Papers
Research papers from arXiv and related sources
Logos: An evolvable reasoning engine for rational molecular design
The discovery and design of functional molecules remain central challenges across chemistry,biology, and materials science. While recent advances in machine learning have accelerated molecular prop...
Haibin Wen, Zhe Zhao, Fanfu Wang, Tianyi Xu, Hao Zhang, Chao Yang, Ye Wei
From Perception to Cognition: How Latency Affects Interaction Fluency and Social Presence in VR Conferencing
Virtual reality (VR) conferencing has the potential to provide geographically dispersed users with an immersive environment, enabling rich social interactions and user experience using avatars. How...
Jiarun Song, Ninghao Wan, FuZheng Yang, Weisi Lin
Transductive Generalization via Optimal Transport and Its Application to Graph Node Classification
Many existing transductive bounds rely on classical complexity measures that are computationally intractable and often misaligned with empirical behavior. In this work, we establish new representat...
MoonJeong Park, Seungbeom Lee, Kyungmin Kim, Jaeseung Heo, Seunghyuk Cho, Shouheng Li, Sangdon Pa...
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
Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval
Personalized large language models (LLMs) rely on memory retrieval to incorporate user-specific histories, preferences, and contexts. Existing approaches either overload the LLM by feeding all the ...
Yingyi Zhang, Junyi Li, Wenlin Zhang, Penyue Jia, Xianneng Li, Yichao Wang, Derong Xu, Yi Wen, Hu...
Social-R1: Towards Human-like Social Reasoning in LLMs
While large language models demonstrate remarkable capabilities across numerous domains, social intelligence - the capacity to perceive social cues, infer mental states, and generate appropriate re...
Jincenzi Wu, Yuxuan Lei, Jianxun Lian, Yitian Huang, Lexin Zhou, Haotian Li, Xing Xie, Helen Meng
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
When Detectors Forget Forensics: Blocking Semantic Shortcuts for Generalizable AI-Generated Image Detection
AI-generated image detection has become increasingly important with the rapid advancement of generative AI. However, detectors built on Vision Foundation Models (VFMs, \emph{e.g.}, CLIP) often stru...
Chao Shuai, Zhenguang Liu, Shaojing Fan, Bin Gong, Weichen Lian, Xiuli Bi, Zhongjie Ba, Kui Ren
BridgeDiff: Bridging Human Observations and Flat-Garment Synthesis for Virtual Try-Off
Virtual try-off (VTOFF) aims to recover canonical flat-garment representations from images of dressed persons for standardized display and downstream virtual try-on. Prior methods often treat VTOFF...
Shuang Liu, Ao Yu, Linkang Cheng, Xiwen Huang, Li Zhao, Junhui Liu, Zhiting Lin, Yu Liu
Cognitively Layered Data Synthesis for Domain Adaptation of LLMs to Space Situational Awareness
Large language models (LLMs) demonstrate exceptional performance on general-purpose tasks. however, transferring them to complex engineering domains such as space situational awareness (SSA) remain...
Ding Linghu, Cheng Wang, Da Fan, Wei Shi, Kaifeng Yin, Xiaoliang Xue, Fan Yang, Haiyi Ren, Cong Z...
Flash-KMeans: Fast and Memory-Efficient Exact K-Means
$k$-means has historically been positioned primarily as an offline processing primitive, typically used for dataset organization or embedding preprocessing rather than as a first-class component in...
Shuo Yang, Haocheng Xi, Yilong Zhao, Muyang Li, Xiaoze Fan, Jintao Zhang, Han Cai, Yujun Lin, Xiu...
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