Research

Papers

Research papers from arXiv and related sources

Total: 4694 AI/LLM: 2583 Testing: 2111
TESTING

LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

Feedforward geometric foundation models achieve strong short-window reconstruction, yet scaling them to minutes-long videos is bottlenecked by quadratic attention complexity or limited effective me...

Junyi Zhang, Charles Herrmann, Junhwa Hur, Chen Sun, Ming-Hsuan Yang, Forrester Cole, Trevor Darr...

2603.03269 2026-03-03
TESTING

A More Rigorous Test Problem For Viscous Hydrodynamics Codes

We advocate for a more stringent test problem for codes that aim to solve the equations of viscous hydrodynamics. Specifically, we discuss a nonuniform-density version of the common (uniform-densit...

Alexander J. Dittmann, Geoffrey Ryan

2603.03266 2026-03-03
TESTING

House Price Effects of Commercial Entry: Event Study Evidence from London

Restaurants, cafes, and other commercial amenities are among the most visible markers of neighborhood change, yet whether their arrival drives house price appreciation or merely follows rising dema...

Wanqi Liu, Rong Zhao

2603.03260 2026-03-03
AI LLM

Inherited Goal Drift: Contextual Pressure Can Undermine Agentic Goals

The accelerating adoption of language models (LMs) as agents for deployment in long-context tasks motivates a thorough understanding of goal drift: agents' tendency to deviate from an original obje...

Achyutha Menon, Magnus Saebo, Tyler Crosse, Spencer Gibson, Eyon Jang, Diogo Cruz

2603.03258 2026-03-03
AI LLM

Valet: A Standardized Testbed of Traditional Imperfect-Information Card Games

AI algorithms for imperfect-information games are typically compared using performance metrics on individual games, making it difficult to assess robustness across game choices. Card games are a na...

Mark Goadrich, Achille Morenville, Éric Piette

2603.03252 2026-03-03
TESTING

Speculative Speculative Decoding

Autoregressive decoding is bottlenecked by its sequential nature. Speculative decoding has become a standard way to accelerate inference by using a fast draft model to predict upcoming tokens from ...

Tanishq Kumar, Tri Dao, Avner May

2603.03251 2026-03-03
AI LLM

Using Learning Progressions to Guide AI Feedback for Science Learning

Generative artificial intelligence (AI) offers scalable support for formative feedback, yet most AI-generated feedback relies on task-specific rubrics authored by domain experts. While effective, r...

Xin Xia, Nejla Yuruk, Yun Wang, Xiaoming Zhai

2603.03249 2026-03-03
AI LLM

Density-Guided Response Optimization: Community-Grounded Alignment via Implicit Acceptance Signals

Language models deployed in online communities must adapt to norms that vary across social, cultural, and domain-specific contexts. Prior alignment approaches rely on explicit preference supervisio...

Patrick Gerard, Svitlana Volkova

2603.03242 2026-03-03
AI LLM

Conversational Learning Diagnosis via Reasoning Multi-Turn Interactive Learning

Learning diagnosis is a critical task that monitors students' cognitive state during educational activities, with the goal of enhancing learning outcomes. With advancements in language models (LMs)...

Fangzhou Yao, Sheng Chang, Weibo Gao, Qi Liu

2603.03236 2026-03-03
AI LLM

AI-for-Science Low-code Platform with Bayesian Adversarial Multi-Agent Framework

Large Language Models (LLMs) demonstrate potentials for automating scientific code generation but face challenges in reliability, error propagation in multi-agent workflows, and evaluation in domai...

Zihang Zeng, Jiaquan Zhang, Pengze Li, Yuan Qi, Xi Chen

2603.03233 2026-03-03
TESTING

Adaptive Methods Are Preferable in High Privacy Settings: An SDE Perspective

Differential Privacy (DP) is becoming central to large-scale training as privacy regulations tighten. We revisit how DP noise interacts with adaptivity in optimization through the lens of stochasti...

Enea Monzio Compagnoni, Alessandro Stanghellini, Rustem Islamov, Aurelien Lucchi, Anastasiia Kolo...

2603.03226 2026-03-03
TESTING

Stabilized Adaptive Loss and Residual-Based Collocation for Physics-Informed Neural Networks

Physics-Informed Neural Networks (PINNs) have been recognized as a mesh-free alternative to solve partial differential equations where physics information is incorporated. However, in dealing with ...

Divyavardhan Singh, Shubham Kamble, Dimple Sonone, Kishor Upla

2603.03224 2026-03-03
TESTING

Expanding Universal Machine Learning Interatomic Potentials to 97 Elements Towards Nuclear Applications

Machine learning interatomic potentials (MLIPs) evaluate potential energy surfaces orders of magnitude faster while maintaining accuracy comparable to first-principles calculations, and universal M...

Naoya Kuroda, Kenji Ishihara, Tomoya Shiota, Wataru Mizukami

2603.03223 2026-03-03
TESTING

Geodesic flows on a black-hole background

A recent notion of geodesic flows which comes out of noncommutative geometry but which is also novel in the classical case is studied in detail for a Schwarzschild spacetime. In this framework, the...

Kaushlendra Kumar, Shahn Majid

2603.03222 2026-03-03
AI LLM

Understanding and Mitigating Dataset Corruption in LLM Steering

Contrastive steering has been shown as a simple and effective method to adjust the generative behavior of LLMs at inference time. It uses examples of prompt responses with and without a trait to id...

Cullen Anderson, Narmeen Oozeer, Foad Namjoo, Remy Ogasawara, Amirali Abdullah, Jeff M. Phillips

2603.03206 2026-03-03
AI LLM

Learning When to Act or Refuse: Guarding Agentic Reasoning Models for Safe Multi-Step Tool Use

Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon actions where a single misstep, such as accessing f...

Aradhye Agarwal, Gurdit Siyan, Yash Pandya, Joykirat Singh, Akshay Nambi, Ahmed Awadallah

2603.03205 2026-03-03
AI LLM

Code2Math: Can Your Code Agent Effectively Evolve Math Problems Through Exploration?

As large language models (LLMs) advance their mathematical capabilities toward the IMO level, the scarcity of challenging, high-quality problems for training and evaluation has become a significant...

Dadi Guo, Yuejin Xie, Qingyu Liu, Jiayu Liu, Zhiyuan Fan, Qihan Ren, Shuai Shao, Tianyi Zhou, Don...

2603.03202 2026-03-03
AI LLM

Search for a massless particle beyond the Standard Model in the $Ξ^0\toΛ+ \text{invisible}$ decay

A search for a massless beyond-standard-model particle is performed in the decay $Ξ^{0}\toΛ+\text{invisible}$ using $(1.0087 \pm 0.0044)\times 10^{10}$ $J/ψ$ events collected with the BESIII detect...

BESIII Collaboration, M. Ablikim, M. N. Achasov, P. Adlarson, X. C. Ai, C. S. Akondi, R. Alibert...

2603.03199 2026-03-03
AI LLM

Shared (Mis)Understandings and the Governance of AI: A Thematic Analysis of the 2023-2024 Oversight of AI Hearings

This paper investigates early legislative deliberations over Artificial Intelligence in the United States through a thematic analysis of the 2023-2024 Oversight of AI hearings held by the Senate Ju...

Rachel Leach

2603.03193 2026-03-03
AI LLM

MoD-DPO: Towards Mitigating Cross-modal Hallucinations in Omni LLMs using Modality Decoupled Preference Optimization

Omni-modal large language models (omni LLMs) have recently achieved strong performance across audiovisual understanding tasks, yet they remain highly susceptible to cross-modal hallucinations arisi...

Ashutosh Chaubey, Jiacheng Pang, Mohammad Soleymani

2603.03192 2026-03-03