NeurIPS 2025 Papers

5,858 papers found • Page 116 of 118

What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers

Pulkit Gopalani, Wei Hu

NeurIPS 2025posterarXiv:2506.13688
1
citations

What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions

Sang Choe, Hwijeen Ahn, Juhan Bae et al.

NeurIPS 2025poster

What Makes a Reward Model a Good Teacher? An Optimization Perspective

Noam Razin, Zixuan Wang, Hubert Strauss et al.

NeurIPS 2025spotlight

WHAT MAKES MATH PROBLEMS HARD FOR REINFORCEMENT LEARNING: A CASE STUDY

Ali Shehper, Anibal Medina-Mardones, Lucas Fagan et al.

NeurIPS 2025poster
7
citations

What Matters in Data for DPO?

Yu Pan, Zhongze Cai, Huaiyang Zhong et al.

NeurIPS 2025poster
5
citations

What Moves the Eyes: Doubling Mechanistic Model Performance Using Deep Networks to Discover and Test Cognitive Hypotheses

Federico D'Agostino, Lisa Schwetlick, Matthias Bethge et al.

NeurIPS 2025oral

What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains

Chanakya Ekbote, Ashok Vardhan Makkuva, Marco Bondaschi et al.

NeurIPS 2025spotlightarXiv:2508.07208

What Really is a Member? Discrediting Membership Inference via Poisoning

Neal Mangaokar, Ashish Hooda, Zhuohang Li et al.

NeurIPS 2025poster

What’s in Common? Multimodal Models Hallucinate When Reasoning Across Scenes

Candace Ross, Florian Bordes, Adina Williams et al.

NeurIPS 2025poster

What's Producible May Not Be Reachable: Measuring the Steerability of Generative Models

Keyon Vafa, Sarah Bentley, Jon Kleinberg et al.

NeurIPS 2025poster
2
citations

What We Miss Matters: Learning from the Overlooked in Point Cloud Transformers

Yi Wang, Jiaze Wang, Ziyu Guo et al.

NeurIPS 2025poster

When Additive Noise Meets Unobserved Mediators: Bivariate Denoising Diffusion for Causal Discovery

Dominik Meier, Sujai Hiremath, PROMIT GHOSAL et al.

NeurIPS 2025poster

When and how can inexact generative models still sample from the data manifold?

Nisha Chandramoorthy, Adriaan de Clercq

NeurIPS 2025posterarXiv:2508.07581

When Are Concepts Erased From Diffusion Models?

Kevin Lu, Nicky Kriplani, Rohit Gandikota et al.

NeurIPS 2025poster
5
citations

When Can Model-Free Reinforcement Learning be Enough for Thinking?

Josiah Hanna, Nicholas Corrado

NeurIPS 2025poster

When Causal Dynamics Matter: Adapting Causal Strategies through Meta-Aware Interventions

Moritz Willig, Tim Woydt, Devendra Singh Dhami et al.

NeurIPS 2025poster

When Data Can't Meet: Estimating Correlation Across Privacy Barriers

Abhinav Chakraborty, Arnab Auddy, T. Tony Cai

NeurIPS 2025spotlight

When Does Closeness in Distribution Imply Representational Similarity? An Identifiability Perspective

Beatrix Nielsen, Emanuele Marconato, Andrea Dittadi et al.

NeurIPS 2025poster

When Does Curriculum Learning Help? A Theoretical Perspective

Raman Arora, Yunjuan Wang, Kaibo Zhang

NeurIPS 2025poster

When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective

Alireza Mousavi-Hosseini, Clayton Sanford, Denny Wu et al.

NeurIPS 2025poster

When Kernels Multiply, Clusters Unify: Fusing Embeddings with the Kronecker Product

Youqi WU, Jingwei Zhang, Farzan Farnia

NeurIPS 2025poster

When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners

Weixiang Zhao, Jiahe Guo, Yang Deng et al.

NeurIPS 2025spotlight

When Lower-Order Terms Dominate: Adaptive Expert Algorithms for Heavy-Tailed Losses

Antoine Moulin, Emmanuel Esposito, Dirk van der Hoeven

NeurIPS 2025poster

When majority rules, minority loses: bias amplification of gradient descent

François Bachoc, Jerome Bolte, Ryan Boustany et al.

NeurIPS 2025poster
1
citations

When Models Don’t Collapse: On the Consistency of Iterative MLE

Daniel Barzilai, Ohad Shamir

NeurIPS 2025poster

When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration

Quan Shi, Carlos Jimenez, Shunyu Yao et al.

NeurIPS 2025oral
2
citations

When No Paths Lead to Rome: Benchmarking Systematic Neural Relational Reasoning

Anirban Das, Muhammad Irtaza Khalid, Rafael Peñaloza et al.

NeurIPS 2025poster

When One Moment Isn't Enough: Multi-Moment Retrieval with Cross-Moment Interactions

Zhuo Cao, Heming Du, Bingqing Zhang et al.

NeurIPS 2025oralarXiv:2510.17218

When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding

Yan Shu, Hangui Lin, Yexin Liu et al.

NeurIPS 2025poster

When Thinking Drifts: Evidential Grounding for Robust Video Reasoning

Romy Luo, Zihui (Sherry) Xue, Alex Dimakis et al.

NeurIPS 2025poster
4
citations

When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs

Xiaomin Li, Zhou Yu, Zhiwei Zhang et al.

NeurIPS 2025spotlight

When Worse is Better: Navigating the Compression Generation Trade-off In Visual Tokenization

Vivek Ramanujan, Kushal Tirumala, Armen Aghajanyan et al.

NeurIPS 2025spotlight

Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models

Donghoon Ahn, Jiwon Kang, Sanghyun Lee et al.

NeurIPS 2025poster
1
citations

Where Does It Exist from the Low-Altitude: Spatial Aerial Video Grounding

Yang Zhan, Yuan Yuan

NeurIPS 2025oral

Where Graph Meets Heterogeneity: Multi-View Collaborative Graph Experts

Zhihao Wu, Jinyu Cai, Yunhe Zhang et al.

NeurIPS 2025poster

Which Algorithms Have Tight Generalization Bounds?

Michael Gastpar, Ido Nachum, Jonathan Shafer et al.

NeurIPS 2025spotlightarXiv:2410.01969

Which Data Attributes Stimulate Math and Code Reasoning? An Investigation via Influence Functions

Siqi Kou, Qingyuan Tian, Hanwen Xu et al.

NeurIPS 2025poster

Whitened Score Diffusion: A Structured Prior for Imaging Inverse Problems

Jeffrey Alido, Tongyu Li, Yu Sun et al.

NeurIPS 2025poster
1
citations

Whole-Body Conditioned Egocentric Video Prediction

Yutong Bai, Danny Tran, Amir Bar et al.

NeurIPS 2025poster

Who Reasons in the Large Language Models?

Jie Shao, Jianxin Wu

NeurIPS 2025poster

Whose Instructions Count? Resolving Preference Bias in Instruction Fine-Tuning

Jiayu Zhang, Changbang Li, Yinan Peng et al.

NeurIPS 2025poster

Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models

Charvi Rastogi, Tian Huey Teh, Pushkar Mishra et al.

NeurIPS 2025spotlightarXiv:2507.13383
3
citations

Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers

Xin Zhao, Xiaojun Chen, Bingshan Liu et al.

NeurIPS 2025poster

Who You Are Matters: Bridging Interests and Social Roles via LLM-Enhanced Logic Recommendation

Qing Yu, Xiaobei Wang, Shuchang Liu et al.

NeurIPS 2025oral

Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering

Yangfu Li, Hongjian Zhan, Tianyi Chen et al.

NeurIPS 2025poster
1
citations

Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations

Yiyou Sun, Yu Gai, Lijie Chen et al.

NeurIPS 2025poster
10
citations

Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization in Training

Tony Bonnaire, Raphaël Urfin, Giulio Biroli et al.

NeurIPS 2025oral

Why Do Multi-Agent LLM Systems Fail?

Mert Cemri, Melissa Z Pan, Shuyi Yang et al.

NeurIPS 2025spotlightarXiv:2503.13657
188
citations

Why Do Some Language Models Fake Alignment While Others Don't?

Abhay Sheshadri, John Hughes, Julian Michael et al.

NeurIPS 2025spotlight

Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation

Sungmin Cha, Kyunghyun Cho

NeurIPS 2025poster