---
title: "NeurIPS 2025 — all accepted papers, page 36 — Elamur Research"
description: "All 5,819 papers of NeurIPS 2025 · page 36 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/36/"
---
[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/36/)

[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 36

# NeurIPS 2025: all accepted papers

5,819 papers · page 36 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/35/) [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/) … [35](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/35/) **36** [37](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/37/) … [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/37/)

3501. **[Gompertz Linear Units: Leveraging Asymmetry for Enhanced Learning Dynamics ↗](https://doi.org/10.52202/085713-2139)**Indrashis Das, Mahmoud Safari, Steven Adriænsen et al.
3502. **[GraSS: Scalable Data Attribution with Gradient Sparsification and Sparse Projection ↗](https://doi.org/10.52202/085713-1464)**Pingbang Hu, Joseph Melkonian, Weijing Tang et al.
3503. **[GradMetaNet: An Equivariant Architecture for Learning on Gradients ↗](https://doi.org/10.52202/085713-5155)**Yoav Gelberg, Yam Eitan, Aviv Navon et al.
3504. **[Gradient Descent as Loss Landscape Navigation: a Normative Framework for Deriving Learning Rules ↗](https://doi.org/10.52202/085713-3993)**John J. Vastola, Samuel J. Gershman, Kanaka Rajan
3505. **[Gradient Multi-Normalization for Efficient LLM Training ↗](https://doi.org/10.52202/085713-1433)**Meyer Scetbon, Chao Ma, Wenbo Gong et al.
3506. **[Gradient-Guided Epsilon Constraint Method for Online Continual Learning ↗](https://doi.org/10.52202/085713-4138)**Song Lai, Changyi Ma, Fei Zhu et al.
3507. **[Gradient-Weight Alignment as a Train-Time Proxy for Generalization in Classification Tasks ↗](https://doi.org/10.52202/085713-1784)**Florian A. Hölzl, Daniel Rueckert, Georgios Kaissis
3508. **[Graph Alignment via Birkhoff Relaxation ↗](https://doi.org/10.52202/085713-1755)**Sushil Varma, Irène Waldspurger, Laurent Massoulié
3509. **[Graph Diffusion that can Insert and Delete ↗](https://doi.org/10.52202/085713-2625)**Matteo Ninniri, Marco Podda, Davide Bacciu
3510. **[Graph Neural Network Based Action Ranking for Planning ↗](https://doi.org/10.52202/085713-5735)**Rajesh Mangannavar, Stefan Lee, Alan Fern et al.
3511. **[Graph Persistence goes Spectral ↗](https://doi.org/10.52202/085713-5365)**Mattie Ji, Amauri Holanda de Souza Junior, Vikas Garg
3512. **[Graph Your Own Prompt ↗](https://doi.org/10.52202/085713-1272)**Xiao Pan Ding, Lei Wang, Piotr Koniusz et al.
3513. **[Graph-Based Attention for Differentiable MaxSAT Solving ↗](https://doi.org/10.52202/085713-4598)**S Moriyama, Katsumi Inoue
3514. **[Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models ↗](https://doi.org/10.52202/085713-2298)**Haoyu Wang, Peihao Wang, Mufei Li et al.
3515. **[Graph-based Symbolic Regression with Invariance and Constraint Encoding ↗](https://doi.org/10.52202/085713-0237)**Ziyu Xiang, Kenna Ashen, Xiaofeng Qian et al.
3516. **[GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining ↗](https://doi.org/10.52202/085713-0253)**Chunyu Wei, HU Wen-ji, Xingjia Hao et al.
3517. **[GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks ↗](https://doi.org/10.52202/085713-5289)**Xingbo Fu, Zhenyu Lei, Zihan Chen et al.
3518. **[Graphs Help Graphs: Multi-Agent Graph Socialized Learning ↗](https://doi.org/10.52202/085713-1985)**Jialu Li, Yu Wang, Pengfei Zhu et al.
3519. **[Graph–Smoothed Bayesian Black-Box Shift Estimator and Its Information Geometry ↗](https://doi.org/10.52202/085713-3785)**Masanari Kimura
3520. **[Grasp2Grasp: Vision-Based Dexterous Grasp Translation via Schrödinger Bridges ↗](https://doi.org/10.52202/085713-0575)**Tao Zhong, Jonah Buchanan, Christine Allen-Blanchette
3521. **[Greed is Good: A Unifying Perspective on Guided Generation ↗](https://doi.org/10.52202/085713-3797)**Zander Blasingame, Chen Liu
3522. **[Greedy Algorithms for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure ↗](https://doi.org/10.52202/085713-4510)**Aleksandrs Slivkins, Yunzong Xu, Shiliang Zuo
3523. **[Greedy Sampling Is Provably Efficient For RLHF ↗](https://doi.org/10.52202/085713-3608)**Di Wu, Chengshuai Shi, Jing Yang et al.
3524. **[Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Data ↗](https://doi.org/10.52202/085713-5372)**Andrew Li, Toryn Q. Klassen, Andrew Wang et al.
3525. **[Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs ↗](https://doi.org/10.52202/085713-3516)**Hao Fang, Changle Zhou, Jiawei Kong et al.
3526. **[Guarantees for Alternating Least Squares in Overparameterized Tensor Decompositions ↗](https://doi.org/10.52202/085713-2614)**Dionysis Arvanitakis, Vaidehi Srinivas, Aravindan Vijayaraghavan
3527. **[GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning ↗](https://doi.org/10.52202/085713-0977)**Yue Liu, Shengfang Zhai, Mingzhe Du et al.
3528. **[GuideFlow3D: Optimization-Guided Rectified Flow For Appearance Transfer ↗](https://doi.org/10.52202/085713-2154)**Sayan Deb Sarkar, Sinisa Stekovic, Vincent Lepetit et al.
3529. **[Guided Diffusion Sampling on Function Spaces with Applications to PDEs ↗](https://doi.org/10.52202/085713-4233)**Jiachen Yao, Abbas Mammadov, Julius Berner et al.
3530. **[G²M: A Generalized Gaussian Mirror Method to Boost Feature Selection Power ↗](https://doi.org/10.52202/085713-2581)**Hongyu Shen, Zhizhen Jane Zhao
3531. **[H-SPLID: HSIC-based Saliency Preserving Latent Information Decomposition ↗](https://doi.org/10.52202/085713-1808)**Lukas Miklautz, Chengzhi Shi, Andrii Shkabrii et al.
3532. **[HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs ↗](https://doi.org/10.52202/085713-3966)**Saleh Ashkboos, Mahdi Nikdan, Rush Tabesh et al.
3533. **[HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance ↗](https://doi.org/10.52202/085713-1768)**JUE GONG, Tingyu Yang, Jingkai Wang et al.
3534. **[HARDMath2: A Benchmark for Applied Mathematics Built by Students as Part of a Graduate Class ↗](https://doi.org/10.52202/085713-0859)**James V. Roggeveen, Erik Wang, David Ettel et al.
3535. **[HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMs ↗](https://doi.org/10.52202/085713-5137)**Ningning Chen, Weicai Ye, Ying Lan Jiang
3536. **[HEIR: Learning Graph-Based Motion Hierarchies ↗](https://doi.org/10.52202/085713-1970)**Cheng Zheng, William Koch, Baiang Li et al.
3537. **[HIDISC: A Hyperbolic Framework for Domain Generalization with Generalized Category Discovery ↗](https://doi.org/10.52202/085713-3322)**Vaibhav Rathore, Divyam Gupta, Biplab Banerjee
3538. **[HMARL-CBF – Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems ↗](https://doi.org/10.52202/085713-2754)**H. M. Sabbir Ahmad, Ehsan Sabouni, Alexander Wasilkoff et al.
3539. **[HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction ↗](https://doi.org/10.52202/085713-5683)**Jikai Wang, Qifan Zhang, Yu-Wei Chao et al.
3540. **[HOComp: Interaction-Aware Human-Object Composition ↗](https://doi.org/10.52202/085713-3263)**Dong Liang, Jinyuan Jia, Yuhao Liu et al.
3541. **[HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models ↗](https://doi.org/10.52202/085713-5694)**Han Hsi Indy Liu, Jiaqi Li, Zhi Xu et al.
3542. **[HYPERION: Fine-Grained Hypersphere Alignment for Robust Federated Graph Learning ↗](https://doi.org/10.52202/085713-2202)**Frank Wan, Xiaoran Shang, Yuxin Wu et al.
3543. **[Hadamard Test is Sufficient for Efficient Quantum Gradient Estimation with Lie Algebraic Symmetries ↗](https://doi.org/10.52202/085713-4198)**Mohsen Heidari, Masih Mozakka, Wojciech Szpankowski A
3544. **[Hadamax Encoding: Elevating Performance in Model-Free Atari ↗](https://doi.org/10.52202/085713-5092)**Jacob E. Kooi, Zhao Yang, Vincent François-Lavet
3545. **[HairFree: Compositional 2D Head Prior for Text-Driven 360° Bald Texture Synthesis ↗](https://doi.org/10.52202/085713-3687)**Mirela Oštrek, Michael J. Black, Justus Thies
3546. **[Hamiltonian Descent Algorithms for Optimization: Accelerated Rates via Randomized Integration Time ↗](https://doi.org/10.52202/085713-3132)**Qiang Fu, Andre Wibisono
3547. **[Hamiltonian Neural PDE Solvers through Functional Approximation ↗](https://doi.org/10.52202/085713-1045)**Anthony Zhou, Amir Barati Farimani
3548. **[Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization ↗](https://doi.org/10.52202/085713-1553)**Kuan Zhang, Chengliang Chai, Jing‐Zhe Xu et al.
3549. **[Handling Missing Responses under Cluster Dependence with Applications to Language Model Evaluation ↗](https://doi.org/10.52202/085713-1890)**Zhenghao Zeng, David T. Arbour, Avi Feller et al.
3550. **[Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access ↗](https://doi.org/10.52202/085713-2974)**Xiang Hu, Jiaqi Leng, Jun Zhao et al.
3551. **[Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning ↗](https://doi.org/10.52202/085713-5819)**Qitao Tan, Jun Liu, Zheng Zhan et al.
3552. **[Harnessing Feature Resonance under Arbitrary Target Alignment for Out-of-Distribution Node Detection ↗](https://doi.org/10.52202/085713-5417)**Shenzhi Yang, Junbo Zhao, Sharon Li et al.
3553. **[Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability ↗](https://doi.org/10.52202/085713-2580)**Jiani Liu, Zhiyuan Wang, Zeliang Zhang et al.
3554. **[Hawaii: Hierarchical Visual Knowledge Transfer for Efficient Vision-Language Models ↗](https://doi.org/10.52202/085713-0034)**Yimu Wang, Mozhgan Nasr Azadani, Sean Sedwards et al.
3555. **[Head Pursuit: Probing Attention Specialization in Multimodal Transformers ↗](https://doi.org/10.52202/085713-3752)**Lorenzo Basile, Valentino Maiorca, Diego Doimo et al.
3556. **[HeavyWater and SimplexWater: Distortion-free LLM Watermarks for Low-Entropy Distributions ↗](https://doi.org/10.52202/085713-3575)**Dor Tsur, Carol Xuan Long, Claudio Mayrink Verdun et al.
3557. **[Hephaestus: Mixture Generative Modeling with Energy Guidance for Large-scale QoS Degradation ↗](https://doi.org/10.52202/085713-2418)**Nguyen Do, Bach Ngo, Youval Kashuv et al.
3558. **[HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations ↗](https://doi.org/10.52202/085713-2162)**Shuaicheng Zhang, Haohui Wang, Junhong Lin et al.
3559. **[Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points ↗](https://doi.org/10.52202/085713-1442)**Naoya Yamamoto, Juno Kim, Taiji Suzuki
3560. **[Heterogeneous Adversarial Play in Interactive Environments ↗](https://doi.org/10.52202/085713-2664)**Manjie Xu, Xinyi Yang, Jiayu Zhan et al.
3561. **[Heterogeneous Graph Transformers for Simultaneous Mobile Multi-Robot Task Allocation and Scheduling under Temporal Constraints ↗](https://doi.org/10.52202/085713-3031)**Batuhan Altundas, Shengkang Chen, Shivika Singh et al.
3562. **[Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems ↗](https://doi.org/10.52202/085713-3813)**Shangbin Feng, Zifeng Wang, Palash Goyal et al.
3563. **[HiMoLE: Towards OOD-Robust LoRA via Hierarchical Mixture of Experts ↗](https://doi.org/10.52202/085713-4763)**Yinuo Jiang, Yan Xiaodong, Keyan Ding et al.
3564. **[HiPoNet: A Multi-View Simplicial Complex Network for High Dimensional Point-Cloud and Single-Cell data ↗](https://doi.org/10.52202/085713-4107)**Siddharth Viswanath, Hiren Madhu, Dhananjay Bhaskar et al.
3565. **[Hierachical Balance Packing: Towards Efficient Supervised Fine-tuning for Long-Context LLM ↗](https://doi.org/10.52202/085713-1517)**Yongqiang Yao, Jingru Tan, Kaihuan Liang et al.
3566. **[Hierarchical Demonstration Order Optimization for Many-shot In-Context Learning ↗](https://doi.org/10.52202/085713-3089)**Yinhan He, Wendy Zheng, Song Wang et al.
3567. **[Hierarchical Implicit Neural Emulators ↗](https://doi.org/10.52202/085713-2471)**Ruoxi Jiang, Xiao Zhang, Karan Jakhar et al.
3568. **[Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory ↗](https://doi.org/10.52202/085713-2921)**Hanru Bai, Weiyang Ding, Difan Zou
3569. **[Hierarchical Optimization via LLM-Guided Objective Evolution for Mobility-on-Demand Systems ↗](https://doi.org/10.52202/085713-5012)**Yi Zhang, Yushen Long, Yun Ni et al.
3570. **[Hierarchical Retrieval: The Geometry and a Pretrain-Finetune Recipe ↗](https://doi.org/10.52202/085713-4993)**Chong You, Rajesh Jayaram, Ananda Theertha Suresh et al.
3571. **[Hierarchical Self-Attention: Generalizing Neural Attention Mechanics to Multi-Scale Problems ↗](https://doi.org/10.52202/085713-0107)**Saeed Amizadeh, Sara Abdali, Yinheng Li et al.
3572. **[Hierarchical Shortest-Path Graph Kernel Network ↗](https://doi.org/10.52202/085713-2031)**Jiaxin Wang, Wenxuan Tu, Jieren Cheng
3573. **[High Dynamic Range Imaging with Time-Encoding Spike Camera ↗](https://doi.org/10.52202/085713-3052)**Zhenkun Zhu, Ruiqin Xiong, Jiyu Xie et al.
3574. **[High Resolution UDF Meshing via Iterative Networks ↗](https://doi.org/10.52202/085713-5692)**Federico Stella, Nicolas Talabot, Hieu Trung Le et al.
3575. **[High-Dimensional Calibration from Swap Regret ↗](https://doi.org/10.52202/085713-1682)**Maxwell Fishelson, Noah Golowich, Mehryar Mohri et al.
3576. **[High-Performance Arithmetic Circuit Optimization via Differentiable Architecture Search ↗](https://doi.org/10.52202/085713-0750)**Xilin Xia, Jie Wang, Wanbo Zhang et al.
3577. **[High-order Equivariant Flow Matching for Density Functional Theory Hamiltonian Prediction ↗](https://doi.org/10.52202/085713-0449)**Seongsu Kim, Nayoung Kim, Dongwoo Kim et al.
3578. **[High-order Interactions Modeling for Interpretable Multi-Agent Q-Learning ↗](https://doi.org/10.52202/085713-5233)**Qiang Xu, Yuanyang Zhu, Xuefei Wu et al.
3579. **[Higher-Order Learning with Graph Neural Networks via Hypergraph Encodings ↗](https://doi.org/10.52202/085713-5782)**Raphaël Pellegrin, Lukas Fesser, Melanie Weber
3580. **[Highlighting What Matters: Promptable Embeddings for Attribute-Focused Image Retrieval ↗](https://doi.org/10.52202/085713-3837)**Siting Li, Xiang Gao, Simon S. Du
3581. **[Hippocampal-like Sequential Editing for Continual Knowledge Updates in Large Language Models ↗](https://doi.org/10.52202/085713-0305)**Quntian Fang, Zhen Huang, Zhiliang Tian et al.
3582. **[HoT-VI: Reparameterizable Variational Inference for Capturing Instance-Level High-Order Correlations ↗](https://doi.org/10.52202/085713-1262)**Junxi Xiao, Qinliang Su, Zexin Yuan
3583. **[Hogwild! Inference: Parallel LLM Generation via Concurrent Attention ↗](https://doi.org/10.52202/085713-1551)**Gleb Rodionov, Roman Garipov, Alina Shutova et al.
3584. **[Holistic Order Prediction in Natural Scenes ↗](https://doi.org/10.52202/085713-0480)**Pierre Musacchio, Hyun-Min Lee, Jaesik Park
3585. **[HollowFlow: Efficient Sample Likelihood Evaluation using Hollow Message Passing ↗](https://doi.org/10.52202/085713-1190)**Johann Flemming Gloy, Simon Olsson
3586. **[Homogeneous Algorithms Can Reduce Competition in Personalized Pricing ↗](https://doi.org/10.52202/085713-3365)**Nathanael Jo, Ashia Wilson, Kathleen Creel et al.
3587. **[Homogeneous Keys, Heterogeneous Values: Exploiting Local KV Cache Asymmetry for Long-Context LLMs ↗](https://doi.org/10.52202/085713-2726)**Wanyun Cui, Mingwei Xu
3588. **[Horizon Reduction Makes RL Scalable ↗](https://doi.org/10.52202/085713-0284)**Seohong Park, Kevin Frans, Deepinder Mann et al.
3589. **[HouseLayout3D: A Benchmark and Training-free Baseline for 3D Layout Estimation in the Wild ↗](https://doi.org/10.52202/085713-4677)**Valentin Bieri, Marie‐Julie Rakotosaona, Keisuke Tateno et al.
3590. **[How Benchmark Prediction from Fewer Data Misses the Mark ↗](https://doi.org/10.52202/085713-4528)**Guanhua Zhang, Florian E. Dorner, Moritz Hardt
3591. **[How Classifier Features Transfer to Downstream: An Asymptotic Analysis in a Two-Layer Model ↗](https://doi.org/10.52202/085713-0129)**Hee Bin Yoo, Sungyoon Lee, Cheongjae Jang et al.
3592. **[How Data Mixing Shapes In-Context Learning: Asymptotic Equivalence for Transformers with MLPs ↗](https://doi.org/10.52202/085713-3984)**Samet Demir, Zafer Doğan
3593. **[How Different from the Past? Spatio-Temporal Time Series Forecasting with Self-Supervised Deviation Learning ↗](https://doi.org/10.52202/085713-4905)**Haotian Gao, Zheng Dong, Jiawei Yong et al.
3594. **[How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime? ↗](https://doi.org/10.52202/085713-5816)**Wei Huang, Andi Han, Yujin Song et al.
3595. **[How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities Degradation ↗](https://doi.org/10.52202/085713-1425)**Xin Biao Lu, Yanyan Zhao, Si Wei et al.
3596. **[How Does Topology Bias Distort Message Passing in Graph Recommender? A Dirichlet Energy Perspective ↗](https://doi.org/10.52202/085713-1513)**Yanbiao Ji, Yue Ding, Dan Luo et al.
3597. **[How Ensembles of Distilled Policies Improve Generalisation in Reinforcement Learning ↗](https://doi.org/10.52202/085713-4537)**Max Weltevrede, Moritz A. Zanger, Matthijs T. J. Spaan et al.
3598. **[How Far Are We from Optimal Reasoning Efficiency? ↗](https://doi.org/10.52202/085713-0365)**Jiaxuan Gao, Shu Yan, Qixin Tan et al.
3599. **[How Many Domains Suffice for Domain Generalization? A Tight Characterization via the Domain Shattering Dimension ↗](https://doi.org/10.52202/085713-3835)**Cynthia Dwork, Lunjia Hu, Han Shao
3600. **[How Memory in Optimization Algorithms Implicitly Modifies the Loss ↗](https://doi.org/10.52202/085713-5215)**Matias D. Cattaneo, Boris Shigida

[← prev](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/35/) [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/) … [35](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/35/) **36** [37](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/37/) … [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/37/)

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