---
title: "NeurIPS 2025 — all accepted papers, page 39 — Elamur Research"
description: "All 5,819 papers of NeurIPS 2025 · page 39 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/39/"
---
[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/39/)

[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 39

# NeurIPS 2025: all accepted papers

5,819 papers · page 39 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/38/) [1](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/) … [30](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/30/) … [38](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/38/) **39** [40](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/40/) … [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/40/)

3801. **[KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments ↗](https://doi.org/10.52202/085713-0210)**Junyoung Park, Dalton Jones, Matthew Morse et al.
3802. **[Kinaema: a recurrent sequence model for memory and pose in motion ↗](https://doi.org/10.52202/085713-2608)**Mert Bülent Sarıyıldız, Philippe Weinzaepfel, Guillaume Bono et al.
3803. **[Kinetics: Rethinking Test-Time Scaling Law ↗](https://doi.org/10.52202/085713-2827)**Ranajoy Sadhukhan, Zhuoming Chen, Haizhong Zheng et al.
3804. **[Knee-Deep in C-RASP: A Transformer Depth Hierarchy ↗](https://doi.org/10.52202/085713-1249)**Andy J Yang, Michaël Cadilhac, David Chiang
3805. **[Knot So Simple: A Minimalistic Environment for Spatial Reasoning ↗](https://doi.org/10.52202/085713-2125)**Zizhao Chen, Yoav Artzi
3806. **[Know Thyself by Knowing Others: Learning Neuron Identity from Population Context ↗](https://doi.org/10.52202/085713-3325)**Vinam Arora, Divyansha Lachi, Ian Knight et al.
3807. **[Know What You Don't Know: Uncertainty Calibration of Process Reward Models ↗](https://doi.org/10.52202/085713-1297)**Young‐Jin Park, Kristjan H. Greenewald, Kaveh Alim et al.
3808. **[KnowMol: Advancing Molecular Large Language Models with Multi-Level Chemical Knowledge ↗](https://doi.org/10.52202/085713-1328)**Zaifei Yang, Hong Chang, Ruibing Hou et al.
3809. **[Knowing When to Stop: Efficient Context Processing via Latent Sufficiency Signals ↗](https://doi.org/10.52202/085713-1376)**Roy Xie, Junlin Wang, Paul Rosu et al.
3810. **[Knowledge Distillation Detection for Open-weights Models ↗](https://doi.org/10.52202/085713-3999)**Qin Shi, Amber Yijia Zheng, Qifan Song et al.
3811. **[Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning ↗](https://doi.org/10.52202/085713-2861)**Xusheng Cao, Haori Lu, Linlan Huang et al.
3812. **[Knowledge Starts with Practice: Knowledge-Aware Exercise Generative Recommendation with Adaptive Multi-Agent Cooperation ↗](https://doi.org/10.52202/085713-3110)**Yangtao Zhou, Hua Chu, chen chen et al.
3813. **[Kuramoto Orientation Diffusion Models ↗](https://doi.org/10.52202/085713-0143)**Yue Song, T. Anderson Keller, Sevan Brodjian et al.
3814. **[L2DGCN: Learnable Enhancement and Label Selection Dynamic Graph Convolutional Networks for Mitigating Degree Bias ↗](https://doi.org/10.52202/085713-5809)**Jingxiao Zhang, Shifei Ding, Jian Zhang et al.
3815. **[L2RSI: Cross-view LiDAR-based Place Recognition for Large-scale Urban Scenes via Remote Sensing Imagery ↗](https://doi.org/10.52202/085713-5366)**Ziwei Shi, Xiaoran Zhang, Wenjing Xu et al.
3816. **[LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs ↗](https://doi.org/10.52202/085713-1485)**Ran Li, Hao Wang, Chengzhi Mao
3817. **[LASeR: Learning to Adaptively Select Reward Models with Multi-Arm Bandits ↗](https://doi.org/10.52202/085713-3895)**Duy Nguyen, Archiki Prasad, Elias Stengel-Eskin et al.
3818. **[LBMKGC: Large Model-Driven Balanced Multimodal Knowledge Graph Completion ↗](https://doi.org/10.52202/085713-3736)**Yuan Guo, Qian Ma, Hui Li et al.
3819. **[LCDB 1.1: A Database Illustrating Learning Curves Are More Ill-Behaved Than Previously Thought ↗](https://doi.org/10.52202/085713-0487)**Cheng Yan, Felix Mohr, Tom Julian Viering
3820. **[LD-RoViS: Training-free Robust Video Steganography for Deterministic Latent Diffusion Model ↗](https://doi.org/10.52202/085713-4276)**Xiangkun Wang, Kejiang Chen, Lincong Li et al.
3821. **[LIFEBENCH: Evaluating Length Instruction Following in Large Language Models ↗](https://doi.org/10.52202/085713-4574)**Wei Zhang, Zhenhong Zhou, Kun Wang et al.
3822. **[LIMOPro: Reasoning Refinement for Efficient and Effective Test-time Scaling ↗](https://doi.org/10.52202/085713-5246)**Yang Xiao, Jiashuo WANG, Ruifeng Yuan et al.
3823. **[LLM Interpretability with Identifiable Temporal-Instantaneous Representation ↗](https://doi.org/10.52202/085713-3472)**Xiangchen Song, Jiaqi Sun, Zijian Li et al.
3824. **[LLM Layers Immediately Correct Each Other ↗](https://doi.org/10.52202/085713-4643)**Arjun Patrawala, Jiahai Feng, Erik Jones et al.
3825. **[LLM Meets Diffusion: A Hybrid Framework for Crystal Material Generation ↗](https://doi.org/10.52202/085713-5635)**Subhojyoti Khastagir, Kishalay Das, Pawan Goyal et al.
3826. **[LLM Safety Alignment is Divergence Estimation in Disguise ↗](https://doi.org/10.52202/085713-3145)**Rajdeep Haldar, Ziyi Wang, Guang Lin et al.
3827. **[LLM at Network Edge: A Layer-wise Efficient Federated Fine-tuning Approach ↗](https://doi.org/10.52202/085713-3506)**Jinglong Shen, Nan Cheng, Wenchao Xu et al.
3828. **[LLM-DAMVC: A Large Language Model Assisted Dynamic Agent for Multi-View Clustering ↗](https://doi.org/10.52202/085713-3990)**Qianqian Wang, Qianqian Wang
3829. **[LOMIA: Label-Only Membership Inference Attacks against Pre-trained Large Vision-Language Models ↗](https://doi.org/10.52202/085713-5140)**Yihao Liu, Xinqi Lyu, Dong Wang et al.
3830. **[LOPT: Learning Optimal Pigovian Tax in Sequential Social Dilemmas ↗](https://doi.org/10.52202/085713-1229)**Yun Hua, Shang Gao, Wenhao Li et al.
3831. **[LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups ↗](https://doi.org/10.52202/085713-2549)**Masih Aminbeidokhti, Subhankar Roy, Eric Granger et al.
3832. **[LTD-Bench: Evaluating Large Language Models by Letting Them Draw ↗](https://doi.org/10.52202/085713-1283)**Liuhao Lin, Ke Li, Zihan Xu et al.
3833. **[LVLM-Driven Attribute-Aware Modeling for Visible-Infrared Person Re-Identification ↗](https://doi.org/10.52202/085713-0066)**Zhiqi Pang, Lingling Zhao, Junjie Wang et al.
3834. **[LangHOPS: Language Grounded Hierarchical Open-Vocabulary Part Segmentation ↗](https://doi.org/10.52202/085713-5756)**Miao Yang, Jan-Nico Zaech, Xi Wang et al.
3835. **[Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale ↗](https://doi.org/10.52202/085713-3426)**James A. Michaelov, Roger Lévy, Benjamin Bergen
3836. **[Language Models can Self-Improve at State-Value Estimation for Better Search ↗](https://doi.org/10.52202/085713-5544)**Ethan Mendes, Alan Ritter
3837. **[Language Ranker: A Lightweight Ranking framework for LLM Decoding ↗](https://doi.org/10.52202/085713-4025)**Chenheng Zhang, Tianqi Du, Jizhe Zhang et al.
3838. **[Language‑Bias‑Resilient Visual Question Answering via Adaptive Multi‑Margin Collaborative Debiasing ↗](https://doi.org/10.52202/085713-4191)**Huanjia Zhu, Shuyuan Zheng, Yishu Liu et al.
3839. **[Large Language Models Think Too Fast To Explore Effectively ↗](https://doi.org/10.52202/085713-3428)**Lan Pan, Hanbo Xie, Robert C. Wilson
3840. **[Large Language Models as Model Organisms for Human Associative Learning ↗](https://doi.org/10.52202/085713-3761)**Camila Kolling, Vy Vo, Mariya Toneva
3841. **[Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression ↗](https://doi.org/10.52202/085713-3490)**Jingfeng Wu, Pierre Marion, Peter L. Bartlett
3842. **[Large language models can learn and generalize steganographic chain-of-thought under process supervision ↗](https://doi.org/10.52202/085713-0930)**Robert Mc Carthy, Joey SKAF, Luis Ibañez-Lissen et al.
3843. **[Last Iterate Convergence in Monotone Mean Field Games ↗](https://doi.org/10.52202/085713-0611)**Noboru Isobe, Kenshi Abe, Kaito Ariu
3844. **[Last-Iterate Convergence of Smooth Regret Matching+ Variants in Learning Nash Equilibria ↗](https://doi.org/10.52202/085713-0644)**Linjian Meng, Youzhi Zhang, Zhenxing Ge et al.
3845. **[Latency NMS Attacks: Is It Real Life or Is It Just Fantasy? ↗](https://doi.org/10.52202/085713-1289)**Jean-Philippe Monteuuis, Cong Chen, Jonathan Petit
3846. **[Latent Mixture of Symmetries for Sample-Efficient Dynamic Learning ↗](https://doi.org/10.52202/085713-3626)**Haoran Li, Chenhan Xiao, Muhao Guo et al.
3847. **[Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution ↗](https://doi.org/10.52202/085713-5797)**Zhanyi Sun, Shuran Song
3848. **[Latent Principle Discovery for Language Model Self-Improvement ↗](https://doi.org/10.52202/085713-5420)**Keshav Ramji, Tahira Naseem, Ramón Fernández Astudillo
3849. **[Latent Refinement via Flow Matching for Training-free Linear Inverse Problem Solving ↗](https://doi.org/10.52202/085713-3606)**Hossein Askari, Yadan Luo, Hongfu Sun et al.
3850. **[Latent Retrieval Augmented Generation of Cross-Domain Protein Binders ↗](https://doi.org/10.52202/085713-2514)**Zishen Zhang, Xiangzhe Kong, Wenbing Huang et al.
3851. **[Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification ↗](https://doi.org/10.52202/085713-4893)**Zinan Lin, Enshu Liu, Xuefei Ning et al.
3852. **[Lattice Boltzmann Model for Learning Real-World Pixel Dynamicity ↗](https://doi.org/10.52202/085713-0173)**Guangze Zheng, Shijie Lin, Haobo Zuo et al.
3853. **[LawShift: Benchmarking Legal Judgment Prediction Under Statute Shifts ↗](https://doi.org/10.52202/085713-4010)**Zhuo Han, Yi Ping Yang, Yi Feng et al.
3854. **[Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation ↗](https://doi.org/10.52202/085713-0235)**Fei Wang, Li Shen, Liang Ding et al.
3855. **[Layer-wise Update Aggregation with Recycling for Communication-Efficient Federated Learning ↗](https://doi.org/10.52202/085713-2888)**Jisoo Kim, Sung‐Min Kang, Sunwoo Lee
3856. **[LayerNavigator: Finding Promising Intervention Layers for Efficient Activation Steering in Large Language Models ↗](https://doi.org/10.52202/085713-3383)**Hao Sun, Huailiang Peng, Qiong Dai et al.
3857. **[Leader360V: A Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment ↗](https://doi.org/10.52202/085713-1606)**Weiming Zhang, Dingwen Xiao, Aobotao DAI et al.
3858. **[LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching ↗](https://doi.org/10.52202/085713-3961)**Zhuo Cao, Xuan Zhao, Lena Krieger et al.
3859. **[Learn and Ensemble Bridge Adapters for Multi-domain Task Incremental Learning ↗](https://doi.org/10.52202/085713-5326)**Ziqi Gu, Chunyan Xu, Wenxuan Fang et al.
3860. **[Learning (Approximately) Equivariant Networks via Constrained Optimization ↗](https://doi.org/10.52202/085713-4832)**Andrei Manolache, Luiz F. O. Chamon, Mathias Niepert
3861. **[Learning 3D Anisotropic Noise Distributions Improves Molecular Force Fields ↗](https://doi.org/10.52202/085713-2091)**Xixian Liu, Rui Jiao, ZHIYUAN LIU et al.
3862. **[Learning Across the Gap: Hybrid Multi-armed Bandits with Heterogeneous Offline and Online Data ↗](https://doi.org/10.52202/085713-0681)**Qijia He, Minghan Wang, Xutong Liu et al.
3863. **[Learning CAD Modeling Sequences via Projection and Part Awareness ↗](https://doi.org/10.52202/085713-3283)**Yang Liu, Daxuan Ren, Yijie Ding et al.
3864. **[Learning Chern Numbers of Multiband Topological Insulators with Gauge Equivariant Neural Networks ↗](https://doi.org/10.52202/085713-4948)**Longde Huang, O.S. Balabanov, Hampus Linander et al.
3865. **[Learning Counterfactual Outcomes Under Rank Preservation ↗](https://doi.org/10.52202/085713-4955)**Peng Wu, Haoxuan Li, Chunyuan Zheng et al.
3866. **[Learning Crossmodal Interaction Patterns via Attributed Bipartite Graphs for Single-Cell Omics ↗](https://doi.org/10.52202/085713-3024)**Xiaotang Wang, Xuanwei Lin, Yun Zhu et al.
3867. **[Learning Differential Pyramid Representation for Tone Mapping ↗](https://doi.org/10.52202/085713-5396)**Qirui Yang, Yinbo Li, Yihao Liu et al.
3868. **[Learning Diffusion Models with Flexible Representation Guidance ↗](https://doi.org/10.52202/085713-4368)**Chenyu Wang, Cai Zhou, Sharut Gupta et al.
3869. **[Learning Dynamics of RNNs in Closed-Loop Environments ↗](https://doi.org/10.52202/085713-3221)**Yoav Ger, Omri Barak
3870. **[Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting ↗](https://doi.org/10.52202/085713-2563)**Yiming Wang, Lucy Chai, Xuan Luo et al.
3871. **[Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning ↗](https://doi.org/10.52202/085713-3267)**Till Freihaut, Luca Viano, Volkan Cevher et al.
3872. **[Learning Expandable and Adaptable Representations for Continual Learning ↗](https://doi.org/10.52202/085713-1758)**Ruilong Yu, Mingyan Liu, Fei Ye et al.
3873. **[Learning Generalizable Shape Completion with SIM(3) Equivariance ↗](https://doi.org/10.52202/085713-0821)**Yuqing Wang, Zhaiyu Chen, Xiao Xiang Zhu
3874. **[Learning Gradient Boosted Decision Trees with Algorithmic Recourse ↗](https://doi.org/10.52202/085713-2569)**Kentaro Kanamori, Ken Kobayashi, Takuya Takagi
3875. **[Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization ↗](https://doi.org/10.52202/085713-2801)**Jian-Ting Guo, Yu‐Cheng Chen, Ping-Chun Hsieh et al.
3876. **[Learning Individual Behavior in Agent-Based Models with Graph Diffusion Networks ↗](https://doi.org/10.52202/085713-1212)**Francesco Cozzi, Marco Pangallo, Alan Perotti et al.
3877. **[Learning Interactive World Model for Object-Centric Reinforcement Learning ↗](https://doi.org/10.52202/085713-3004)**Fan Feng, Phillip Lippe, Sara Magliacane
3878. **[Learning Interestingness in Automated Mathematical Theory Formation ↗](https://doi.org/10.52202/085713-1298)**George Tsoukalas, Rahul Saha, Amitayush Thakur et al.
3879. **[Learning Intractable Multimodal Policies with Reparameterization and Diversity Regularization ↗](https://doi.org/10.52202/085713-5313)**Ziqi Wang, Jiashun Liu, Ling Pan
3880. **[Learning Juntas under Markov Random Fields ↗](https://doi.org/10.52202/085713-3965)**Gautam Chandrasekaran, Adam R. Klivans
3881. **[Learning Latent Variable Models via Jarzynski-adjusted Langevin Algorithm ↗](https://doi.org/10.52202/085713-3563)**James Cuin, Davide Carbone, Ömer Deniz Akyıldız
3882. **[Learning Multi-Source and Robust Representations for Continual Learning ↗](https://doi.org/10.52202/085713-5822)**Fei Ye, yongcheng zhong, Qihe Liu et al.
3883. **[Learning Orthogonal Multi-Index Models: A Fine-Grained Information Exponent Analysis ↗](https://doi.org/10.52202/085713-5528)**Yunwei Ren, Jason D. Lee
3884. **[Learning Parameterized Skills from Demonstrations ↗](https://doi.org/10.52202/085713-1264)**Vedant Gupta, Haotian Fu, Calvin Luo et al.
3885. **[Learning Personalized Ad Impact via Contextual Reinforcement Learning under Delayed Rewards ↗](https://doi.org/10.52202/085713-4713)**Yuwei Cheng, Zifeng Zhao, Haifeng Xu
3886. **[Learning Preferences without Interaction for Cooperative AI: A Hybrid Offline-Online Approach ↗](https://doi.org/10.52202/085713-1333)**Haitong Ma, Haoran Yu, Haobo Fu et al.
3887. **[Learning Provably Improves the Convergence of Gradient Descent ↗](https://doi.org/10.52202/085713-1225)**Qingyu Song, Wei Lin, Hong Xu
3888. **[Learning Reconfigurable Representations for Multimodal Federated Learning with Missing Data ↗](https://doi.org/10.52202/085713-0968)**Duong Nguyen, Nghia Hoang, Thanh Trung Huynh et al.
3889. **[Learning Repetition-Invariant Representations for Polymer Informatics ↗](https://doi.org/10.52202/085713-2957)**Yihan Zhu, Gang Liu, Eric Inae et al.
3890. **[Learning Robust Vision-Language Models from Natural Latent Spaces ↗](https://doi.org/10.52202/085713-5270)**Zhangyun Wang, Ni Ding, Aniket Mahanti
3891. **[Learning Shared Representations from Unpaired Data ↗](https://doi.org/10.52202/085713-1552)**Amitai Yacobi, Nir Ben-Ari, Ronen Talmon et al.
3892. **[Learning Simple Interpolants for Linear Integer Arithmetic ↗](https://doi.org/10.52202/085713-2050)**Minchao Wu, Naoki Kobayashi
3893. **[Learning Source-Free Domain Adaptation for Visible-Infrared Person Re-Identification ↗](https://doi.org/10.52202/085713-0690)**Yongxiang Li, Yanglin Feng, Yuan Sun et al.
3894. **[Learning Sparse Approximate Inverse Preconditioners for Conjugate Gradient Solvers on GPUs ↗](https://doi.org/10.52202/085713-0852)**Zhehao Li, Kangbo Lyu, Yixuan Li et al.
3895. **[Learning Spatial-Aware Manipulation Ordering ↗](https://doi.org/10.52202/085713-5493)**Yuxiang Yan, Zhiyuan Zhou, Xin Gao et al.
3896. **[Learning Stochastic Multiscale Models ↗](https://doi.org/10.52202/085713-1836)**Andrew F. Ilersich, Prasanth B. Nair
3897. **[Learning Task-Agnostic Representations through Multi-Teacher Distillation ↗](https://doi.org/10.52202/085713-3664)**Philippe Formont, Maxime Darrin, Banafsheh Karimian et al.
3898. **[Learning Temporal 3D Semantic Scene Completion via Optical Flow Guidance ↗](https://doi.org/10.52202/085713-0203)**Meng Wang, Fan Wu, Ruihui Li et al.
3899. **[Learning Theory for Kernel Bilevel Optimization ↗](https://doi.org/10.52202/085713-0493)**Fares El Khoury, Edouard Pauwels, Samuel Vaiter et al.
3900. **[Learning Urban Climate Dynamics via Physics-Guided Urban Surface–Atmosphere Interactions ↗](https://doi.org/10.52202/085713-4194)**Jiyang Xia, Fenghua Ling, Zhenhui Jessie Li et al.

[← prev](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/38/) [1](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/) … [30](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/30/) … [38](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/38/) **39** [40](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/40/) … [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/40/)

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