Tootfinder

Deconstructing Attention: Investigating Design Principles for Effective Language Modeling
Huiyin Xue, Nafise Sadat Moosavi, Nikolaos Aletras
https://arxiv.org/abs/2510.11602 htt…

Deconstructing Attention: Investigating Design Principles for Effective Language Modeling
The success of Transformer language models is widely credited to their dot-product attention mechanism, which interweaves a set of key design principles: mixing information across positions (enabling multi-token interactions), sequence-dependent activations (where attention weights adapt to each input), a specific mathematical form (dot-product similarities plus softmax weighting), and coupling of queries and keys to evolving hidden states (grounding attention in the current layer). However, th…

Design Principles for Sequence Models via Coefficient Dynamics
Jerome Sieber, Antonio Orvieto, Melanie N. Zeilinger, Carmen Amo Alonso
https://arxiv.org/abs/2510.09389 https://

Design Principles for Sequence Models via Coefficient Dynamics
Deep sequence models, ranging from Transformers and State Space Models (SSMs) to more recent approaches such as gated linear RNNs, fundamentally compute outputs as linear combinations of past value vectors. To draw insights and systematically compare such architectures, we develop a unified framework that makes this output operation explicit, by casting the linear combination coefficients as the outputs of autonomous linear dynamical systems driven by impulse inputs. This viewpoint, in spirit s…

AI-Agents for Culturally Diverse Online Higher Education Environments
Fuze Sun, Paul Craig, Lingyu Li, Shixiangyue Meng, Chuxi Nan
https://arxiv.org/abs/2510.10520 https://

AI-Agents for Culturally Diverse Online Higher Education Environments
As the global reach of online higher education continues to grow, universities are increasingly accommodating students from diverse cultural backgrounds \parencite{tereshko2024culturally}. This can present a number of challenges including linguistic barriers \parencite{ullah2021linguistic}, cultural differences in learning style \parencite{omidvar2012cultural}, cultural sensitivity in course design \parencite{nguyen2022cultural} and perceived isolation when students feel their perspectives or e…

ExpVid: A Benchmark for Experiment Video Understanding & Reasoning
Yicheng Xu, Yue Wu, Jiashuo Yu, Ziang Yan, Tianxiang Jiang, Yinan He, Qingsong Zhao, Kai Chen, Yu Qiao, Limin Wang, Manabu Okumura, Yi Wang
https://arxiv.org/abs/2510.11606

ExpVid: A Benchmark for Experiment Video Understanding & Reasoning
Multimodal Large Language Models (MLLMs) hold promise for accelerating scientific discovery by interpreting complex experimental procedures. However, their true capabilities are poorly understood, as existing benchmarks neglect the fine-grained and long-horizon nature of authentic laboratory work, especially in wet-lab settings. To bridge this gap, we introduce ExpVid, the first benchmark designed to systematically evaluate MLLMs on scientific experiment videos. Curated from peer-reviewed video…

Few-shot Molecular Property Prediction: A Survey
Zeyu Wang, Tianyi Jiang, Huanchang Ma, Yao Lu, Xiaoze Bao, Shanqing Yu, Qi Xuan, Shirui Pan, Xin Zheng
https://arxiv.org/abs/2510.08900

Few-shot Molecular Property Prediction: A Survey
AI-assisted molecular property prediction has become a promising technique in early-stage drug discovery and materials design in recent years. However, due to high-cost and complex wet-lab experiments, real-world molecules usually experience the issue of scarce annotations, leading to limited labeled data for effective supervised AI model learning. In light of this, few-shot molecular property prediction (FSMPP) has emerged as an expressive paradigm that enables learning from only a few labeled…

A Vision for Access Control in LLM-based Agent Systems
Xinfeng Li, Dong Huang, Jie Li, Hongyi Cai, Zhenhong Zhou, Wei Dong, XiaoFeng Wang, Yang Liu
https://arxiv.org/abs/2510.11108

A Vision for Access Control in LLM-based Agent Systems
The autonomy and contextual complexity of LLM-based agents render traditional access control (AC) mechanisms insufficient. Static, rule-based systems designed for predictable environments are fundamentally ill-equipped to manage the dynamic information flows inherent in agentic interactions. This position paper argues for a paradigm shift from binary access control to a more sophisticated model of information governance, positing that the core challenge is not merely about permission, but about…

Demystifying Reinforcement Learning in Agentic Reasoning
Zhaochen Yu, Ling Yang, Jiaru Zou, Shuicheng Yan, Mengdi Wang
https://arxiv.org/abs/2510.11701 https://

Demystifying Reinforcement Learning in Agentic Reasoning
Recently, the emergence of agentic RL has showcased that RL could also effectively improve the agentic reasoning ability of LLMs, yet the key design principles and optimal practices remain unclear. In this work, we conduct a comprehensive and systematic investigation to demystify reinforcement learning in agentic reasoning from three key perspectives: data, algorithm, and reasoning mode. We highlight our key insights: (i) Replacing stitched synthetic trajectories with real end-to-end tool-use t…

Walking, Rolling, and Beyond: First-Principles and RL Locomotion on a TARS-Inspired Robot
Aditya Sripada, Abhishek Warrier
https://arxiv.org/abs/2510.05001 https://

Walking, Rolling, and Beyond: First-Principles and RL Locomotion on a TARS-Inspired Robot
Robotic locomotion research typically draws from biologically inspired leg designs, yet many human-engineered settings can benefit from non-anthropomorphic forms. TARS3D translates the block-shaped 'TARS' robot from Interstellar into a 0.25 m, 0.99 kg research platform with seven actuated degrees of freedom. The film shows two primary gaits: a bipedal-like walk and a high-speed rolling mode. For TARS3D, we build reduced-order models for each, derive closed-form limit-cycle conditions, and valid…

Engineering the uncontrollable: Steering noisy spin-correlated radical-pairs with coherent and incoherent control
Farhan T. Chowdhury, Luke D. Smith, Daniel R. Kattnig
https://arxiv.org/abs/2510.05074 …

Engineering the uncontrollable: Steering noisy spin-correlated radical-pairs with coherent and incoherent control
The quantum control of spin-correlated radical pairs (SCRPs) holds promise for the targeted manipulation of magnetic field effects, with potential applications ranging from the design of noise-resilient quantum information processors to genetically encodable quantum sensors. However, achieving precise handles over the intricate interplay between coherent electron spin dynamics and incoherent relaxation processes in photoexcited radical-pair reactions requires tractable approaches for numericall…

Surrogate Graph Partitioning for Spatial Prediction
Yuta Shikuri, Hironori Fujisawa
https://arxiv.org/abs/2510.07832 https://arxiv.org/pdf/2510.07832

Surrogate Graph Partitioning for Spatial Prediction
Spatial prediction refers to the estimation of unobserved values from spatially distributed observations. Although recent advances have improved the capacity to model diverse observation types, adoption in practice remains limited in industries that demand interpretability. To mitigate this gap, surrogate models that explain black-box predictors provide a promising path toward interpretable decision making. In this study, we propose a graph partitioning problem to construct spatial segments tha…