain or equivalently minimizes uncertainty. However, obtaining accurate estimates of mutual information or conditional entropy for LLMs is very difficult in practice due to over- or under-confident LLM probabilities, which leads to suboptimal query selection and predictive performance. To better estimate the uncertainty at each iteration, we propose *Conformal Information Pursuit (C-IP)*, an alternative approach to sequential information gain based on conformal prediction sets. More specifically, C-IP leverages a relationship between prediction sets and conditional entropy at each iteration to estimate uncertainty based on the average size of conformal prediction sets. In contrast to conditional entropy, we find that conformal prediction sets are a distribution-free and robust method of measuring uncertainty. Experiments with 20 Questions show that C-IP obtains better predictive performance and shorter query-answer chains compared to previous approaches to IP and uncertainty-based chain-of-thought methods. Furthermore, extending to an interactive medical setting between a doctor and a patient on the MediQ dataset, C-IP achieves competitive performance with direct single-turn prediction while offering greater interpretability.

Applications · Neuroscience, Cognitive Science

Federico D'Agostino, Lisa Schwetlick, Matthias Bethge, Matthias Kümmerer

Understanding how humans move their eyes to gather visual information is a central question in neuroscience, cognitive science, and vision research. While recent deep learning (DL) models achieve state-of-the-art performance in predicting human scanpaths, their underlying decision processes remain opaque. At an opposite end of the modeling spectrum, cognitively inspired mechanistic models aim to explain scanpath behavior through interpretable cognitive mechanisms but lag far behind in predictive accuracy. In this work, we bridge this gap by using a high-performing deep model—DeepGaze III—to discover and test mechanisms that improve a leading mechanistic model, SceneWalk. By identifying individual fixations where DeepGaze III succeeds and SceneWalk fails, we isolate behaviorally meaningful discrepancies and use them to motivate targeted extensions of the mechanistic framework. These include time-dependent temperature scaling, saccadic momentum and an adaptive cardinal attention bias: Simple, interpretable additions that substantially boost predictive performance. With these extensions, SceneWalk’s explained variance on the MIT1003 dataset doubles from 35% to 70%, setting a new state of the art in mechanistic scanpath prediction. Our findings show how performance-optimized neural networks can serve as tools for cognitive model discovery, offering a new path toward interpretable and high-performing models of visual behavior. Our code is available at https://github.com/bethgelab/what-moves-the-eyes

Applications · Neuroscience, Cognitive Science

Alicia Zeng, Jack Gallant

Encoding models based on word embeddings or artificial neural network (ANN) features reliably predict brain responses to naturalistic stimuli but remain difficult to interpret. A central limitation is superposition—the entanglement of distinct semantic features along correlated directions in dense embeddings, which arises when latent features outnumber the embedding dimensions. This entanglement renders regression weights non-identifiable: different combinations of semantic directions can produce identical predicted brain activity, preventing principled interpretation of voxel selectivity. To overcome this, we introduce the Sparse Concept Encoding Model, which transforms dense embeddings into a higher-dimensional, sparse, and non-negative space of learned concept atoms. This transformation yields an axis-aligned semantic basis where each dimension corresponds to an interpretable concept, enabling direct readout of conceptual selectivity from voxel weights. When applied to fMRI data collected during story listening, our model matches the prediction performance of conventional dense models while substantially enhancing interpretability. It enables novel neuroscientific analyses such as disentangling overlapping cortical representations of time, space, and number, and revealing structured similarity among distributed conceptual maps. This framework offers a scalable and interpretable bridge between ANN-derived features and human conceptual representations in the brain.

Applications · Health

Hao Zhang, Zhan Zhuang, Xuehao Wang, Xiaodong Yang, Yu Zhang

Human Activity Recognition (HAR) with wearable sensors is challenged by limited interpretability, which significantly impacts cross-dataset generalization. To address this challenge, we propose Motion-Primitive Transformer (MoPFormer), a novel self-supervised framework that enhances interpretability by tokenizing inertial measurement unit signals into semantically meaningful motion primitives and leverages a Transformer architecture to learn rich temporal representations. MoPFormer comprises two stages. The first stage is to partition multi-channel sensor streams into short segments and quantize them into discrete ``motion primitive'' codewords, while the second stage enriches those tokenized sequences through a context-aware embedding module and then processes them with a Transformer encoder. The proposed MoPFormer can be pre-trained using a masked motion-modeling objective that reconstructs missing primitives, enabling it to develop robust representations across diverse sensor configurations. Experiments on six HAR benchmarks demonstrate that MoPFormer not only outperforms state-of-the-art methods but also successfully generalizes across multiple datasets. More importantly, the learned motion primitives significantly enhance both interpretability and cross-dataset performance by capturing fundamental movement patterns that remain consistent across similar activities, regardless of dataset origin.

Applications · Robotics

Haotian Chi, Zeyu Feng, Yueming LYU, Chengqi Zheng, Linbo Luo, Yew Soon Ong, Ivor Tsang, Hechang Chen, Yi Chang, Haiyan Yin

Long-horizon planning in robotic manipulation tasks requires translating underspecified, symbolic goals into executable control programs satisfying spatial, temporal, and physical constraints. However, language model-based planners often struggle with long-horizon task decomposition, robust constraint satisfaction, and adaptive failure recovery. We introduce InstructFlow, a multi-agent framework that establishes a symbolic, feedback-driven flow of information for code generation in robotic manipulation tasks. InstructFlow employs a InstructFlow Planner to construct and traverse a hierarchical instruction graph that decomposes goals into semantically meaningful subtasks, while a Code Generator generates executable code snippets conditioned on this graph. Crucially, when execution failures occur, a Constraint Generator analyzes feedback and induces symbolic constraints, which are propagated back into the instruction graph to guide targeted code refinement without regenerating from scratch. This dynamic, graph-guided flow enables structured, interpretable, and failure-resilient planning, significantly improving task success rates and robustness across diverse manipulation benchmarks, especially in constraint-sensitive and long-horizon scenarios.

Data-centric AI · Everything Else

George Cazenavette, Antonio Torralba, Vincent Sitzmann

The task of dataset distillation aims to find a small set of synthetic images such that training a model on them reproduces the performance of the same model trained on a much larger dataset of real samples. Existing distillation methods focus on synthesizing datasets that enable training randomly initialized models. In contrast, state-of-the-art vision approaches are increasingly building on large, pre-trained self-supervised models rather than training from scratch. In this paper, we investigate the problem of distilling datasets that enable us to optimally train linear probes on top of such large, pre-trained vision models. We introduce a method of dataset distillation for this task called Linear Gradient Matching that optimizes the synthetic images such that, when passed through a pre-trained feature extractor, they induce gradients in the linear classifier similar to those produced by the real data. Our method yields synthetic data that out-perform all real-image baselines and, remarkably, generalize across pre-trained vision models, enabling us, for instance, to train a linear CLIP probe that performs competitively using a dataset distilled via a DINO backbone. Further, we show that distilled datasets provide a valuable tool for model interpretability, predicting, among other things, how similar two model's representations spaces are under the platonic representation hypothesis or whether a model is sensitive to spurious correlations in adversarial datasets.

Deep Learning · Attention Mechanisms

Julien Siems, Timur Carstensen, Arber Zela, Frank Hutter, Massimiliano Pontil, Riccardo Grazzi

Linear Recurrent Neural Networks (linear RNNs) have emerged as competitive alternatives to Transformers for sequence modeling, offering efficient training and linear-time inference. However, existing architectures face a fundamental trade-off between expressivity and efficiency, dictated by the structure of their state-transition matrices. Diagonal matrices, used in models such as Mamba, GLA, or mLSTM, yield fast runtime but have limited expressivity. To address this, recent architectures such as DeltaNet and RWKV-7 adopted a diagonal plus rank-1 structure, which allows simultaneous token and channel mixing, improving associative recall and, as recently shown, state-tracking when allowing negative eigenvalues in the state-transition matrices. Building on the interpretation of DeltaNet's recurrence as performing one step of online gradient descent per token on an associative recall loss, we introduce DeltaProduct, which instead takes multiple ($n_h$) steps per token. This naturally leads to diagonal plus rank-$n_h$ state-transition matrices, formed as products of $n_h$ generalized Householder transformations, providing a tunable mechanism to balance expressivity and efficiency. We provide a detailed theoretical characterization of the state-tracking capability of DeltaProduct in finite precision and how it improves by increasing $n_h$. Our extensive experiments demonstrate that DeltaProduct outperforms DeltaNet in both state-tracking and language modeling, while also showing significantly improved length extrapolation capabilities.

Applications · Neuroscience, Cognitive Science

Victor Geadah, Amin Nejatbakhsh, David Lipshutz, Jonathan Pillow, Alex Williams

Neural population activity exhibits complex, nonlinear dynamics, varying in time, over trials, and across experimental conditions. Here, we develop *Conditionally Linear Dynamical System* (CLDS) models as a general-purpose method to characterize these dynamics. These models use Gaussian Process priors to capture the nonlinear dependence of circuit dynamics on task and behavioral variables. Conditioned on these covariates, the data is modeled with linear dynamics. This allows for transparent interpretation and tractable Bayesian inference. We find that CLDS models can perform well even in severely data-limited regimes (e.g. one trial per condition) due to their Bayesian formulation and ability to share statistical power across nearby task conditions. In example applications, we apply CLDS to model thalamic neurons that nonlinearly encode heading direction and to model motor cortical neurons during a cued-reaching task.

Deep Learning · Attention Mechanisms

Satoshi Noguchi, Yoshinobu Kawahara

Transformers have achieved remarkable success across natural language processing (NLP) and computer vision (CV). However, deep transformer models often suffer from an over-smoothing issue, in which token representations converge to similar values as they pass through successive transformer blocks. In this paper, we establish an equivalence between the hidden-state dynamics induced by stacked attention layers and graph neural diffusion on a complete graph. From this perspective, over-smoothing can be interpreted as a consequence of the dissipative nature of the underlying diffusion dynamics. Motivated by this physical interpretation, we propose Wavy Transformer, which consists of a novel attention layer based on second-order wavy dynamics. We also introduce a feed-forward network and a normalization layer designed to preserve the physical state-velocity relationship under the chain rule, thereby extending the transformer architecture. We further validate our proposed techniques on various transformer models for NLP and CV tasks. The results consistently demonstrate that Wavy Transformer improves performance with minimal additional parameters and no extra hyperparameter tuning.

Probabilistic Methods · Monte Carlo and Sampling Methods

Han Cui, Jingbo Liu

Conditional sampling is a fundamental task in Bayesian statistics and generative modeling. Consider the problem of sampling from the posterior distribution $P\_{X|Y=y^\*}$ for some observation $y^\*$, where the likelihood $P\_{Y|X}$ is known, and we are given $n$ i.i.d. samples $D=\\{X\_i\\}\_{i=1}^n$ drawn from an unknown prior distribution $\pi\_X$. Suppose that $f(\hat{\pi}\_{X^n})$ is the distribution of a posterior sample generated by an algorithm (e.g. a conditional generative model or the Bayes rule) when $\hat{\pi}\_{X^n}$ is the empirical distribution of the training data. Although averaging over the randomness of the training data $D$, we have $\mathbb{E}\_D\left(\hat{\pi}\_{X^n}\right)= \pi\_X$, we do not have $\mathbb{E}\_D\left\\{f(\hat{\pi}\_{X^n})\right\\}= f(\pi\_X)$ due to the nonlinearity of $f$, leading to a bias. In this paper we propose a black-box debiasing scheme that improves the accuracy of such a naive plug-in approach. For any integer $k$ and under boundedness of the likelihood and smoothness of $f$, we generate samples $\hat{X}^{(1)},\dots,\hat{X}^{(k)}$ and weights $w\_1,\dots,w\_k$ such that $\sum_{i=1}^kw_iP\_{\hat{X}^{(i)}}$ is a $k$-th order approximation of $f(\pi\_X)$, where the generation process treats $f$ as a black-box. Our generation process achieves higher accuracy when averaged over the randomness of the training data, without degrading the variance, which can be interpreted as improving memorization without compromising generalization in generative models.

Computer Vision · Vision Models & Multimodal

Zinuo Li, Xian Zhang, Yongxin Guo, Mohammed Bennamoun, Farid Boussaid, Girish Dwivedi, Luqi Gong, Qiuhong Ke

Humans naturally understand moments in a video by integrating visual and auditory cues. For example, localizing a scene in the video like “A scientist passionately speaks on wildlife conservation as dramatic orchestral music plays, with the audience nodding and applauding” requires simultaneous processing of visual, audio, and speech signals. However, existing models often struggle to effectively fuse and interpret audio information, limiting their capacity for comprehensive video temporal understanding. To address this, we present TriSense, a triple-modality large language model designed for holistic video temporal understanding through the integration of visual, audio, and speech modalities. Central to TriSense is a Query-Based Connector that adaptively reweights modality contributions based on the input query, enabling robust performance under modality dropout and allowing flexible combinations of available inputs. To support TriSense's multimodal capabilities, we introduce TriSense-2M, a high-quality dataset of over 2 million curated samples generated via an automated pipeline powered by fine-tuned LLMs. TriSense-2M includes long-form videos and diverse modality combinations, facilitating broad generalization. Extensive experiments across multiple benchmarks demonstrate the effectiveness of TriSense and its potential to advance multimodal video analysis.

Computer Vision · Vision Models & Multimodal

Weiqi Li, Xuanyu Zhang, Shijie Zhao, Yabin ZHANG, Junlin Li, Li zhang, Jian Zhang

Image quality assessment (IQA) focuses on the perceptual visual quality of images, playing a crucial role in downstream tasks such as image reconstruction, compression, and generation. The rapid advancement of multi-modal large language models (MLLMs) has significantly broadened the scope of IQA, moving toward comprehensive image quality understanding that incorporates content analysis, degradation perception, and comparison reasoning beyond mere numerical scoring. Previous MLLM-based methods typically either generate numerical scores lacking interpretability or heavily rely on supervised fine-tuning (SFT) using large-scale annotated datasets to provide descriptive assessments, limiting their flexibility and applicability. In this paper, we propose Q-Insight, a reinforcement learning-based model built upon group relative policy optimization (GRPO), which demonstrates strong visual reasoning capability for image quality understanding while requiring only a limited amount of rating scores and degradation labels. By jointly optimizing score regression and degradation perception tasks with carefully designed reward functions, our approach effectively exploits their mutual benefits for enhanced performance. Extensive experiments demonstrate that Q-Insight substantially outperforms existing state-of-the-art methods on both score regression and degradation perception tasks, while exhibiting impressive zero-shot generalization and superior comparison reasoning capability. The code and models are available at https://github.com/bytedance/Q-Insight.

Computer Vision · Image and Video Generation

Arman Zarei, Samyadeep Basu, Keivan Rezaei, Zihao Lin, Sayan Nag, Soheil Feizi

Understanding how knowledge is distributed across the layers of generative models is crucial for improving interpretability, controllability, and adaptation. While prior work has explored knowledge localization in UNet-based architectures, Diffusion Transformer (DiT)-based models remain underexplored in this context. In this paper, we propose a model- and knowledge-agnostic method to localize where specific types of knowledge are encoded within the DiT blocks. We evaluate our method on state-of-the-art DiT-based models, including PixArt-$\alpha$, FLUX, and SANA, across six diverse knowledge categories. We show that the identified blocks are both interpretable and causally linked to the expression of knowledge in generated outputs. Building on these insights, we apply our localization framework to two key applications: *model personalization* and *knowledge unlearning*. In both settings, our localized fine-tuning approach enables efficient and targeted updates, reducing computational cost, improving task-specific performance, and better preserving general model behavior with minimal interference to unrelated or surrounding content. Overall, our findings offer new insights into the internal structure of DiTs and introduce a practical pathway for more interpretable, efficient, and controllable model editing.

Zidi Xiong, Shan Chen, Zhenting Qi, Himabindu Lakkaraju

Large Reasoning Models (LRMs) have significantly enhanced their capabilities in complex problem-solving by introducing a thinking draft that enables multi-path Chain-of-Thought explorations before producing final answers. Ensuring the faithfulness of these intermediate reasoning processes is crucial for reliable monitoring, interpretation, and effective control. In this paper, we propose a systematic counterfactual intervention framework to rigorously evaluate *thinking draft faithfulness*. Our approach focuses on two complementary dimensions: **(1) Intra-Draft Faithfulness**, which assesses whether individual reasoning steps causally influence subsequent steps and the final draft conclusion through counterfactual step insertions; and **(2) Draft-to-Answer Faithfulness**, which evaluates whether final answers are logically consistent with and dependent on the thinking draft, by perturbing the draft’s concluding logic. We conduct extensive experiments across six state-of-the-art LRMs. Our findings show that current LRMs demonstrate selective faithfulness to intermediate reasoning steps and frequently fail to faithfully align with the draft conclusions. These results underscore the need for more faithful and interpretable reasoning in advanced LRMs.