Tootfinder

Multi-State Tracker: Enhancing Efficient Object Tracking via Multi-State Specialization and Interaction
Shilei Wang, Gong Cheng, Pujian Lai, Dong Gao, Junwei Han
https://arxiv.org/abs/2508.11531

Multi-State Tracker: Enhancing Efficient Object Tracking via Multi-State Specialization and Interaction
Efficient trackers achieve faster runtime by reducing computational complexity and model parameters. However, this efficiency often compromises the expense of weakened feature representation capacity, thus limiting their ability to accurately capture target states using single-layer features. To overcome this limitation, we propose Multi-State Tracker (MST), which utilizes highly lightweight state-specific enhancement (SSE) to perform specialized enhancement on multi-state features produced by …

Characterization of fiberwise bimeromorphism and specialization of bimeromorphic types I: the non-negative Kodaira dimension case
Jian Chen, Sheng Rao, I-Hsun Tsai
https://arxiv.org/abs/2506.12670

Characterization of fiberwise bimeromorphism and specialization of bimeromorphic types I: the non-negative Kodaira dimension case
Inspired by the recent works of M. Kontsevich--Y. Tschinkel and J. Nicaise--J. C. Ottem on specialization of birational types for smooth families (in the scheme category) and J. Koll{á}r's work on fiberwise bimeromorphism, we focus on characterizing the fiberwise bimeromorphism and utilizing the characterization to investigate the specialization of bimeromorphic types for non-smooth families in the complex analytic setting. We provide some criteria for a bimeromorphic map between two families …

A Performance Model for Warp Specialization Kernels
Zhengyang Liu, Vinod Grover
https://arxiv.org/abs/2506.11209 https://arxiv.org/pd…

A Performance Model for Warp Specialization Kernels
This paper presents a performance model tailored for warp specialization kernels, focusing on factors such as warp size, tilling size, input matrix size, memory bandwidth, and thread divergence. Our model offers accurate predictions of execution time by leveraging differential equations validated through simulations and experiments. The insights gained from this model not only enhance our understanding of warp specialization techniques but also have practical implications for optimizing GPU-acc…

Assistant/Associate Professor of Church History
https://ift.tt/DmKVkZU
Fuller Theological Seminary School of Mission and Theology Tenure-Track Faculty Series Position…
via Input 4 RELCFP htt…

"Bypassing" #specialization in #Rust or How I Learned to Stop Worrying and Love Function Pointers
https://

FLUID: Flow-Latent Unified Integration via Token Distillation for Expert Specialization in Multimodal Learning
Van Duc Cuong, Ta Dinh Tam, Tran Duc Chinh, Nguyen Thi Hanh
https://arxiv.org/abs/2508.07264

FLUID: Flow-Latent Unified Integration via Token Distillation for Expert Specialization in Multimodal Learning
Multimodal classification requires robust integration of visual and textual signals, yet common fusion strategies are brittle and vulnerable to modality-specific noise. In this paper, we present \textsc{FLUID}-Flow-Latent Unified Integration via Token Distillation for Expert Specialization, a principled token-level pipeline that improves cross-modal robustness and scalability. \textsc{FLUID} contributes three core elements: (1) \emph{Q-transforms}, learnable query tokens that distill and retain…

MoE-MLoRA for Multi-Domain CTR Prediction: Efficient Adaptation with Expert Specialization
Ken Yagel, Eyal German, Aviel Ben Siman Tov
https://arxiv.org/abs/2506.07563

MoE-MLoRA for Multi-Domain CTR Prediction: Efficient Adaptation with Expert Specialization
Personalized recommendation systems must adapt to user interactions across different domains. Traditional approaches like MLoRA apply a single adaptation per domain but lack flexibility in handling diverse user behaviors. To address this, we propose MoE-MLoRA, a mixture-of-experts framework where each expert is first trained independently to specialize in its domain before a gating network is trained to weight their contributions dynamically. We evaluate MoE-MLoRA across eight CTR models on Mov…

Instruction-Tuned Video-Audio Models Elucidate Functional Specialization in the Brain
Subba Reddy Oota, Khushbu Pahwa, Prachi Jindal, Satya Sai Srinath Namburi, Maneesh Singh, Tanmoy Chakraborty, Bapi S. Raju, Manish Gupta
https://arxiv.org/abs/2506.08277

Instruction-Tuned Video-Audio Models Elucidate Functional Specialization in the Brain
Recent voxel-wise multimodal brain encoding studies have shown that multimodal large language models (MLLMs) exhibit a higher degree of brain alignment compared to unimodal models in both unimodal and multimodal stimulus settings. More recently, instruction-tuned multimodal models have shown to generate task-specific representations that align strongly with brain activity. However, prior work evaluating the brain alignment of MLLMs has primarily focused on unimodal settings or relied on non-ins…

Towards Memory Specialization: A Case for Long-Term and Short-Term RAM
Peijing Li, Muhammad Shahir Abdurraman, Rachel Cleaveland, Sergey Legtchenko, Philip Levis, Ioan Stefanovici, Thierry Tambe, David Tennenhouse, Caroline Trippel
https://arxiv.org/abs/2508.02992

Towards Memory Specialization: A Case for Long-Term and Short-Term RAM
Both SRAM and DRAM have stopped scaling: there is no technical roadmap to reduce their cost (per byte/GB). As a result, memory now dominates system cost. This paper argues for a paradigm shift from today's simple memory hierarchy toward specialized memory architectures that exploit application-specific access patterns. Rather than relying solely on traditional off-chip DRAM and on-chip SRAM, we envisage memory systems equipped with additional types of memory whose performance trade-offs benefit…

This https://arxiv.org/abs/2212.05366 has been replaced.
link: https://scholar.google.com/scholar?q=a

Specialization of Difference Equations and High Frobenius Powers
We study valued fields equipped with an automorphism $σ$ which is locally infinitely contracting in the sense that $α\llσα$ for all $0<α\inΓ$. We show that various notions of valuation theory, such as Henselian and strictly Henselian hulls, admit meaningful transformal analogues. We prove canonical amalgamation results, and exhibit the way that transformal wild ramification is controlled by torsors over generalized vector groups. Model theoretically, we determine the model companion: it i…

that moment when you discover the non-CS specialization of your fellow #RSEng you have known for years, by pure accident / #serendipity
@…

Volumes of moduli spaces of directed ribbon graphs and Cut-and-Join operators
Simon Barazer
https://arxiv.org/abs/2507.07308 https://…

Volumes of moduli spaces of directed ribbon graphs and Cut-and-Join operators
In this paper, we investigate the algebraic structure underlying the acyclic decomposition. This decomposition applies to directed metric ribbon graphs and enables the recursive computation of the volumes of their moduli spaces. Building on this, we define integral operators with these volumes and show that they satisfy a Cut-and-Join type equation. Furthermore, we demonstrate that a suitable specialization of these operators gives rise to a generating series for \textit{dessins d'enfants}.

Do We Really Need Specialization? Evaluating Generalist Text Embeddings for Zero-Shot Recommendation and Search
Matteo Attimonelli, Alessandro De Bellis, Claudio Pomo, Dietmar Jannach, Eugenio Di Sciascio, Tommaso Di Noia
https://arxiv.org/abs/2507.05006

Do We Really Need Specialization? Evaluating Generalist Text Embeddings for Zero-Shot Recommendation and Search
Pre-trained language models (PLMs) are widely used to derive semantic representations from item metadata in recommendation and search. In sequential recommendation, PLMs enhance ID-based embeddings through textual metadata, while in product search, they align item characteristics with user intent. Recent studies suggest task and domain-specific fine-tuning are needed to improve representational power. This paper challenges this assumption, showing that Generalist Text Embedding Models (GTEs), p…

Hybrid Game Control Envelope Synthesis
Aditi Kabra, Jonathan Laurent, Stefan Mitsch, Andr\'e Platzer
https://arxiv.org/abs/2508.05997 https://arxiv.org…

Hybrid Game Control Envelope Synthesis
Control problems for embedded systems like cars and trains can be modeled by two-player hybrid games. Control envelopes, which are families of safe control solutions, correspond to nondeterministic winning policies of hybrid games, where each deterministic specialization of the policy is a control solution. This paper synthesizes nondeterministic winning policies for hybrid games that are as permissive as possible. It introduces subvalue maps, a compositional representation of such policies tha…

Hecto: Modular Sparse Experts for Adaptive and Interpretable Reasoning
Sanskar Pandey, Ruhaan Chopra, Saad Murtaza Bhat, Ark Abhyudaya
https://arxiv.org/abs/2506.22919

Hecto: Modular Sparse Experts for Adaptive and Interpretable Reasoning
Mixture-of-Experts (MoE) models enable conditional computation by routing inputs to specialized experts, but these experts rely on identical inductive biases, thus limiting representational diversity. This static computation pathway is inefficient for inputs that require different types of reasoning and limits specialization and interpretability. We propose Hecto, a lightweight MoE architecture that leverages architectural heterogeneity by combining a GRU expert for temporal reasoning and an FF…

This https://arxiv.org/abs/2411.16826 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCY_…

Ideological Fragmentation of the Social Media Ecosystem: From echo chambers to echo platforms
The entertainment-driven nature of social media encourages users to engage with like-minded individuals and consume content aligned with their beliefs, limiting exposure to diverse perspectives. Simultaneously, users migrate between platforms, either due to moderation policies like de-platforming or in search of environments better suited to their preferences. These dynamics drive the specialization of the social media ecosystem, shifting from internal echo chambers to "echo platforms"--entire …

Specialization and rigidity
Zinovy Reichstein, Federico Scavia
https://arxiv.org/abs/2506.22314 https://arxiv.org/pdf/2506.22314

Specialization and rigidity
We describe a general method, originated by Ofer Gabber, for showing that a very general fiber in a family has certain properties. We illustrate this method with concrete examples taken from algebraic dynamics, the rationality problem for algebraic varieties, Galois theory, quadratic form theory and the theory of central simple algebras.

Coh zeta functions for inert quadratic orders
Yifeng Huang
https://arxiv.org/abs/2507.21966 https://arxiv.org/pdf/2507.21966…

Coh zeta functions for inert quadratic orders
We study the Coh zeta function for a family of inert quadratic orders, which we conjecture to be given by $t$-deformed Bressoud $q$-series. This completes a trilogy connecting the zeta functions of ramified and split quadratic orders to the classical Andrews--Gordon and Bressoud identities, respectively. We provide strong evidence for this conjecture by deriving the first explicit formulas for the finitized Coh zeta function of the simplest order in the family, and for the $t=1$ specialization …

Collaborative Medical Triage under Uncertainty: A Multi-Agent Dynamic Matching Approach
Hongyan Cheng, Chengzhang Yu, Yanshu Shi, Chiyue Wang, Cong Liu, Zhanpeng Jin
https://arxiv.org/abs/2507.22504

Collaborative Medical Triage under Uncertainty: A Multi-Agent Dynamic Matching Approach
The post-pandemic surge in healthcare demand, coupled with critical nursing shortages, has placed unprecedented pressure on emergency department triage systems, necessitating innovative AI-driven solutions. We present a multi-agent interactive intelligent system for medical triage that addresses three fundamental challenges in current AI-based triage systems: insufficient medical specialization leading to hallucination-induced misclassifications, heterogeneous department structures across healt…

A Comparative Study of Specialized LLMs as Dense Retrievers
Hengran Zhang, Keping Bi, Jiafeng Guo
https://arxiv.org/abs/2507.03958 https://

A Comparative Study of Specialized LLMs as Dense Retrievers
While large language models (LLMs) are increasingly deployed as dense retrievers, the impact of their domain-specific specialization on retrieval effectiveness remains underexplored. This investigation systematically examines how task-specific adaptations in LLMs influence their retrieval capabilities, an essential step toward developing unified retrievers capable of handling text, code, images, and multimodal content. We conduct extensive experiments with eight Qwen2.5 7B LLMs, including base,…

The Theory of Economic Complexity
C\'esar A. Hidalgo, Viktor Stojkoski
https://arxiv.org/abs/2506.18829 https://arxiv.org/pdf/250…

The Theory of Economic Complexity
Economic complexity estimates rely on eigenvectors derived from matrices of specialization to explain differences in economic growth, inequality, and sustainability. Yet, despite their widespread use, we still lack a principled theory that can deduce these eigenvectors from first principles and place them in the context of a mechanistic model. Here, we calculate these eigenvectors analytically for a model where the output of an economy in an activity increases with the probability the economy i…

Modular versus Hierarchical: A Structural Signature of Topic Popularity in Mathematical Research
Brian Hepler
https://arxiv.org/abs/2506.22946 https://

Modular versus Hierarchical: A Structural Signature of Topic Popularity in Mathematical Research
Mathematical researchers, especially those in early-career positions, face critical decisions about topic specialization with limited information about the collaborative environments of different research areas. The aim of this paper is to study how the popularity of a research topic is associated with the structure of that topic's collaboration network, as observed by a suite of measures capturing organizational structure at several scales. We apply these measures to 1,938 algorithmically disc…

This https://arxiv.org/abs/2008.08520 has been replaced.
link: https://scholar.google.com/scholar?q=a

Endoscopic decompositions and the Hausel-Thaddeus conjecture
We construct natural operators connecting the cohomology of the moduli spaces of stable Higgs bundles with different ranks and genera which, after numerical specialization, recover the topological mirror symmetry conjecture of Hausel-Thaddeus concerning $\mathrm{SL}_n$- and $\mathrm{PGL}_n$-Higgs bundles. This provides a complete description of the cohomology of the moduli space of stable $\mathrm{SL}_n$-Higgs bundles in terms of the tautological classes, and gives a new proof of the Hausel-Tha…

EnTao-GPM: DNA Foundation Model for Predicting the Germline Pathogenic Mutations
Zekai Lin, Haoran Sun, Yucheng Guo, Yujie Yang, Yanwen Wang, Bozhen Hu, Chonghang Ye, Qirong Yang, Fan Zhong, Xiaoming Zhang, Lei Liu
https://arxiv.org/abs/2507.21706

EnTao-GPM: DNA Foundation Model for Predicting the Germline Pathogenic Mutations
Distinguishing pathogenic mutations from benign polymorphisms remains a critical challenge in precision medicine. EnTao-GPM, developed by Fudan University and BioMap, addresses this through three innovations: (1) Cross-species targeted pre-training on disease-relevant mammalian genomes (human, pig, mouse), leveraging evolutionary conservation to enhance interpretation of pathogenic motifs, particularly in non-coding regions; (2) Germline mutation specialization via fine-tuning on ClinVar and HG…

Mix-of-Language-Experts Architecture for Multilingual Programming
Yifan Zong, Yuntian Deng, Pengyu Nie
https://arxiv.org/abs/2506.18923 https://

Mix-of-Language-Experts Architecture for Multilingual Programming
Large language models (LLMs) have demonstrated impressive capabilities in aiding developers with tasks like code comprehension, generation, and translation. Supporting multilingual programming -- i.e., coding tasks across multiple programming languages -- typically requires either (1) finetuning a single LLM across all programming languages, which is cost-efficient but sacrifices language-specific specialization and performance, or (2) finetuning separate LLMs for each programming language, whi…

Exploration on Demand: From Algorithmic Control to User Empowerment
Edoardo Bianchi
https://arxiv.org/abs/2507.21884 https://arxiv.org/pdf/2507.21884

Exploration on Demand: From Algorithmic Control to User Empowerment
Recommender systems often struggle with over-specialization, which severely limits users' exposure to diverse content and creates filter bubbles that reduce serendipitous discovery. To address this fundamental limitation, this paper introduces an adaptive clustering framework with user-controlled exploration that effectively balances personalization and diversity in movie recommendations. Our approach leverages sentence-transformer embeddings to group items into semantically coherent clusters t…