---
title: "NeurIPS 2025 — all accepted papers, page 48 — Elamur Research"
description: "All 5,819 papers of NeurIPS 2025 · page 48 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/48/"
---
[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/48/)

[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 48

# NeurIPS 2025: all accepted papers

5,819 papers · page 48 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/47/) [1](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/) … [40](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/40/) … [47](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/47/) **48** [49](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/49/) [50](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/50/) … [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/49/)

4701. **[Quantifying Distributional Invariance in Causal Subgraph for IRM-Free Graph Generalization ↗](https://doi.org/10.52202/085713-2452)**Yang Qiu, Yixiong Zou, Jun Wang et al.
4702. **[Quantifying Elicitation of Latent Capabilities in Language Models ↗](https://doi.org/10.52202/085713-5029)**Elizabeth Donoway, Hailey Joren, Arushi Somani et al.
4703. **[Quantifying Generalisation in Imitation Learning ↗](https://doi.org/10.52202/085713-5106)**Nathan Gavenski, Odinaldo Rodrigues
4704. **[Quantifying Statistical Significance of Deep Nearest Neighbor Anomaly Detection via Selective Inference ↗](https://doi.org/10.52202/085713-5762)**Mizuki Niihori, Shuichi Nishino, Teruyuki Katsuoka et al.
4705. **[Quantifying Task-relevant Similarities in Representations Using Decision Variable Correlations ↗](https://doi.org/10.52202/085713-5008)**Yu (Eric) Qian, Wilson S. Geisler, Xue-Xin Wei
4706. **[Quantifying Uncertainty in the Presence of Distribution Shifts ↗](https://doi.org/10.52202/085713-3237)**Yuli Slavutsky, David M. Blei
4707. **[Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions ↗](https://doi.org/10.52202/085713-3434)**Simon Matrenok, Skander Moalla, Çağlar Gülçehre
4708. **[Quantitative convergence of trained neural networks to Gaussian processes ↗](https://doi.org/10.52202/085713-5492)**Andréa Agazzi, Eloy Mósig García, Dario Trevisan
4709. **[Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization ↗](https://doi.org/10.52202/085713-5080)**Yamato Arai, Yuma Ichikawa
4710. **[Quantization-Free Autoregressive Action Transformer ↗](https://doi.org/10.52202/085713-2712)**Ziyad Sheebaelhamd, Michael Tschannen, Michael Muehlebach et al.
4711. **[Quantum Speedups for Minimax Optimization and Beyond ↗](https://doi.org/10.52202/085713-3974)**Chengchang Liu, Zongqi Wan, John C. S. Lui
4712. **[Quantum Visual Fields with Neural Amplitude Encoding ↗](https://doi.org/10.52202/085713-5297)**Shuteng Wang, Christian Theobalt, Vladislav Golyanik
4713. **[Quantum speedup of non-linear Monte Carlo problems ↗](https://doi.org/10.52202/085713-0631)**José Blanchet, Yassine Hamoudi, Márió Szegedy et al.
4714. **[Quartet: Native FP4 Training Can Be Optimal for Large Language Models ↗](https://doi.org/10.52202/085713-1449)**Roberto L. Castro, Andrei Panferov, Soroush Tabesh et al.
4715. **[Quasi-Self-Concordant Optimization with ∞ Lewis Weights ↗](https://doi.org/10.52202/085713-4002)**Alina Ene, Ta Duy Nguyen, Adrian Vladu
4716. **[Query-Efficient Locally Private Hypothesis Selection via the Scheffe Graph ↗](https://doi.org/10.52202/085713-2845)**Gautam Kamath, Alireza F. Pour, Matthew Regehr et al.
4717. **[QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks? ↗](https://doi.org/10.52202/085713-4503)**Belinda Li, Been Kim, Zi Wang
4718. **[R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing ↗](https://doi.org/10.52202/085713-4135)**Tianyu Fu, Yi Ge, Yichen You et al.
4719. **[RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis ↗](https://doi.org/10.52202/085713-4109)**Haolin Li, Tianjie Dai, Zhe Chen et al.
4720. **[RADAR: Benchmarking Language Models on Imperfect Tabular Data ↗](https://doi.org/10.52202/085713-3699)**Ken Gu, Z.H. Zhang, Kate Lin et al.
4721. **[RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models ↗](https://doi.org/10.52202/085713-0532)**Jiarui Zhang, Xiangyu Liu, Yong Sheng Hu et al.
4722. **[RAM-W600: A Multi-Task Wrist Dataset and Benchmark for Rheumatoid Arthritis ↗](https://doi.org/10.52202/085713-3375)**YANG SONGXIAO, Haolin Wang, Yao Fu et al.
4723. **[RANK++LETR: Learn to Rank and Optimize Candidates for Line Segment Detection ↗](https://doi.org/10.52202/085713-1393)**Xin Tong, Baojie Tian, Yufei Guo et al.
4724. **[RAPTR: Radar-based 3D Pose Estimation using Transformer ↗](https://doi.org/10.52202/085713-5727)**Sorachi Kato, Ryoma Yataka, Pu Perry Wang et al.
4725. **[RAT: Bridging RNN Efficiency and Attention Accuracy via Chunk-based Sequence Modeling ↗](https://doi.org/10.52202/085713-1165)**Xiuying Wei, Anunay Yadav, Razvan Pascanu et al.
4726. **[RDB2G-Bench: A Comprehensive Benchmark for Automatic Graph Modeling of Relational Databases ↗](https://doi.org/10.52202/085713-4078)**Dongwon Choi, Sunwoo Kim, Ju‐Yeon Kim et al.
4727. **[RDD: Retrieval-Based Demonstration Decomposer for Planner Alignment in Long-Horizon Tasks ↗](https://doi.org/10.52202/085713-1578)**Mingxuan Yan, Yuping Wang, Zechun Liu et al.
4728. **[REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving ↗](https://doi.org/10.52202/085713-3565)**Annabelle Sujun Tang, Christopher Priebe, Rohan Mahapatra et al.
4729. **[REDOUBT: Duo Safety Validation for Autonomous Vehicle Motion Planning ↗](https://doi.org/10.52202/085713-1210)**Shuguang Wang, Qian Zhou, Kui Wu et al.
4730. **[REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing ↗](https://doi.org/10.52202/085713-1619)**Weihan Xu, Yimeng Ma, Jingyue Huang et al.
4731. **[REINFORCE Converges to Optimal Policies with Any Learning Rate ↗](https://doi.org/10.52202/085713-0541)**Samuel Robertson, Thang Chu, Bo Dai et al.
4732. **[REMI: Reconstructing Episodic Memory During Internally Driven Path Planning ↗](https://doi.org/10.52202/085713-2668)**Zhaoze Wang, Genela Morris, Dori Derdikman et al.
4733. **[RESPIN-S1.0: A read speech corpus of 10000+ hours in dialects of nine Indian Languages ↗](https://doi.org/10.52202/085713-4928)**Saurabh Kumar, Abhayjeet Singh, G Deekshitha et al.
4734. **[RETRO SYNFLOW: Discrete Flow-Matching for Accurate and Diverse Single-Step Retrosynthesis ↗](https://doi.org/10.52202/085713-1846)**Robin Yadav, Qi Yan, Guy Wolf et al.
4735. **[RF-Agent: Automated Reward Function Design via Language Agent Tree Search ↗](https://doi.org/10.52202/085713-5742)**Ning Gao, Xiuhui Zhang, Xingyu Jiang et al.
4736. **[RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes ↗](https://doi.org/10.52202/085713-1949)**Fang Li, Hao Zhang, Narendra Ahuja
4737. **[RGNMR: A Gauss-Newton method for robust matrix completion with theoretical guarantees ↗](https://doi.org/10.52202/085713-2011)**Eilon Vaknin, Boaz Nadler
4738. **[RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility ↗](https://doi.org/10.52202/085713-2838)**Haoyu He, Haozheng Luo, Yan Chen et al.
4739. **[RLZero: Direct Policy Inference from Language Without In-Domain Supervision ↗](https://doi.org/10.52202/085713-2794)**Harshit Sikchi, Siddhant Agarwal, Pranaya Jajoo et al.
4740. **[RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative Models ↗](https://doi.org/10.52202/085713-0869)**Yiqi Tian, Pengfei Jin, Mingze Yuan et al.
4741. **[ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridge ↗](https://doi.org/10.52202/085713-3299)**Manh Cuong Dao, The Hung Tran, Phi Le Nguyen et al.
4742. **[ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks ↗](https://doi.org/10.52202/085713-4699)**Philip Schroeder, Ondřej Bíža, Thomas Weng et al.
4743. **[RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models ↗](https://doi.org/10.52202/085713-0054)**Zukang Xu, Xing Hu, Qiang Wu et al.
4744. **[RSafe: Incentivizing proactive reasoning to build robust and adaptive LLM safeguards ↗](https://doi.org/10.52202/085713-0960)**jingnan zheng, Xiangtian Ji, Yijun Lu et al.
4745. **[RUAGO: Effective and Practical Retain-Free Unlearning via Adversarial Attack and OOD Generator ↗](https://doi.org/10.52202/085713-4855)**SangYong Lee, Sangjun Chung, Simon Woo
4746. **[RULE: Reinforcement UnLEarning Achieves Forget-retain Pareto Optimality ↗](https://doi.org/10.52202/085713-1315)**Chenlong Zhang, Zhuoran Jin, Hong Yuan et al.
4747. **[RadarQA: Multi-modal Quality Analysis of Weather Radar Forecasts ↗](https://doi.org/10.52202/085713-4385)**Xuming He, Zhiyuan You, Junchao Gong et al.
4748. **[Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Observation Delays ↗](https://doi.org/10.52202/085713-2074)**Songchen Fu, Siang Chen, Shaojing Zhao et al.
4749. **[Random Forest Autoencoders for Guided Representation Learning ↗](https://doi.org/10.52202/085713-3204)**Adrien Aumon, Shuang Ni, Myriam Lizotte et al.
4750. **[Random Search Neural Networks for Efficient and Expressive Graph Learning ↗](https://doi.org/10.52202/085713-0348)**Michael Ito, Danai Koutra, Jenna Wiens
4751. **[Randomized-MLP Regularization Improves Domain Adaptation and Interpretability in DINOv2 ↗](https://doi.org/10.52202/085713-0027)**Joel Valdivia Ortega, Lorenz Lamm, Franziska Eckardt et al.
4752. **[RankSEG-RMA: An Efficient Segmentation Algorithm via Reciprocal Moment Approximation ↗](https://doi.org/10.52202/085713-5452)**Zixun Wang, Ben Dai
4753. **[Ranking-based Preference Optimization for Diffusion Models from Implicit User Feedback ↗](https://doi.org/10.52202/085713-1996)**Yi-Lun Wu, Bo-Kai Ruan, Chiang Tseng et al.
4754. **[Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusion ↗](https://doi.org/10.52202/085713-1586)**Vinh Tong, Trung Dung Hoang, Anji Liu et al.
4755. **[Rao-Blackwellised Reparameterisation Gradients ↗](https://doi.org/10.52202/085713-3399)**Kevin H. Lam, Thang D. Bui, George Deligiannidis et al.
4756. **[Rationalized All-Atom Protein Design with Unified Multi-Modal Bayesian Flow ↗](https://doi.org/10.52202/085713-0105)**Hanlin Wu, Yuxuan Song, Zhe Zhang et al.
4757. **[RayFusion: Ray Fusion Enhanced Collaborative Visual Perception ↗](https://doi.org/10.52202/085713-3090)**Shaohong Wang, Lu Bin, Xinyu Xiao et al.
4758. **[Re-coding for Uncertainties: Edge-awareness Semantic Concordance for Resilient Event-RGB Segmentation ↗](https://doi.org/10.52202/085713-3390)**Nan Bao, Yifan Zhao, Lin Zhu et al.
4759. **[ReCAP: Recursive Context-Aware Reasoning and Planning for Large Language Model Agents ↗](https://doi.org/10.52202/085713-3181)**Zhenyu Zhang, Tianyi Chen, Weiran Xu et al.
4760. **[ReCon: Region-Controllable Data Augmentation with Rectification and Alignment for Object Detection ↗](https://doi.org/10.52202/085713-2515)**Haowei Zhu, Tianxiang Pan, Rui Qin et al.
4761. **[ReDit: Reward Dithering for Improved LLM Policy Optimization ↗](https://doi.org/10.52202/085713-2055)**Chenxing Wei, Jiarui Yu, Ying He et al.
4762. **[ReMindRAG: Low-Cost LLM-Guided Knowledge Graph Traversal for Efficient RAG ↗](https://doi.org/10.52202/085713-1793)**Yongli Hu, Zhu Jifeng, Lanrui Tang et al.
4763. **[RePO: Understanding Preference Learning Through ReLU-Based Optimization ↗](https://doi.org/10.52202/085713-1390)**Junkang Wu, Kexin Huang, xue wang et al.
4764. **[Reaction Prediction via Interaction Modeling of Symmetric Difference Shingle Sets ↗](https://doi.org/10.52202/085713-4094)**Runhan Shi, Letian Chen, Gufeng Yu et al.
4765. **[Real-DRL: Teach and Learn at Runtime ↗](https://doi.org/10.52202/085713-5276)**Yanbing Mao, Yihao Cai, Lui Sha
4766. **[Real-World Reinforcement Learning of Active Perception Behaviors ↗](https://doi.org/10.52202/085713-3910)**Edward S. Hu, Jie Wang, Xingfang Yuan et al.
4767. **[Reasoning Is Not a Race: When Stopping Early Beats Going Deeper ↗](https://doi.org/10.52202/085713-3639)**Mohan Zhang, Jiaxuan Gao, Shusheng Xu et al.
4768. **[Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models ↗](https://doi.org/10.52202/085713-5052)**Junyi Li, Hwee Tou Ng
4769. **[Reasoning Models Sometimes Output Illegible Chains of Thought ↗](https://doi.org/10.52202/085713-3688)**Arun Jose
4770. **[Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning ↗](https://doi.org/10.52202/085713-4668)**Jiwon Song, Dongwon Jo, Yulhwa Kim et al.
4771. **[Reasoning Planning for Language Models ↗](https://doi.org/10.52202/085713-4059)**Ngoc Bao Nguyen, Trung Hieu Nguyen, Ruifeng She et al.
4772. **[Reasoning as an Adaptive Defense for Safety ↗](https://doi.org/10.52202/085713-2585)**Taeyoun Kim, Fahim Tajwar, Aditi Raghunathan et al.
4773. **[Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought ↗](https://doi.org/10.52202/085713-2670)**Hanlin Zhu, Shibo Hao, Zhiting Hu et al.
4774. **[Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity Modeling ↗](https://doi.org/10.52202/085713-5290)**Yihong Dong, Ge Li, Xue Jiang et al.
4775. **[Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval ↗](https://doi.org/10.52202/085713-0104)**Jian Xiao, Zijie Song, Jialong Hu et al.
4776. **[Rebalancing Return Coverage for Conditional Sequence Modeling in Offline Reinforcement Learning ↗](https://doi.org/10.52202/085713-4956)**Wensong Bai, Chufan Chen, Yichao Fu et al.
4777. **[Reconciling Geospatial Prediction and Retrieval via Sparse Representations ↗](https://doi.org/10.52202/085713-4256)**YI LI, CHEN YUANLONG, Weiming Huang et al.
4778. **[Reconstructing Heterogeneous Biomolecules via Hierarchical Gaussian Mixtures and Part Discovery ↗](https://doi.org/10.52202/085713-2538)**Shayan Shekarforoush, David B. Lindell, Marcus A. Brubaker et al.
4779. **[Reconstruction and Secrecy under Approximate Distance Queries ↗](https://doi.org/10.52202/085713-2216)**Shay Moran, E.V. Nesterova
4780. **[Rectified CFG++ for Flow Based Models ↗](https://doi.org/10.52202/085713-4985)**Shreshth Saini, Shashank Gupta, Alan Conrad Bovik
4781. **[Rectifying Shortcut Behaviors in Preference-based Reward Learning ↗](https://doi.org/10.52202/085713-2168)**Wenqian Ye, Guangtao Zheng, Aidong Zhang
4782. **[Rectifying Soft-Label Entangled Bias in Long-Tailed Dataset Distillation ↗](https://doi.org/10.52202/085713-4428)**Chenyang Jiang, Hang Zhao, Xinyu Zhang et al.
4783. **[Recurrent Memory for Online Interdomain Gaussian Processes ↗](https://doi.org/10.52202/085713-4499)**Wenlong Chen, Naoki Kiyohara, Harrison Zhu et al.
4784. **[Recurrent Self-Attention Dynamics: An Energy-Agnostic Perspective from Jacobians ↗](https://doi.org/10.52202/085713-4675)**Akiyoshi Tomihari, Ryo Karakida
4785. **[Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems ↗](https://doi.org/10.52202/085713-3636)**Ibrahim Alabdulmohsin, Xiaohua Zhai
4786. **[Recursive Transformer: Boosting Reasoning Ability with State Stack ↗](https://doi.org/10.52202/085713-3078)**Kechi Zhang, Ge Li, Huangzhao Zhang et al.
4787. **[Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling ↗](https://doi.org/10.52202/085713-5039)**Yu Cao, Yibo Miao, Xiao-Shan Gao et al.
4788. **[Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigation ↗](https://doi.org/10.52202/085713-4656)**Zuhair Hasan Shaik, Abdullah Mazhar, Aseem Srivastava et al.
4789. **[Reducing the Probability of Undesirable Outputs in Language Models Using Probabilistic Inference ↗](https://doi.org/10.52202/085713-4530)**Stephen Zhao, Aidan Li, Rob Brekelmans et al.
4790. **[Reduction-based Pseudo-label Generation for Instance-dependent Partial Label Learning ↗](https://doi.org/10.52202/085713-0441)**Congyu Qiao, Ning Xu, Yihao Hu et al.
4791. **[RefLoRA: Refactored Low-Rank Adaptation for Efficient Fine-Tuning of Large Models ↗](https://doi.org/10.52202/085713-3106)**Yilang Zhang, Bingcong Li, Georgios B. Giannakis
4792. **[Refinement Methods for Distributed Distribution Estimation under p-Losses ↗](https://doi.org/10.52202/085713-2042)**Deheng Yuan, Tao Guo, Zhongyi Huang
4793. **[Refining Norms: A Post-hoc Framework for OOD Detection in Graph Neural Networks ↗](https://doi.org/10.52202/085713-1360)**Jiawei Gu, Ziyue Qiao, Zechao Li
4794. **[Reframing Gaussian Splatting Densification with Complexity-Density Consistency of Primitives ↗](https://doi.org/10.52202/085713-4243)**Zhemeng Dong, Junjun Jiang, Youyu Chen et al.
4795. **[Regional Explanations: Bridging Local and Global Variable Importance ↗](https://doi.org/10.52202/085713-5070)**Salim I. Amoukou, Nicolas Brunel
4796. **[Registration is a Powerful Rotation-Invariance Learner for 3D Anomaly Detection ↗](https://doi.org/10.52202/085713-0180)**Yuyang Yu, Zhengwei Chen, Xuemiao Xu et al.
4797. **[Regression Trees Know Calculus ↗](https://doi.org/10.52202/085713-0790)**Nathan Wycoff
4798. **[Regret Analysis of Average-Reward Unichain MDPs via an Actor-Critic Approach ↗](https://doi.org/10.52202/085713-2221)**Swetha Ganesh, Vaneet Aggarwal
4799. **[Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback ↗](https://doi.org/10.52202/085713-1063)**Orin Levy, Liad Erez, Alon Cohen et al.
4800. **[Regret Lower Bounds for Decentralized Multi-Agent Stochastic Shortest Path Problems ↗](https://doi.org/10.52202/085713-5786)**Utkarsh U. Chavan, Prashant Trivedi, N. Hemachandra

[← prev](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/47/) [1](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/) … [40](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/40/) … [47](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/47/) **48** [49](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/49/) [50](https://md.research.elamur.ai/free/en/venues/neural-information-processing-systems/2025/papers/page/50/) … [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/49/)

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