Papers
Research papers from arXiv and related sources
Safe or Slow? The Illusion of Thermal Stability Under Reduced-Velocity Nail Intrusion
This study investigates the effects of nail penetration speed on the safety outcomes of large-format automotive lithium-ion pouch cells. Through six controlled tests varying the speed of nail inser...
Eymen Ipek, Oliver Korak, Georg Gsellmann, Andrey Golubkov
Efficient Reasoning at Fixed Test-Time Cost via Length-Aware Attention Priors and Gain-Aware Training
We study efficient reasoning under tight compute. We ask how to make structured, correct decisions without increasing test time cost. We add two training only components to small and medium Transfo...
Rian Atri
Towards Instance Segmentation with Polygon Detection Transformers
One of the bottlenecks for instance segmentation today lies in the conflicting requirements of high-resolution inputs and lightweight, real-time inference. To address this bottleneck, we present a ...
Jiacheng Sun, Jiaqi Lin, Wenlong Hu, Haoyang Li, Xinghong Zhou, Chenghai Mao, Yan Peng, Xiaomao Li
Beyond Test-Time Training: Learning to Reason via Hardware-Efficient Optimal Control
Associative memory has long underpinned the design of sequential models. Beyond recall, humans reason by projecting future states and selecting goal-directed actions, a capability that modern langu...
Peihao Wang, Shan Yang, Xijun Wang, Tesi Xiao, Xin Liu, Changlong Yu, Yu Lou, Pan Li, Zhangyang W...
Distributed Convolutional Neural Networks for Object Recognition
This paper proposes a novel loss function for training a distributed convolutional neural network (DisCNN) to recognize only a specific positive class. By mapping positive samples to a compact set ...
Liang Sun
AlgoXpert Alpha Research Framework. A Rigorous IS WFA OOS Protocol for Mitigating Overfitting in Quantitative Strategies
Transitioning a strategy from backtest to live trading is a common failure point for quantitative systems due to parameter overfitting, selection bias, and sensitivity to regime changes. This paper...
The Anh Pham, Bao Chan Nguyen, Nguyet Nguyen Thi
Abundant Intelligence and Deficient Demand: A Macro-Financial Stress Test of Rapid AI Adoption
We formalize a macro-financial stress test for rapid AI adoption. Rather than a productivity bust or existential risk, we identify a distribution-and-contract mismatch: AI-generated abundance coexi...
Xupeng Chen
MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data
Self-evolving has emerged as a key paradigm for improving foundational models such as Large Language Models (LLMs) and Vision Language Models (VLMs) with minimal human intervention. While recent ap...
Zongxia Li, Hongyang Du, Chengsong Huang, Xiyang Wu, Lantao Yu, Yicheng He, Jing Xie, Xiaomin Wu,...
The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness
Situational awareness, the capacity of an AI system to recognize its own nature, understand its training and deployment context, and reason strategically about its circumstances, is widely consider...
Subramanyam Sahoo, Aman Chadha, Vinija Jain, Divya Chaudhary
POLISH'ing the Sky: Wide-Field and High-Dynamic Range Interferometric Image Reconstruction with Application to Strong Lens Discovery
Radio interferometry enables high-resolution imaging of astronomical radio sources by synthesizing a large effective aperture from an array of antennas and solving a deconvolution problem to recons...
Zihui Wu, Liam Connor, Samuel McCarty, Katherine L. Bouman
Real-Time Trust Verification for Safe Agentic Actions using TrustBench
As large language models evolve from conversational assistants to autonomous agents, ensuring trustworthiness requires a fundamental shift from post-hoc evaluation to real-time action verification....
Tavishi Sharma, Vinayak Sharma, Pragya Sharma
Binary Black Hole inspirals cannot hide their eccentricity
The events detected by the LIGO Virgo KAGRA collaboration over a period of 10 years have yielded a treasure trove of signals from compact binary coalescences. None of these events have shown a conf...
Johann Fernandes, Praveer Tiwari, Archana Pai
RTFDNet: Fusion-Decoupling for Robust RGB-T Segmentation
RGB-Thermal (RGB-T) semantic segmentation is essential for robotic systems operating in low-light or dark environments. However, traditional approaches often overemphasize modality balance, resulti...
Kunyu Tan, Mingjian Liang
A detailed analysis of possible new-physics effects in semileptonic decays $B_s \to D_s^{(*)}τ\barν$
We study the semileptonic decays $B_s \to D_s^{(*)}τ\barν$ as a promising probe for new physics (NP) beyond the standard model (SM). The extension of the SM is done through the introduction of four...
Mikhail A. Ivanov, Jignesh N. Pandya, Pietro Santorelli, Nakul R. Soni, Chien-Thang Tran, Hai-Cat...
From Verification to Amplification: Auditing Reverse Image Search as Algorithmic Gatekeeping in Visual Misinformation Fact-checking
As visual misinformation becomes increasingly prevalent, platform algorithms act as intermediaries that curate information for users' verification practices. Yet, it remains unclear how algorithmic...
Cong Lin, Yifei Chen, Jiangyue Chen, Yingdan Lu, Yilang Peng, Cuihua Shen
PM-Nav: Priori-Map Guided Embodied Navigation in Functional Buildings
Existing language-driven embodied navigation paradigms face challenges in functional buildings (FBs) with highly similar features, as they lack the ability to effectively utilize priori spatial kno...
Jiang Gao, Xiangyu Dong, Haozhou Li, Haoran Zhao, Yaoming Zhou, Xiaoguang Ma
Dynamic Stability Assessment of Grid-Connected Data Centers Powered by Small Modular Reactors
The accelerating growth of computational demand in modern data centers has further heightened the need for power infrastructures that are highly reliable, environmentally sustainable, and capable o...
Sobhan Badakhshan, Roshni Anna Jacob, Ali Mahboub Rad, Chao Pan, Yaoyu Li, Jie Zhang
Probabilistic Hysteresis Factor Prediction for Electric Vehicle Batteries with Graphite Anodes Containing Silicon
Batteries with silicon-graphite-based anodes, which offer higher energy density and improved charging performance, introduce pronounced voltage hysteresis, making state-of-charge (SoC) estimation p...
Runyao Yu, Viviana Kleine, Philipp Gromotka, Thomas Rudolf, Adrian Eisenmann, Gautham Ram Chandra...
Provably Safe Trajectory Generation for Manipulators Under Motion and Environmental Uncertainties
Robot manipulators operating in uncertain and non-convex environments present significant challenges for safe and optimal motion planning. Existing methods often struggle to provide efficient and f...
Fei Meng, Zijiang Yang, Xinyu Mao, Haobo Liang, Max Q. -H. Meng
A multi-phase-field model for fiber-reinforced composite laminates based on puck failure theory
This article proposes a multi-phase-field model using the Puck failure theory to predict the failure in fiber-reinforced composites (FRCs) laminates. Specifically, this work proposes a two-dimensio...
Pavan Kumar Asur Vijaya Kumar, Rafael Fleischhacker, Aamir Dean, Heinz E Pettermann