---
title: "NeurIPS 2025 — all accepted papers, page 52 — Elamur Research"
description: "All 5,819 papers of NeurIPS 2025 · page 52 of 59, the most cited first; those with our summary link to it."
canonical: "https://research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/52/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/52/)

[home](https://md.research.elamur.ai/free/en/) / [venues](https://md.research.elamur.ai/free/en/venues/) / [NeurIPS](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/) / [2025](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/) / [papers](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/) / page 52

# NeurIPS 2025: all accepted papers

5,819 papers · page 52 of 59 · the most cited first · [← NeurIPS 2025](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/)

[← prev](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/51/) [1](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/) … [50](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/50/) [51](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/51/) **52** [53](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/53/) … [59](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/59/) [next →](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/53/)

5101. **[Sequentially Auditing Differential Privacy ↗](https://doi.org/10.52202/085713-4821)**Tomás González Lara, Mateo Dulce Rubio, Aaditya Ramdas et al.
5102. **[Set Smoothness Unlocks Clarke Hyper-stationarity in Bilevel Optimization ↗](https://doi.org/10.52202/085713-4504)**He Chen, Jiajin Li, Anthony Man–Cho So
5103. **[Set-LLM: A Permutation-Invariant LLM ↗](https://doi.org/10.52202/085713-2105)**Béni Egressy, Jan Stühmer
5104. **[Setting ε is not the Issue in Differential Privacy ↗](https://doi.org/10.52202/085713-4798)**Edwige Cyffers
5105. **[Shallow Flow Matching for Coarse-to-Fine Text-to-Speech Synthesis ↗](https://doi.org/10.52202/085713-2571)**Dong Lin Yang, Yiyi Cai, Yuki Saito et al.
5106. **[Shape it Up! Restoring LLM Safety during Finetuning ↗](https://doi.org/10.52202/085713-4397)**ShengYun Peng, Pin-Yu Chen, Jianfeng Chi et al.
5107. **[ShapeEmbed: a self-supervised learning framework for 2D contour quantification ↗](https://doi.org/10.52202/085713-0416)**Anna Foix, Craig Russell, Alexander Krull et al.
5108. **[ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Models ↗](https://doi.org/10.52202/085713-0897)**B. Q. Huang, Ming Jin, Yuxuan Liang et al.
5109. **[Shaping Sequence Attractor Schema in Recurrent Neural Networks ↗](https://doi.org/10.52202/085713-0243)**Zhikun Chu, Bo Ho, Xiaolong Zou et al.
5110. **[Shapley-Based Data Valuation for Weighted k-Nearest Neighbors ↗](https://doi.org/10.52202/085713-1615)**Guangyi Zhang, Qiyu Liu, Aristides Gionis
5111. **[Sharp Analysis for KL-Regularized Contextual Bandits and RLHF ↗](https://doi.org/10.52202/085713-3600)**Heyang Zhao, Chenlu Ye, Quanquan Gu et al.
5112. **[Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs ↗](https://doi.org/10.52202/085713-3747)**Siyuan Chen, Runlong Zhou, Zihan Zhang et al.
5113. **[Sharp Gaussian approximations for Decentralized Federated Learning ↗](https://doi.org/10.52202/085713-5253)**Soham Bonnerjee, Sayar Karmakar, Wei Biao Wu
5114. **[Sharp Matrix Empirical Bernstein Inequalities ↗](https://doi.org/10.52202/085713-5680)**Hongjian Wang, Aaditya Ramdas
5115. **[SharpZO: Hybrid Sharpness-Aware Vision Language Model Prompt Tuning via Forward-Only Passes ↗](https://doi.org/10.52202/085713-4811)**Yifan Yang, Zhen Zhang, Rupak Vignesh Swaminathan et al.
5116. **[Sharper Convergence Rates for Nonconvex Optimisation via Reduction Mappings ↗](https://doi.org/10.52202/085713-2995)**Evan Markou, Thalaiyasingam Ajanthan, Stephen Gould
5117. **[Sheetpedia: A 300K-Spreadsheet Corpus for Spreadsheet Intelligence and LLM Fine-Tuning ↗](https://doi.org/10.52202/085713-3355)**Zailong Tian, Zhuoheng Han, Houfeng Wang et al.
5118. **[ShiQ: Bringing back Bellman to LLMs ↗](https://doi.org/10.52202/085713-3536)**Pierre Clavier, Nathan Grinsztajn, Raphaël Avalos et al.
5119. **[Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning ↗](https://doi.org/10.52202/085713-2425)**Bastien Dubail, Stefan Stojanovic, Alexandre Proutière
5120. **[ShoeFit: A New Dataset and Dual-image-stream DiT Framework for Virtual Footwear Try-On ↗](https://doi.org/10.52202/085713-1088)**Yuhan Li, Zhiyu Jin, Yifan Tong et al.
5121. **[Short-length Adversarial Training Helps LLMs Defend Long-length Jailbreak Attacks: Theoretical and Empirical Evidence ↗](https://doi.org/10.52202/085713-2157)**Shaopeng Fu, Liang Ding, Jingfeng ZHANG et al.
5122. **[ShortListing Model: A Streamlined Simplex Diffusion for Discrete Variable Generation ↗](https://doi.org/10.52202/085713-1558)**Yuxuan Song, Zhe Zhang, Yu Pei et al.
5123. **[Shortcut Features as Top Eigenfunctions of NTK: A Linear Neural Network Case and More ↗](https://doi.org/10.52202/085713-3149)**Jinwoo Lim, Suhyun Kim, Soo‐Mook Moon
5124. **[Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens ↗](https://doi.org/10.52202/085713-5763)**Samuele Bortolotti, Emanuele Marconato, Paolo Morettin et al.
5125. **[Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch ↗](https://doi.org/10.52202/085713-5119)**Xu Cai, Yang Qing Wu, Qianli Chen et al.
5126. **[ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning ↗](https://doi.org/10.52202/085713-1302)**Jingyang Yi, Jiazheng Wang, Sida Li
5127. **[Siegel Neural Networks ↗](https://doi.org/10.52202/085713-4627)**Xuan Son Nguyen, Aymeric Histace, Nistor Grozavu
5128. **[Sign-In to the Lottery: Reparameterizing Sparse Training ↗](https://doi.org/10.52202/085713-3932)**Advait Gadhikar, Tom Jacobs, Chao Zhou et al.
5129. **[SignFlow Bipartite Subgraph Network For Large-Scale Graph Link Sign Prediction ↗](https://doi.org/10.52202/085713-3286)**Yixiao Zhou, Xiaoqing Lyu, Hongxiang Lin et al.
5130. **[Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation ↗](https://doi.org/10.52202/085713-0576)**David Heineman, Valentin Hofmann, Ian Magnusson et al.
5131. **[Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-Generator ↗](https://doi.org/10.52202/085713-4317)**Peiwen Yuan, Yiwei Li, Shaoxiong Feng et al.
5132. **[SilentStriker: Toward Stealthy Bit-Flip Attacks on Large Language Models ↗](https://doi.org/10.52202/085713-1732)**Haotian Xu, Qingsong Peng, Jie Shi et al.
5133. **[SimSort: A Data-Driven Framework for Spike Sorting by Large-Scale Electrophysiology Simulation ↗](https://doi.org/10.52202/085713-3840)**Yimu Zhang, Dongqi Han, Yansen Wang et al.
5134. **[Simple and Effective Specialized Representations for Fair Classifiers ↗](https://doi.org/10.52202/085713-0610)**Alberto Sinigaglia, Davide Sartor, Marina Ceccon et al.
5135. **[Simple and Optimal Sublinear Algorithms for Mean Estimation ↗](https://doi.org/10.52202/085713-4321)**Beatrice Bertolotti, Matteo Russo, Chris Schwiegelshohn et al.
5136. **[SimpleStrat: Diversifying Language Model Generation with Stratification ↗](https://doi.org/10.52202/085713-3897)**Justin Wong, Yury Orlovskiy, Alexander Shypula et al.
5137. **[SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translation ↗](https://doi.org/10.52202/085713-1423)**Chenyang Le, Bing Han, Junqian Li et al.
5138. **[Simulation-Based Inference for Adaptive Experiments ↗](https://doi.org/10.52202/085713-4761)**Brian Cho, Aurélien Bibaut, Nathan Kallus
5139. **[Simultaneous Modeling of Protein Conformation and Dynamics via Autoregression ↗](https://doi.org/10.52202/085713-3666)**Yuning Shen, Lihao Wang, Huizhuo Yuan et al.
5140. **[Simultaneous Statistical Inference for Off-Policy Evaluation in Reinforcement Learning ↗](https://doi.org/10.52202/085713-2367)**Tianpai Luo, Xinyuan Fan, Weichi Wu
5141. **[Simultaneous Swap Regret Minimization via KL-Calibration ↗](https://doi.org/10.52202/085713-2116)**Haipeng Luo, Spandan Senapati, Vatsal Sharan
5142. **[SingRef6D: Monocular Novel Object Pose Estimation with a Single RGB Reference ↗](https://doi.org/10.52202/085713-0854)**Jiahui Wang, Haiyue Zhu, Haoren Guo et al.
5143. **[Single-Step Operator Learning for Conditioned Time-Series Diffusion Models ↗](https://doi.org/10.52202/085713-5472)**Hui Chen, Vikas Singh
5144. **[Sinusoidal Initialization, Time for a New Start ↗](https://doi.org/10.52202/085713-2285)**Alberto Fernández-Hernández, Jose I. Mestre, Manuel F. Dolz et al.
5145. **[Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model ↗](https://doi.org/10.52202/085713-3046)**Ruiping Liu, Junwei Zheng, Yufan Chen et al.
5146. **[Sketch-Augmented Features Improve Learning Long-Range Dependencies in Graph Neural Networks ↗](https://doi.org/10.52202/085713-2568)**Ryien Hosseini, Filippo Simini, Venkatram Vishwanath et al.
5147. **[Sketched Gaussian Mechanism for Private Federated Learning ↗](https://doi.org/10.52202/085713-4394)**Qiaobo Li, Zhijie Chen, Arindam Banerjee
5148. **[Skrull: Towards Efficient Long Context Fine-tuning through Dynamic Data Scheduling ↗](https://doi.org/10.52202/085713-3841)**Hongtao Xu, Wenting Shen, Yuanxin Wei et al.
5149. **[SkyLadder: Better and Faster Pretraining via Context Window Scheduling ↗](https://doi.org/10.52202/085713-4227)**Tongyao Zhu, Qian Liu, Haonan Wang et al.
5150. **[Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families ↗](https://doi.org/10.52202/085713-1318)**Felipe Maia Polo, Seamus Somerstep, Leshem Choshen et al.
5151. **[Slow Transition to Low-Dimensional Chaos in Heavy-Tailed Recurrent Neural Networks ↗](https://doi.org/10.52202/085713-4102)**Eva Xie, Ştefan Mihalaş, Łukasz Kuśmierz
5152. **[Small Resamples, Sharp Guarantees: Convergence Rates for Resampled Studentized Quantile Estimators ↗](https://doi.org/10.52202/085713-2090)**Imon Banerjee, Sayak Chakrabarty
5153. **[SmallKV: Small Model Assisted Compensation of KV Cache Compression for Efficient LLM Inference ↗](https://doi.org/10.52202/085713-1624)**Yi Zhao, Yajuan Peng, Cam-Tu Nguyen et al.
5154. **[Smart Surrogate Losses for Contextual Stochastic Linear Optimization with Robust Constraints ↗](https://doi.org/10.52202/085713-2523)**Hyungki Im, Wyame Benslimane, Paul Grigas
5155. **[SmartCache: Context-aware Semantic Cache for Efficient Multi-turn LLM Inference ↗](https://doi.org/10.52202/085713-5740)**Chengye Yu, Tianyu Wang, Zili Shao et al.
5156. **[SmokeViz: A Large-Scale Satellite Dataset for Wildfire Smoke Detection and Segmentation ↗](https://doi.org/10.52202/085713-1383)**Rey Koki, Michael McCabe, Dhruv Kedar et al.
5157. **[Smooth Quadratic Prediction Markets ↗](https://doi.org/10.52202/085713-2054)**Enrique Nueve, Bo Waggoner
5158. **[Smooth Regularization for Efficient Video Recognition ↗](https://doi.org/10.52202/085713-4876)**Gil Goldman, Raja Giryes, Mahadev Satyanarayanan
5159. **[Smooth Sailing: Lipschitz-Driven Uncertainty Quantification for Spatial Associations ↗](https://doi.org/10.52202/085713-4505)**David Burt, Renato Berlinghieri, Stephen Bates et al.
5160. **[Smoothed Agnostic Learning of Halfspaces over the Hypercube ↗](https://doi.org/10.52202/085713-3079)**Yiwen Kou, Raghu Meka
5161. **[Smoothed Differentiation Efficiently Mitigates Shattered Gradients in Explanations ↗](https://doi.org/10.52202/085713-0271)**Adrian Hill, Neal McKee, Johannes Maeß et al.
5162. **[SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions ↗](https://doi.org/10.52202/085713-2492)**Xianzhe Fan, Xuhui Zhou, Chuanyang Jin et al.
5163. **[SoPo: Text-to-Motion Generation Using Semi-Online Preference Optimization ↗](https://doi.org/10.52202/085713-2029)**Xiaofeng Tan, Hongsong Wang, Xin Geng et al.
5164. **[Social World Model-Augmented Mechanism Design Policy Learning ↗](https://doi.org/10.52202/085713-3730)**Xiaoyuan Zhang, Yizhe Huang, Chengdong Ma et al.
5165. **[Soft Task-Aware Routing of Experts for Equivariant Representation Learning ↗](https://doi.org/10.52202/085713-0372)**Jaeseung Jeon, Hyunseo Jang, Jy-yong Sohn et al.
5166. **[Solver-Free Decision-Focused Learning for Linear Optimization Problems ↗](https://doi.org/10.52202/085713-5284)**Senne Berden, Ali İrfan Mahmutoğulları, Dimosthenis C. Tsouros et al.
5167. **[Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary Dynamics ↗](https://doi.org/10.52202/085713-3484)**Lorenzo Magnino, Kai Shao, Zida Wu et al.
5168. **[Solving Discrete (Semi) Unbalanced Optimal Transport with Equivalent Transformation Mechanism and KKT-Multiplier Regularization ↗](https://doi.org/10.52202/085713-3519)**Weiming Liu, Xinting Liao, Jun Dan et al.
5169. **[Solving Inequality Proofs with Large Language Models ↗](https://doi.org/10.52202/085713-4559)**Jiayi Sheng, Luna Lyu, Jikai Jin et al.
5170. **[Solving Neural Min-Max Games: The Role of Architecture, Initialization & Dynamics ↗](https://doi.org/10.52202/085713-2227)**Deep Patel, Emmanouil-Vasileios Vlatakis-Gkaragkounis
5171. **[Solving and Learning Partial Differential Equations with Variational Q-Exponential Processes ↗](https://doi.org/10.52202/085713-5787)**Guangting Yu, Shiwei Lan
5172. **[Solving the Asymmetric Traveling Salesman Problem via Trace-Guided Cost Augmentation ↗](https://doi.org/10.52202/085713-1917)**Zhen Zhang, Javen Qinfeng Shi, Wee Sun Lee
5173. **[Some Optimizers are More Equal: Understanding the Role of Optimizers in Group Fairness ↗](https://doi.org/10.52202/085713-0442)**Mojtaba Kolahdouzi, Hatice Güneş, Ali Etemad
5174. **[SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion Refinement ↗](https://doi.org/10.52202/085713-1150)**Chenyu Yang, Shuai Wang, Hangting Chen et al.
5175. **[SpEx: A Spectral Approach to Explainable Clustering ↗](https://doi.org/10.52202/085713-0761)**Tal Argov, Tal Wagner
5176. **[Space Group Equivariant Crystal Diffusion ↗](https://doi.org/10.52202/085713-2439)**Rees Chang, Angela Pak, Alex Guerra et al.
5177. **[Spark Transformer: Reactivating Sparsity in Transformer FFN and Attention ↗](https://doi.org/10.52202/085713-0800)**Chong You, Kan Wu, Zhipeng Jia et al.
5178. **[Sparse Diffusion Autoencoder for Test-time Adapting Prediction of Complex Systems ↗](https://doi.org/10.52202/085713-0414)**Jingwen Cheng, Ruikun Li, Huandong Wang et al.
5179. **[Sparse Gaussian Processes: Structured Approximations and Power-EP Revisited ↗](https://doi.org/10.52202/085713-3530)**Thang D. Bui, Michalis K. Titsias
5180. **[Sparse Image Synthesis via Joint Latent and RoI Flow ↗](https://doi.org/10.52202/085713-4886)**Ziteng Gao, Jay Zhangjie Wu, Mike Zheng Shou
5181. **[Sparse Optimistic Information Directed Sampling ↗](https://doi.org/10.52202/085713-2758)**Ludovic Schwartz, Hamish Flynn, Gergely Neu
5182. **[Sparse Polyak: an adaptive step size rule for high-dimensional M-estimation ↗](https://doi.org/10.52202/085713-0079)**Tianqi Qiao, Marie Maros
5183. **[SparseMVC: Probing Cross-view Sparsity Variations for Multi-view Clustering ↗](https://doi.org/10.52202/085713-5172)**Ruimeng Liu, Xin Zou, Chang Tang et al.
5184. **[Sparta Alignment: Collectively Aligning Multiple Language Models through Combat ↗](https://doi.org/10.52202/085713-4430)**Yuru Jiang, Wenxuan Ding, Shangbin Feng et al.
5185. **[Spatial-Aware Decision-Making with Ring Attractors in Reinforcement Learning Systems ↗](https://doi.org/10.52202/085713-5499)**Marcos Negre Saura, Richard Allmendinger, Wei Li Pan et al.
5186. **[Spatially-aware Weights Tokenization for NeRF-Language Models ↗](https://doi.org/10.52202/085713-5004)**Andrea Amaduzzi, Pierluigi Zama Ramirez, Giuseppe Lisanti et al.
5187. **[Spatiotemporal Consensus with Scene Prior for Unsupervised Domain Adaptive Person Search ↗](https://doi.org/10.52202/085713-0929)**Yimin Jiang, Huibing Wang, Jinjia peng
5188. **[SpecEM: Training-Free LLM Ensembling via Iterative Drafting, Verification, and Online Feedback ↗](https://doi.org/10.52202/085713-1752)**Bo Lv, Nayu Liu, Chen Tang et al.
5189. **[SpecMAS: A Multi-Agent System for Self-Verifying System Generation via Formal Model Checking ↗](https://doi.org/10.52202/085713-2266)**Rishabh Agrawal, Kaushik Ranade, Aja Khanal et al.
5190. **[SpecMER: Fast Protein Generation with K-mer Guided Speculative Decoding ↗](https://doi.org/10.52202/085713-0570)**Thomas Walton, Darin Tsui, Aryan Musharaf et al.
5191. **[SpectraLDS: Provable Distillation for Linear Dynamical Systems ↗](https://doi.org/10.52202/085713-3579)**Devan Shah, Shlomo Fortgang, Sofiia Druchyna et al.
5192. **[Spectral Analysis of Representational Similarity with Limited Neurons ↗](https://doi.org/10.52202/085713-0823)**Hyunmo Kang, Abdülkadir Canatar, SueYeon Chung
5193. **[Spectral Compressive Imaging via Chromaticity-Intensity Decomposition ↗](https://doi.org/10.52202/085713-0142)**Xiaodong Wang, Zijun He, Ping Wang et al.
5194. **[Spectral Conditioning of Attention Improves Transformer Performance ↗](https://doi.org/10.52202/085713-1982)**Hemanth Saratchandran, Simon Lucey
5195. **[Spectral Estimation with Free Decompression ↗](https://doi.org/10.52202/085713-0070)**Siavash Ameli, Chris van der Heide, Liam Hodgkinson et al.
5196. **[Spectral Graph Coarsening Using Inner Product Preservation and the Grassmann Manifold ↗](https://doi.org/10.52202/085713-3915)**I. Bernard Cohen, Ronen Talmon
5197. **[Spectral Graph Neural Networks are Incomplete on Graphs with a Simple Spectrum ↗](https://doi.org/10.52202/085713-3631)**Snir Hordan, Maya Bechler-Speicher, Gur Lifshitz et al.
5198. **[Spectral Learning for Infinite-Horizon Average-Reward POMDPs ↗](https://doi.org/10.52202/085713-1744)**Alessio Russo, Alberto Maria Metelli, Marcello Restelli
5199. **[Spectral Perturbation Bounds for Low-Rank Approximation with Applications to Privacy ↗](https://doi.org/10.52202/085713-0331)**Phuc Tran, Van Vu, Nisheeth K. Vishnoi
5200. **[Speculate Deep and Accurate: Lossless and Training-Free Acceleration for Offloaded LLMs via Substitute Speculative Decoding ↗](https://doi.org/10.52202/085713-1815)**Pei-Shuo Wang, Jian-Jia Chen, Chun-Che Yang et al.

[← prev](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/51/) [1](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/) … [50](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/50/) [51](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/51/) **52** [53](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/53/) … [59](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/59/) [next →](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/53/)

- [← back to](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/) — NeurIPS 2025