Advances in neural information processing systems最新文献

Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation. 基于GFlowNets的多种条件图像生成的潜在图挖掘。

Advances in neural information processing systems Pub Date : 2025-12-01

Bailey Trang, Parham Saremi, Alan Q Wang, Fangrui Huang, Zahra TehraniNasab, Amar Kumar, Tal Arbel, Li Fei-Fei, Ehsan Adeli

{"title":"Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation.","authors":"Bailey Trang, Parham Saremi, Alan Q Wang, Fangrui Huang, Zahra TehraniNasab, Amar Kumar, Tal Arbel, Li Fei-Fei, Ehsan Adeli","doi":"","DOIUrl":"","url":null,"abstract":"Capturing diversity is crucial in conditional and prompt-based image generation, particularly when conditions contain uncertainty that can lead to multiple plausible outputs. To generate diverse images reflecting this diversity, traditional methods often modify random seeds, making it difficult to discern meaningful differences between samples, or diversify the input prompt, which is limited in verbally interpretable diversity. We propose Rainbow, a novel conditional image generation framework, applicable to any pretrained conditional generative model, that addresses inherent condition/prompt uncertainty and generates diverse plausible images. Rainbow is based on a simple yet effective idea: decomposing the input condition into diverse latent representations, each capturing an aspect of the uncertainty and generating a distinct image. First, we integrate a latent graph, parameterized by Generative Flow Networks (GFlowNets), into the prompt representation computation. Second, leveraging GFlowNets' advanced graph sampling capabilities to capture uncertainty and output diverse trajectories over the graph, we produce multiple trajectories that collectively represent the input condition, leading to diverse condition representations and corresponding output images. Evaluations on natural image and medical image datasets demonstrate Rainbow's improvement in both diversity and fidelity across image synthesis, image generation, and counterfactual generation tasks.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"104553-104599"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13138530/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147846688","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Quantifying Task-relevant Similarities in Representations Using Decision Variable Correlations. 使用决策变量关联量化表征中的任务相关相似性。

Advances in neural information processing systems Pub Date : 2025-12-01

Yu Eric Qian, Wilson S Geisler, Xue-Xin Wei

{"title":"Quantifying Task-relevant Similarities in Representations Using Decision Variable Correlations.","authors":"Yu Eric Qian, Wilson S Geisler, Xue-Xin Wei","doi":"","DOIUrl":"","url":null,"abstract":"Previous studies have compared neural activities in the visual cortex to representations in deep neural networks trained on image classification. Interestingly, while some suggest that their representations are highly similar, others argued the opposite. Here, we propose a new approach to characterize the similarity of the decision strategies of two observers (models or brains) using decision variable correlation (DVC). DVC quantifies the image-by-image correlation between the decoded decisions based on the internal neural representations in a classification task. Thus, it can capture task-relevant information rather than general representational alignment. We evaluate DVC using monkey V4/IT recordings and network models trained on image classification tasks. We find that model-model similarity is comparable to monkey-monkey similarity, whereas model-monkey similarity is consistently lower. Strikingly, DVC decreases with increasing network performance on ImageNet-1k. Adversarial training does not improve model-monkey similarity in task-relevant dimensions assessed using DVC, although it markedly increases the model-model similarity. Similarly, pre-training on larger datasets does not improve model-monkey similarity. These results suggest a divergence between the task-relevant representations in monkey V4/IT and those learned by models trained on image classification tasks.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"149725-149758"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13196884/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148018985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Data Fusion for Partial Identification of Causal Effects. 因果效应部分识别的数据融合。

Advances in neural information processing systems Pub Date : 2025-12-01

Quinn Lanners, Cynthia Rudin, Alexander Volfovsky, Harsh Parikh

{"title":"Data Fusion for Partial Identification of Causal Effects.","authors":"Quinn Lanners, Cynthia Rudin, Alexander Volfovsky, Harsh Parikh","doi":"","DOIUrl":"","url":null,"abstract":"Data fusion techniques integrate information from heterogeneous data sources to improve learning, generalization, and decision-making across data sciences. In causal inference, these methods leverage rich observational data to improve causal effect estimation, while maintaining the trustworthiness of randomized controlled trials. Existing approaches often relax the strong \"no unobserved confounding\" assumption by instead assuming exchangeability of counterfactual outcomes across data sources. However, when both assumptions simultaneously fail-a common scenario in practice-current methods cannot identify or estimate causal effects. We address this limitation by proposing a novel partial identification framework that enables researchers to answer key questions such as: Is the causal effect positive/negative? and How severe must assumption violations be to overturn this conclusion? Our approach introduces interpretable sensitivity parameters that quantify assumption violations and derives corresponding causal effect bounds. We develop doubly robust estimators for these bounds and operationalize breakdown frontier analysis to understand how causal conclusions change as assumption violations increase. We apply our framework to the Project STAR study, which investigates the effect of classroom size on students' third-grade standardized test performance. Our analysis reveals that the Project STAR results are robust to simultaneous violations of key assumptions, both on average and across various subgroups of interest. This strengthens confidence in the study's conclusions despite potential unmeasured biases in the data.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"150638-150702"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13196892/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148019069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Emergence and Evolution of Interpretable Concepts in Diffusion Models. 扩散模型中可解释概念的产生与演变。

Advances in neural information processing systems Pub Date : 2025-12-01

Berk Tinaz, Zalan Fabian, Mahdi Soltanolkotabi

{"title":"Emergence and Evolution of Interpretable Concepts in Diffusion Models.","authors":"Berk Tinaz, Zalan Fabian, Mahdi Soltanolkotabi","doi":"","DOIUrl":"","url":null,"abstract":"Diffusion models have become the go-to method for text-to-image generation, producing high-quality images from pure noise. However, the inner workings of diffusion models is still largely a mystery due to their black-box nature and complex, multi-step generation process. Mechanistic interpretability techniques, such as Sparse Autoencoders (SAEs), have been successful in understanding and steering the behavior of large language models at scale. However, the great potential of SAEs has not yet been applied toward gaining insight into the intricate generative process of diffusion models. In this work, we leverage the SAE framework to probe the inner workings of a popular text-to-image diffusion model, and uncover a variety of human-interpretable concepts in its activations. Interestingly, we find that even before the first reverse diffusion step is completed, the final composition of the scene can be predicted surprisingly well by looking at the spatial distribution of activated concepts. Moreover, going beyond correlational analysis, we design intervention techniques aimed at manipulating image composition and style, and demonstrate that (1) in early stages of diffusion image composition can be effectively controlled, (2) in the middle stages image composition is finalized, however stylistic interventions are effective, and (3) in the final stages only minor textural details are subject to change.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"166943-166986"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13225673/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148152285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

R-KV: Redundancy-aware KV Cache Compression for Reasoning Models. R-KV：推理模型的冗余感知KV缓存压缩。

Advances in neural information processing systems Pub Date : 2025-12-01

Zefan Cai, Wen Xiao, Hanshi Sun, Cheng Luo, Yikai Zhang, Ke Wan, Yucheng Li, Yeyang Zhou, Li-Wen Chang, Jiuxiang Gu, Zhen Dong, Anima Anandkumar, Abedelkadir Asi, Junjie Hu

{"title":"R-KV: Redundancy-aware KV Cache Compression for Reasoning Models.","authors":"Zefan Cai, Wen Xiao, Hanshi Sun, Cheng Luo, Yikai Zhang, Ke Wan, Yucheng Li, Yeyang Zhou, Li-Wen Chang, Jiuxiang Gu, Zhen Dong, Anima Anandkumar, Abedelkadir Asi, Junjie Hu","doi":"","DOIUrl":"","url":null,"abstract":"Reasoning models have demonstrated impressive performance in self-reflection and chain-of-thought reasoning. However, they often produce excessively long outputs, leading to prohibitively large key-value (KV) caches during inference. While chain-of-thought inference significantly improves performance on complex reasoning tasks, it can also lead to reasoning failures when deployed with existing KV cache compression approaches. To address this, we propose Redundancy-aware KV Cache Compression for Reasoning models (R-KV), a novel method specifically targeting redundant tokens in reasoning models. Our method preserves nearly 100% of the full KV cache performance using only 10% of the KV cache, substantially outperforming existing KV cache baselines, which reaches only 60% of the performance. Remarkably, R-KV even achieves 105% of full KV cache performance with 16% of the KV cache. This KV-cache reduction also leads to a 90% memory saving and a 6.6× throughput over standard chain-of-thought reasoning inference. Experimental results show that R-KV consistently outperforms existing KV cache compression baselines across two mathematical reasoning datasets.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"60980-61005"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13183371/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147977627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Hyperphantasia: A Benchmark for Evaluating the Mental Visualization Capabilities of Multimodal LLMs. 幻觉过度：评估多模式法学硕士心理可视化能力的基准。

Advances in neural information processing systems Pub Date : 2025-12-01

Mohammad Shahab Sepehri, Berk Tinaz, Zalan Fabian, Mahdi Soltanolkotabi

{"title":"Hyperphantasia: A Benchmark for Evaluating the Mental Visualization Capabilities of Multimodal LLMs.","authors":"Mohammad Shahab Sepehri, Berk Tinaz, Zalan Fabian, Mahdi Soltanolkotabi","doi":"","DOIUrl":"","url":null,"abstract":"Mental visualization, the ability to construct and manipulate visual representations internally, is a core component of human cognition and plays a vital role in tasks involving reasoning, prediction, and abstraction. Despite the rapid progress of Multimodal Large Language Models (MLLMs), current benchmarks primarily assess passive visual perception, offering limited insight into the more active capability of internally constructing visual patterns to support problem solving. Yet mental visualization is a critical cognitive skill in humans, supporting abilities such as spatial navigation, predicting physical trajectories, and solving complex visual problems through imaginative simulation. To bridge this gap, we introduce Hyperphantasia, a synthetic benchmark designed to evaluate the mental visualization abilities of MLLMs through four carefully constructed puzzles. Each puzzle is procedurally generated and presented at three difficulty levels, enabling controlled analysis of model performance across increasing complexity. Our comprehensive evaluation of state-of-the-art models reveals a substantial gap between the performance of humans and MLLMs. Additionally, we explore the potential of reinforcement learning to improve visual simulation capabilities. Our findings suggest that while some models exhibit partial competence in recognizing visual patterns, robust mental visualization remains an open challenge for current MLLMs. Our dataset is publicly available at Huggingface, and the evaluation code can be found at GitHub.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13225675/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148152332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

QuanDA: Quantile-Based Discriminant Analysis for High-Dimensional Imbalanced Classification. 基于分位数的高维不平衡分类判别分析。

Advances in neural information processing systems Pub Date : 2025-12-01

Qian Tang, Yuwen Gu, Boxiang Wang

{"title":"QuanDA: Quantile-Based Discriminant Analysis for High-Dimensional Imbalanced Classification.","authors":"Qian Tang, Yuwen Gu, Boxiang Wang","doi":"","DOIUrl":"","url":null,"abstract":"Binary classification with imbalanced classes is a common and fundamental task, where standard machine learning methods often struggle to provide reliable predictive performance. Although numerous approaches have been proposed to address this issue, classification in low-sample-size and high-dimensional settings still remains particularly challenging. The abundance of noisy features in high-dimensional data limits the effectiveness of classical methods due to overfitting, and the minority class is even difficult to detect because of its severe underrepresentation with low sample size. To address this challenge, we introduce Quantile-based Discriminant Analysis (QuanDA), which builds upon a novel connection with quantile regression and naturally accounts for class imbalance through appropriately chosen quantile levels. We provide comprehensive theoretical analysis to validate QuanDA in ultra-high dimensional settings. Through extensive simulation studies and high-dimensional benchmark data analysis, we demonstrate that QuanDA overall outperforms existing classification methods for imbalanced data, including cost-sensitive large-margin classifiers, random forests, and SMOTE.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"159735-159768"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13333170/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148392594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep Continuous-Time State-Space Models for Marked Event Sequences. 标记事件序列的深度连续时间状态空间模型。

Advances in neural information processing systems Pub Date : 2025-12-01

Yuxin Chang, Alex Boyd, Cao Xiao, Taha Kass-Hout, Parminder Bhatia, Padhraic Smyth, Andrew Warrington

{"title":"Deep Continuous-Time State-Space Models for Marked Event Sequences.","authors":"Yuxin Chang, Alex Boyd, Cao Xiao, Taha Kass-Hout, Parminder Bhatia, Padhraic Smyth, Andrew Warrington","doi":"","DOIUrl":"","url":null,"abstract":"Marked temporal point processes (MTPPs) model sequences of events occurring at irregular time intervals, with wide-ranging applications in fields such as healthcare, finance and social networks. We propose the state-space point process (S2P2) model, a novel and performant model that leverages techniques derived for modern deep state-space models (SSMs) to overcome limitations of existing MTPP models, while simultaneously imbuing strong inductive biases for continuous-time event sequences that other discrete sequence models (i.e., RNNs, transformers) do not capture. Inspired by the classical linear Hawkes processes, we propose an architecture that interleaves stochastic jump differential equations with nonlinearities to create a highly expressive intensity-based MTPP model, without the need for restrictive parametric assumptions for the intensity. Our approach enables efficient training and inference with a parallel scan, bringing linear complexity and sublinear scaling while retaining expressivity to MTPPs. Empirically, S2P2 achieves state-of-the-art predictive likelihoods across eight real-world datasets, delivering an average improvement of 33% over the best existing approaches.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"162672-162713"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13182340/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147977690","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable. 对于任意客户参与下的联邦学习，可以实现精确的线性收敛。

Advances in neural information processing systems Pub Date : 2025-12-01

Bicheng Ying, Zhe Li, Haibo Yang

{"title":"Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable.","authors":"Bicheng Ying, Zhe Li, Haibo Yang","doi":"","DOIUrl":"","url":null,"abstract":"This work tackles the fundamental challenges in Federated Learning (FL) posed by arbitrary client participation and data heterogeneity, prevalent characteristics in practical FL settings. It is well-established that popular FedAvg-style algorithms struggle with exact convergence and can suffer from slow convergence rates since a decaying learning rate is required to mitigate these scenarios. To address these issues, we introduce the concept of stochastic matrix and the corresponding time-varying graphs as a novel modeling tool to accurately capture the dynamics of arbitrary client participation and the local update procedure. Leveraging this approach, we offer a fresh decentralized perspective on designing FL algorithms and present FOCUS, Federated Optimization with Exact Convergence via Push-pull Strategy, a provably convergent algorithm designed to effectively overcome the previously mentioned two challenges. More specifically, we provide a rigorous proof demonstrating that FOCUS achieves exact convergence with a linear rate regardless of the arbitrary client participation, establishing it as the first work to demonstrate this significant result.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"40156-40201"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13152002/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147870820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

NFL-BA: Near-Field Light Bundle Adjustment for SLAM in Dynamic Lighting. NFL-BA: SLAM在动态照明中的近场光束调节。

Advances in neural information processing systems Pub Date : 2025-12-01

Andrea Dunn Beltran, Daniel Rho, Marc Niethammer, Roni Sengupta

{"title":"NFL-BA: Near-Field Light Bundle Adjustment for SLAM in Dynamic Lighting.","authors":"Andrea Dunn Beltran, Daniel Rho, Marc Niethammer, Roni Sengupta","doi":"","DOIUrl":"","url":null,"abstract":"Simultaneous Localization and Mapping (SLAM) systems typically assume static, distant illumination; however, many real-world scenarios, such as endoscopy, subterranean robotics, and search & rescue in collapsed environments, require agents to operate with a co-located light and camera in the absence of external lighting. In such cases, dynamic near-field lighting introduces strong, view-dependent shading that significantly degrades SLAM performance. We introduce Near-Field Lighting Bundle Adjustment Loss (NFL-BA) which explicitly models near-field lighting as a part of Bundle Adjustment loss and enables better performance for scenes captured with dynamic lighting. NFL-BA can be integrated into neural rendering-based SLAM systems with implicit or explicit scene representations. Our evaluations mainly focus on endoscopy procedure where SLAM can enable autonomous navigation, guidance to unsurveyed regions, blindspot detections, and 3D visualizations, which can significantly improve patient outcomes and endoscopy experience for both physicians and patients. Replacing Photometric Bundle Adjustment loss of SLAM systems with NFL-BA leads to significant improvement in camera tracking, 37% for MonoGS and 14% for EndoGS, and leads to state-of-the-art camera tracking and mapping performance on the C3VD colonoscopy dataset. Further evaluation on indoor scenes captured with phone camera with flashlight turned on, also demonstrate significant improvement in SLAM performance due to NFL-BA.","PeriodicalId":72099,"journal":{"name":"Advances in neural information processing systems","volume":"38 ","pages":"15437-15465"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13148239/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147846656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0