Papers
Research papers from arXiv and related sources
A Perfectoid Duality Between M-Theory and F-Theory
We present a non-singular, definition-level formulation of F-theory by replacing the traditional shrinking-fiber limit of M-theory with compactification on a tower-completed circle described using ...
Arshid Shabir, Bobby Eka Gunara, Mir Faizal
Small HVAC Control Demonstrations in Larger Buildings Often Overestimate Savings
How much energy, money, and emissions can advanced control of heating and cooling equipment save in real buildings? To address this question, researchers sometimes control a small number of thermal...
Arash J. Khabbazi, Kevin J. Kircher
Cosmic Environment as the Primary Driver of Dwarf Satellite Statistics
Context:Satellite dwarf galaxies provide key constraints on galaxy formation and evolution as their abundance and spatial distribution reflect both host properties and large-scale environment. Ai...
Saeed Tavasoli, Parsa Ghafour
Fused-Silica Activation Cherenkov Detector for Pulsed D--T Fusion Yields
We demonstrate a compact, non-toxic, low-cost neutron-yield diagnostic for pulsed D--T fusion systems using an undoped fused-silica (SiO$2$) rod as both activation target and Cherenkov radiator. D-...
N. Kaneshige, S. Alawabdeh, W. Hennig, D. Cech, M. Hua, R. Grazioso
EgoAVFlow: Robot Policy Learning with Active Vision from Human Egocentric Videos via 3D Flow
Egocentric human videos provide a scalable source of manipulation demonstrations; however, deploying them on robots requires active viewpoint control to maintain task-critical visibility, which hum...
Daesol Cho, Youngseok Jang, Danfei Xu, Sehoon Ha
CWM: Contrastive World Models for Action Feasibility Learning in Embodied Agent Pipelines
A reliable action feasibility scorer is a critical bottleneck in embodied agent pipelines: before any planning or reasoning occurs, the agent must identify which candidate actions are physically ex...
Chayan Banerjee
From Bias to Balance: Fairness-Aware Paper Recommendation for Equitable Peer Review
Despite frequent double-blind review, systemic biases related to author demographics still disadvantage underrepresented groups. We start from a simple hypothesis: if a post-review recommender is t...
Uttamasha Anjally Oyshi, Susan Gauch
LoBoost: Fast Model-Native Local Conformal Prediction for Gradient-Boosted Trees
Gradient-boosted decision trees are among the strongest off-the-shelf predictors for tabular regression, but point predictions alone do not quantify uncertainty. Conformal prediction provides distr...
Vagner Santos, Victor Coscrato, Luben Cabezas, Rafael Izbicki, Thiago Ramos
Calibrated Test-Time Guidance for Bayesian Inference
Test-time guidance is a widely used mechanism for steering pretrained diffusion models toward outcomes specified by a reward function. Existing approaches, however, focus on maximizing reward rathe...
Daniel Geyfman, Felix Draxler, Jan Groeneveld, Hyunsoo Lee, Theofanis Karaletsos, Stephan Mandt
HubScan: Detecting Hubness Poisoning in Retrieval-Augmented Generation Systems
Retrieval-Augmented Generation (RAG) systems are essential to contemporary AI applications, allowing large language models to obtain external knowledge via vector similarity search. Nevertheless, t...
Idan Habler, Vineeth Sai Narajala, Stav Koren, Amy Chang, Tiffany Saade
Exploring Human Behavior During Abstract Rule Inference and Problem Solving with the Cognitive Abstraction and Reasoning Corpus
Humans exhibit remarkable flexibility in abstract reasoning, and can rapidly learn and apply rules from sparse examples. To investigate the cognitive strategies underlying this ability, we introduc...
Caroline Ahn, Quan Do, Leah Bakst, Michael P. Pascale, Joseph T. McGuire, Michael E. Hasselmo, Ch...
WHOLE: World-Grounded Hand-Object Lifted from Egocentric Videos
Egocentric manipulation videos are highly challenging due to severe occlusions during interactions and frequent object entries and exits from the camera view as the person moves. Current methods ty...
Yufei Ye, Jiaman Li, Ryan Rong, C. Karen Liu
Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets
The reliability of multilingual Large Language Model (LLM) evaluation is currently compromised by the inconsistent quality of translated benchmarks. Existing resources often suffer from semantic dr...
Hanna Yukhymenko, Anton Alexandrov, Martin Vechev
Off-The-Shelf Image-to-Image Models Are All You Need To Defeat Image Protection Schemes
Advances in Generative AI (GenAI) have led to the development of various protection strategies to prevent the unauthorized use of images. These methods rely on adding imperceptible protective pertu...
Xavier Pleimling, Sifat Muhammad Abdullah, Gunjan Balde, Peng Gao, Mainack Mondal, Murtuza Jadliw...
Reimagining Data Work: Participatory Annotation Workshops as Feminist Practice
AI systems depend on the invisible and undervalued labor of data workers, who are often treated as interchangeable units rather than collaborators with meaningful expertise. Critical scholars and p...
Yujia Gao, Isadora Araujo Cruxên, Helena Suárez Val, Alessandra Jungs de Almeida, Catherine D'Ign...
Hybrid Consensus with Quantum Sybil Resistance
Sybil resistance is a key requirement of decentralized consensus protocols. It is achieved by introducing a scarce resource (such as computational power, monetary stake, disk space, etc.), which pr...
Dar Gilboa, Siddhartha Jain, Or Sattath
GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL
Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation tasks. This gap stems from two limitations: a shortage of high-quality, action-aligned reasoning data...
Rui Yang, Qianhui Wu, Zhaoyang Wang, Hanyang Chen, Ke Yang, Hao Cheng, Huaxiu Yao, Baoling Peng, ...
UC-Secure Star DKG for Non-Exportable Key Shares with VSS-Free Enforcement
Distributed Key Generation (DKG) lets parties derive a common public key while keeping the signing key secret-shared. UC-secure DKG requires a verifiable-sharing enforcement layer -- classically sa...
Vipin Singh Sehrawat
Codesigning Ripplet: an LLM-Assisted Assessment Authoring System Grounded in a Conceptual Model of Teachers' Workflows
Assessments are critical in education, but creating them can be difficult. To address this challenge in a grounded way, we partnered with 13 teachers in a seven-month codesign process. We developed...
Yuan Cui, Annabel Goldman, Jovy Zhou, Xiaolin Liu, Clarissa Shieh, Joshua Yao, Mia Cheng, Matthew...
A Taxonomy of Human--MLLM Interaction in Early-Stage Sketch-Based Design Ideation
As multimodal large language models (MLLMs) are increasingly integrated into early-stage design tools, it is important to understand how designers collaborate with AI during ideation. In a user stu...
Weiayn Shi, Kenny Tsu Wei Choo