论文检索

Applications · Neuroscience, Cognitive Science

Fenghao Liu, Yipeng Shen, Peng Chen, Qian Zheng, Peng Lin, Gang Pan

Processing long sequence data such as speech requires models to maintain long-term dependencies, which is challenging for recurrent spiking neural networks due to high temporal dynamics in neuron models that leak stored information in their membrane potentials, and due to vanishing gradients during backpropagation through time. These issues can be mitigated by employing more complex neuron designs, such as ALIF and TC-LIF, but these neuron-level solutions often incur high computational costs and complicate hardware implementation, undermining the efficiency advantages of Spiking neural networks. Here we propose an architectural-level solution that leverages the dynamical interactions of a few leaky integrate-and-fire (LIF) neurons to enhance long-term information storage. The memory capability of this LIF-based micro-circuit is adaptively modulated by global recurrent connections of the recurrent spiking neural network, contributing to selective enhancement of temporal information retention, and promoting stable gradient propagation through time. The proposed model outperforms previous methods including LSTM, ALIF, and TC-LIF in long sequence tasks, achieving 96.52\% accuracy on the PS-MNIST dataset. Furthermore, our method also provides a compelling efficiency advantage, yielding up to 277$\times$ computational efficiency improvement compared to conventional models such as LSTM. This work paves the way for building cost-effective, hardware-friendly, and interpretable spiking neural networks for long sequence modeling.

Applications · Health / Medicine

Salma Ahmed, Emad Mohammed, Azam Bidgoli

Modern segmentation models achieve strong predictive performance but remain largely opaque, limiting our ability to diagnose failures, understand dataset shift, or intervene in a principled manner. We introduce $\textbf{Med-SegLens}$, a model-diffing framework that decomposes segmentation model activations into interpretable latent features using sparse autoencoders trained on SegFormer and U-Net. Through cross-architecture and cross-dataset latent alignment across healthy, adult, pediatric, and sub-Saharan African glioma cohorts, we identify a stable backbone of shared representations, while dataset shift is driven by differential reliance on population-specific latents. We show that these latents act as causal bottlenecks for segmentation failures, and that targeted latent-level interventions can correct errors and improve cross-dataset adaption without retraining, recovering performance in 70% of failure cases and improving Dice score from 39.4% to 74.2%. Our results demonstrate that latent-level model diffing provides a practical and mechanistic tool for diagnosing failures and mitigating dataset shift in segmentation models.

Applications · Health / Medicine

Moritz Schaefer, Zoe Piran, Nils Philipp Walter, Animesh Awasthi, Christoph Bock, Jure Leskovec, Zinaida Good

AI-driven disease characterization in histopathology promises to assist in clinical decision making, but its performance is limited by the scarcity of detailed annotations. In contrast, single-cell gene expression provides expressive and interpretable labels that compensate this scarcity, but assays are costly and rarely acquired in clinical workflows. To overcome this gap, we propose to bridge these data sources using a trimodal contrastive learning framework that aligns histopathology images, gene expression profiles, and natural-language descriptions. Our training data combines atlas-scale datasets of (i) spatially-resolved gene expression paired with histopathology images, and (ii) single-cell gene expression with curated annotations. Together, these data induce an alignment between image and text modalities, which we leverage for zero-shot image annotation tasks, such as the identification of immune cells. We present a sufficient condition under which this transfer can succeed and assess the performance of our approach against established baselines. We predict cell types at 15.4\% improved relative AUROC over leading pathology vision language models. Our method also exhibits significant gains across diverse prediction tasks in low-data regimes, when combining training data from all three modality pairs. Our work thus establishes *transitive representation learning* as an effective strategy to enhance histopathology interpretation.

Social Aspects · Accountability, Transparency, and Interpretability

Manuel Cherep, Nikhil Singh, Pattie Maes

Artificial agentic systems increasingly operate as behavioral systems by interacting with dynamic environments, pursuing goals, and adapting over time. Yet, current evaluation methods largely focus on performance outcomes, not the underlying behavioral processes that produce them. This paper argues that AI agents must be evaluated like other behavioral systems: through systematic observation, perturbation, and interpretation of their actions. We draw on lessons from the behavioral sciences to motivate this position, and propose a research agenda focused on developing rigorous behavioral tests. These include methods for recovering decision strategies from action sequences, constructing environments that isolate behavioral differences, and probing emergent dynamics in multi-agent systems. Taken together, these directions offer a roadmap for developing a science of AI behavior.

Haoyang Liu, Jie Wang, Boxuan Niu, Xiongwei Han, Yian Xu, Mingxuan Ye, Zijie Geng, Fangzhou Zhu, Tao Zhong, Mingxuan Yuan 等

Building mathematical optimization models is critical in operations research (OR), while it requires substantial human expertise. Recent advancements have utilized large language models (LLMs) to automate this modeling process. However, existing works often struggle to verify the correctness of the generated optimization models, without checking the rationality of the constraints and variables or the validity of solutions to the generated models. This hampers the subsequent verification and correction steps, and thus it severely hurts the modeling accuracy. To address this challenge, we propose a novel LLM-based framework with Dual-side Verification (OptiVer) from both structure and solution perspectives, thereby improving the modeling accuracy. The structure-side verification ensures that the modeling structure of the generated optimization models aligns with the original problem description, accurately capturing the problem's constraints and requirements. Meanwhile, the solution-side verification interprets and evaluates the validity of the solutions, confirming that the optimization models are logically and mathematically sound. Extensive experiments on several popular benchmarks demonstrate that our approach significantly outperforms the state-of-the-art, achieving over 20\% improvement in accuracy.

Social Aspects · Accountability, Transparency, and Interpretability

Manuel Cherep, Pranav M R, Pattie Maes, Nikhil Singh

The web is littered with images, once created for human consumption and now increasingly interpreted by agents using vision-language models (VLMs). These agents make visual decisions at scale, deciding what to click, recommend, or buy. Yet, we know little about the structure of their visual preferences. We introduce a framework for studying this by placing VLMs in controlled image-based choice tasks and systematically perturbing their inputs. Our key idea is to treat the agent's decision function as a latent visual utility that can be inferred through revealed preference: choices between systematically edited images. Starting from common images, such as product photos, we propose methods for visual prompt optimization, adapting text optimization methods to iteratively propose and apply visually plausible modifications using an image generation model (such as in composition, lighting, background, or depicted context). We then evaluate which edits increase selection probability. Through large-scale experiments on frontier VLMs, we demonstrate that optimized edits significantly shift choice probabilities in head-to-head comparisons. We develop an automatic interpretability pipeline to explain these preferences, identifying consistent visual themes that drive selection. We argue that this approach offers a new lens on the internal value functions of image-based AI agents, enabling systematic study of what they are visually attracted to and why.

Social Aspects · Security

Zhengxian Huang, Wenjun Zhu, Haoxuan Qiu, Xiaoyu Ji, Wenyuan Xu

By integrating Chain-of-Thought (CoT) reasoning, Vision-Language-Action (VLA) models have demonstrated strong capabilities in robotic manipulation, particularly by improving generalization and interpretability. However, the security of CoT-based reasoning mechanisms remains largely unexplored. In this paper, we show that Chain-of-Thought (CoT) reasoning introduces a novel attack vector for targeted control hijacking—for example, causing a robot to mistakenly deliver a knife to a person instead of an apple—without modifying the user’s instruction. We first provide empirical evidence that CoT strongly governs action generation, even when it is semantically misaligned with the input instructions. Building on this observation, we propose **TRAP**, the first targeted adversarial attack framework for CoT-reasoning VLA models. **TRAP** uses an adversarial patch (e.g., a coaster placed on the table) to corrupt intermediate CoT reasoning and hijack the VLA’s output. By optimizing the CoT adversarial loss, **TRAP** induces specific and adversary-defined behaviors. Extensive evaluations across 3 mainstreaming VLA architectures and 3 CoT reasoning paradigms validate the effectiveness of **TRAP**. Notably, we implemented the patch by printing it on paper in a real-world setting. Our findings highlight the urgent need to secure CoT reasoning in VLA systems.

Applications · Social Sciences

Yanhui Sun, Wu Liu, Haifeng Ming, Xinru Wang, Hantao Yao, Yongdong Zhang

The intelligent verdict is essential for handling voluminous demands of E-commerce dispute. Unlike the legal dispute, it necessitates identifying pivotal clues from redundant multimodal evidence chains, relying on informal transaction rules for dispute verdicts. The complex ``clues-dispute" causal logic and flexible verdict rules render existing methods inadequate. Motivated by this, we propose a pioneering task, **E-commerce Dispute Verdict** (EDV), and introduce **VerdictBench**, the first Multimodal Disputes Verdicts Benchmark for E-commerce, to facilitate the intelligent verdicts. Building upon this, we propose **CyberJurors**, a framework that integrates an Individual Verdict Chain-of-Thought (IV-CoT) and Jury Consensus Verdict (JCV) to clarify the dispute logic and regulate the fair verdict process. *For the individual juror*, IV-CoT decomposes the EDV task into a structured reasoning, enabling fine-grained clues perception and explicit causal logic between clues and dispute. *For the collective jury*, JCV simulates multi-round discussion and voting among jurors guided by Verdict Precedents, effectively mitigating individual biases. Extensive experiments on VerdictBench demonstrate that CyberJurors significantly improves verdict accuracy, fairness, and interpretability, outperforming existing MLLMs by up to 9.48\% in accuracy.

General Machine Learning · Evaluation

Yuanzhe Hu, Xiaopeng Wang, Yuxin Wang, Xiaokun Zhong, Haiquan Lu, Tianyu Pang, Michael Mahoney, Yujun Yan, Pu Ren, Yaoqing Yang

Neural networks (NNs) trained under different hyperparameters can fall into distinct training ``regimes'', with models in the same regime showing homogeneous properties and models across regimes differing qualitatively. In this paper, we analyze multi-regime patterns in scientific machine learning (SciML) models by characterizing these regimes and the transitions between them. We show how different regimes affect trainability and generalization, and we demonstrate that loss-landscape analysis enables regime-based diagnostics to understand, evaluate, and improve SciML model training. Our analysis yields three key insights: (1) compared with computer vision (CV) tasks, SciML models exhibit significantly more pathological loss landscapes; (2) optimization methods are regime-specific -- different optimization strategies help in different regimes, but none is uniformly effective; and (3) SciML models exhibit fine-grained failure modes that challenge conventional interpretations of standard loss-landscape metrics. Using this study, we aim to unify our understanding of seemingly different failure modes across SciML tasks and obtain task-oblivious insights and methodologies for addressing these failures. We validate these findings across widely used SciML models, including physics-informed neural networks (PINNs), Fourier neural operators (FNOs), and Neural Ordinary Differential Equations (NeuralODEs), on benchmarks spanning representative ordinary and partial differential equations.

Deep Learning · Other Representation Learning

Yeqin Zhang, Yunfei Wang, Jiaxuan Chen, Ke Qin, Yizheng Zhao, Cam-Tu Nguyen

Sentence representations are foundational to many Natural Language Processing (NLP) applications. While recent methods leverage Large Language Models (LLMs) to derive sentence representations, most rely on final-layer hidden states, which are optimized for next-token prediction and thus often fail to capture global, sentence-level semantics. This paper introduces a novel perspective, demonstrating that attention value vectors capture sentence semantics more effectively than hidden states. We propose *Value Aggregation (VA)*, a simple method that pools token values across multiple layers and token indices. In a training-free setting, VA outperforms other LLM-based embeddings, even matches or surpasses the ensemble-based MetaEOL. Furthermore, we demonstrate that when paired with suitable prompts, the layer attention outputs can be interpreted as aligned weighted value vectors. Specifically, the attention scores of the last token function as the weights, while the output projection matrix ($W_O$) aligns these weighted value vectors with the common space of the LLM residual stream. This refined method, termed *Aligned Weighted VA (AlignedWVA)*, achieves state-of-the-art performance among training-free LLM-based embeddings, outperforming the high-cost MetaEOL by a substantial margin. Finally, we highlight the potential of obtaining strong LLM embedding models through fine-tuning Value Aggregation.

Social Aspects · Accountability, Transparency, and Interpretability

Yifan Zhang, Wei Bi, Kechi Zhang, Dongming Jin, Jie Fu, Zhi Jin

Algorithm extraction aims to synthesize executable programs directly from models trained on algorithmic tasks, enabling *de novo* algorithm discovery without relying on human-written code. However, applying this paradigm to Transformer is hindered by representation entanglement (e.g., superposition), where entangled features encoded in overlapping directions obstruct the recovery of symbolic expressions. We propose the Discrete Transformer, an architecture explicitly designed to bridge the gap between continuous representations and discrete symbolic logic. By injecting discreteness through temperature-annealed sampling, our framework effectively leverages hypothesis testing and symbolic regression to extract human-readable programs. Empirically, the Discrete Transformer achieves performance comparable to RNN-based methods while extending interpretability to continuous variable domains, and the annealing dynamics exhibit a clear exploration-to-exploitation transition. Finally, we show that architectural inductive biases provide fine-grained control over synthesized programs, establishing the Discrete Transformer as a robust framework for demonstration-free algorithm discovery and Transformer interpretability.

Applications · Time Series

Jiafeng Lin, Yuxuan Wang, HUAKUN LUO, Jianmin Wang, Zhongyi Pei

Multimodal time series forecasting has garnered significant attention for its potential to provide more robust and accurate predictions than traditional single-modality models by leveraging rich information inherent in other modalities. However, due to fundamental challenges in modality alignment, existing methods often struggle to effectively incorporate multimodal data into predictions, particularly textual information that has a causal influence on time series fluctuations, such as emergency reports and policy announcements. In this paper, we reflect on the role of textual information in numerical forecasting and propose **Ti**me series transformers with Multimodal **Mi**xture-of-Experts, **TiMi**, to unleash the causal reasoning capabilities of LLMs. Concretely, TiMi utilizes language models to generate inferences on future developments, which then serve as guidance for time series forecasting. To seamlessly integrate both exogenous factors and time series into predictions, we introduce a Multimodal Mixture-of-Experts (MMoE) module as a lightweight plug-in to empower Transformer-based time series models for multimodal forecasting, eliminating the need for explicit representation-level alignment. Experimentally, our proposed TiMi demonstrates consistent state-of-the-art performance on sixteen real-world multimodal forecasting benchmarks, outperforming advanced baselines while offering strong adaptability and interpretability.

Applications · Computer Vision

Shuai Gong, Chaoran Cui, Xiaolin Dong, Chunyun Zhang, Linwei Fan

Black-box prompt tuning (BBPT) aims to optimize input prompts for large models where internal parameters and gradients are inaccessible. However, existing methods fail to simultaneously address the dual challenges of prompt interpretability and query efficiency. To address these challenges, we propose CRL-BPT, a curriculum reinforcement learning framework that utilizes a large language model as an agent to generate human-readable prompts. Specifically, CRL-BPT implements a dynamic curriculum schedule on two auxiliary objectives: an imitation loss and an innovation loss. By dynamically weighting these objectives, CRL-BPT regularizes the RL process, guiding the agent from mimicking reference prompts to discovering novel patterns. Additionally, we introduce tailored stabilization mechanisms comprising historical loss normalization and relative reward calibration to ensure robust training. Extensive experiments demonstrate that CRL-BPT establishes new state-of-the-art performance and generates highly interpretable prompts under a strict budget of API calls. Code is available at https://anonymous.4open.science/r/CRL-BPT.

Deep Learning · Generative Models and Autoencoders

Elio Moreau, Florentin Coeurdoux, Grégoire Ferré, Eric Vanden-Eijnden

Understanding the geometry of learned distributions is fundamental to improving and interpreting diffusion models, yet systematic tools for exploring their landscape remain limited. Standard latent-space interpolations fail to respect the structure of the learned distribution, often traversing low-density regions. We introduce a framework based on the string method that computes continuous paths between samples by evolving curves under the learned score function. Operating on pretrained models without retraining, our approach interpolates between three regimes: pure generative transport, which yields continuous sample paths; gradient-dominated dynamics, which recover minimum energy paths (MEPs); and finite-temperature string dynamics, which compute principal curves---self-consistent paths that balance energy and entropy. We demonstrate that the choice of regime matters in practice. For image diffusion models, MEPs contain high-likelihood but unrealistic ``cartoon'' images, confirming prior observations that likelihood maxima appear unrealistic; principal curves instead yield realistic morphing sequences despite lower likelihood. For protein structure prediction, our method computes transition pathways between metastable conformers directly from models trained on static structures, yielding paths with physically plausible intermediates. Together, these results establish the string method as a principled tool for probing the modal structure of diffusion models---identifying modes, characterizing barriers, and mapping connectivity in complex learned distributions.

General Machine Learning · Sequential, Network, and Time Series Modeling

Chao Yang, Wenjie Shen, Shuang Li

We propose a non-autoregressive branching diffusion model for generating spatio-temporal point processes. Starting from a geometric principle---the Wasserstein-Fisher-Rao (WFR) gradient flow of a generalized KL divergence toward a simple reference intensity---we obtain a tractable forward noising mechanism with two interpretable components: (i) a Langevin-type \emph{drift-diffusion} step that perturbs event locations and times, and (ii) a \emph{birth-death branching} step that changes the event count via location-dependent thinning (deaths) and Poisson offspring replication (births). We learn the reverse-time dynamics using a permutation-equivariant denoiser that predicts a drift field and a net-growth field, and we train it using an entropic-regularized unbalanced optimal transport (UOT), which naturally handles count mismatch between noisy and clean samples. The resulting generator produces complete spatio-temporal event sets without autoregressive simulation or explicit intensity normalization.

Applications · Computer Vision

Onkar Jadhav, Tim French, Matthew Rayson, Nicole Jones

Probabilistic super-resolution of high-dimensional spatial fields using diffusion models is often computationally prohibitive due to the cost of operating directly in pixel space. We propose PODiff, a structured conditional generative framework that performs diffusion in a fixed, variance-ordered Proper Orthogonal Decomposition (POD) coefficient space, exploiting the orthogonality of POD modes to impose an interpretable, variance-ordered latent geometry. This design enables efficient ensemble generation, preserves dominant spatial structure, and yields spatially interpretable, well-calibrated uncertainty at substantially lower computational cost. We evaluate PODiff on sea surface temperature downscaling over the West Australian coast and on a controlled advection--diffusion benchmark. PODiff achieves reconstruction accuracy comparable to pixel-space diffusion while requiring significantly less memory and producing more reliable uncertainty estimates than deterministic and Monte Carlo Dropout baselines.

Applications · Chemistry, Physics, and Earth Sciences

Dingling Yao, Andrea Polesello, Adeel Pervez, Caroline Muller, Francesco Locatello

While Vision Foundation Models (VFMs) excel at predictive tasks on satellite imagery, their performance can arise from visual correlations rather than underlying structural invariants, making certain perception-based out-of-distribution accuracy a poor proxy for scientific utility. As a result, models may look correct without reasoning correctly—a discrepancy we term the *Perception–Physics Paradox*. To address this gap, we introduce *Scientific Alignment* as an implicit objective for representation learning in scientific domains. We study a principled, testable aspect of scientific alignment through *Structural Isomorphism*, which requires latent representations to uniquely identify physical systems up to a linear reparameterization. This perspective induces a hierarchy of necessary conditions and yields a systematic probing protocol for physical and causal interpretability. To operationalize this framework, we release *TC-Atlas*, a foundational global dataset and automated construction pipeline for tropical cyclone research, and show that current VFMs rely on visual shortcuts that collapse in extreme regimes, indicating that scientific alignment does not arise as a natural byproduct of visual scaling alone.

Deep Learning · Large Language Models

Patrick Langer, Thomas Kaar, Max Rosenblattl, Maxwell A. Xu, Winnie Chow, Martin Maritsch, Robert Jakob, Ning Wang, Juncheng Liu, Aradhana Verma 等

Large Language Models (LLMs) have shown strong capability in interpreting multimodal data but remain limited in their ability to natively handle time-series data. Addressing this limitation could enable the translation of longitudinal and wearable sensing data into actionable insights and patient-facing digital health applications. We propose OpenTSLM, a family of Time Series Language Models that integrate time-series as a native modality into pretrained LLMs, enabling natural-language prompting and reasoning over multiple time-series. We implement two OpenTSLM variants based on soft prompting (OpenTSLM-SP) and cross-attention (OpenTSLM-Flamingo). To conduct comprehensive experiments on reasoning over medical text and time-series, we introduce three chain of thought (CoT) datasets: HAR-CoT (human activity recognition), Sleep-CoT (sleep staging), and ECG-QA-CoT (electrocardiogram question answering). Across tasks, OpenTSLM models consistently outperform baselines. OpenTSLMs with time-series encoders trained from scratch achieve 69.88% in sleep staging and 65.44% in HAR, while OpenTSLM combined with time series foundation models (TSFMs) achieve 68.33% and 67.64%, compared to 9.05% and 60.44% for fine-tuned text-only baselines. Additionally, we conduct expert evaluations with cardiologists, which show that OpenTSLMs exhibit strong reasoning capabilities and temporal understanding on raw sensor data for ECG-QA. We further show that OpenTSLM-Flamingo models scale better in memory as the number and length of time-series increase. To facilitate further research, we release all code, datasets, and models as open-source resources.

Probabilistic Methods · Everything Else

Taeseong Yoon, Heeyoung Kim

Single-pass uncertainty quantification (UQ) methods for classification represent uncertainty by predicting a tractable distribution over the class probability vector. While existing approaches primarily focus on enhancing the expressiveness of this distribution, they often provide limited insight into how predictive uncertainty is structured and aggregated, resulting in weak interpretability. We introduce the *courtroom analogy*, which conceptualizes uncertainty-aware classification as a structured debate among class-specific advocates. Each advocate forms a probabilistic opinion, and a final verdict is reached by aggregating these opinions using input-dependent plausibility weights. In this framework, each advocate's opinion is modeled as a Dirichlet distribution whose concentration parameter is decomposed into shared evidence and class-specific advocacy. This yields a structured mixture of Dirichlet distributions with semantically interpretable parameters. To instantiate this formulation, we propose *Mixture of Dirichlet EXperts* (MoDEX), a single-pass neural architecture that predicts the courtroom parameters, enabling efficient and expressive UQ while explicitly modeling uncertainty aggregation. We demonstrate that MoDEX enjoys strong theoretical properties and achieves state-of-the-art UQ performance across diverse benchmarks, yielding interpretable uncertainty estimates with meaningful semantics.

Social Aspects · Safety

Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang, Yun-Nung Chen

Existing data poisoning attacks on retrieval-augmented generation (RAG) systems scale poorly because they require costly optimization of poisoned documents for each target phrase. We introduce Eyes-on-Me, a modular attack that decomposes an adversarial document into reusable **Attention Attractors** and **Focus Regions**. Attractors are optimized to direct attention to the Focus Region. Attackers can then insert semantic baits for the retriever or malicious instructions for the generator, adapting to new targets at near zero cost. This is achieved by steering a small subset of attention heads that we empirically identify as strongly correlated with attack success. Across 18 end-to-end RAG settings (3 datasets $\times$ 2 retrievers $\times$ 3 generators), Eyes-on-Me raises average attack success rates from 21.9 to 57.8 (+35.9 points, 2.6$\times$ over prior work). A single optimized attractor transfers to unseen black box retrievers and generators without retraining. Our findings establish a scalable paradigm for RAG data poisoning and show that modular, reusable components pose a practical threat to modern AI systems. They also reveal a strong link between attention concentration and model outputs, informing interpretability research.