Curated academic papers that inform our research directions.
Note: These are external publications from arXiv, not SparseTech publications. We share them as context for the mathematical foundations underlying our work.
VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders
Zhihao Xie, Junfeng Wu, Xinting Hu +2 more
Published: July 15, 2026
cs.CV
Video generative models commonly rely on latent spaces learned by 3D Variational Autoencoders (3D-VAEs). However, conventional 3D-VAEs are mainly optimized for pixel-level reconstruction, which can limit the semantic and spatio-temporal structure captured by their latents. Meanwhile, Video Foundation Models (VFMs) such…
Stochastic Domination of Gaussian Maxima: A Resolution to the Weak Simplex Conjecture
Abhijeet Mulgund
Published: July 15, 2026
math.PRcs.ITmath.MG
We prove a stochastic comparison for Gaussian maxima. Let $R$ be an $m\times m$ correlation matrix satisfying $R-\mathbf{1} \mathbf{1}^{\mathsf T}/m\succeq0$, let $X\sim\mathcal{N}(0,R)$, and let $Z_1,\ldots,Z_m$ be independent standard Gaussian random variables. Then…
Leveraging unlabelled data for generalizable neural population decoding
Ximeng Mao, Nanda H. Krishna, Avery Hee-Woon Ryoo +2 more
Published: July 15, 2026
cs.LGq-bio.NC
Robust and accurate neural decoders are integral to neurotechnologies such as brain-computer interfaces and closed-loop experiments. Recent work has shown that tokenizing neural data at the spike level facilitates multi-session pretraining and delivers state-of-the-art decoding performance. However, current spike-based…
Linear Independent Component Analysis via Optimal Transport
Ashutosh Jha, Michel Besserve, Simon Buchholz
Published: July 15, 2026
cs.LGstat.ML
Linear Independent Component Analysis (ICA) recovers jointly independent source signals from their linear mixtures. To achieve this, classical ICA algorithms attempt to maximize non-Gaussianity, measured by negentropy, which is linked to independence by information theory. Because exact negentropy optimization is…
From Pixels to States: Rethinking Interactive World Models as Game Engines
Zhen Li, Zian Meng, Shuwei Shi +4 more
Published: July 15, 2026
cs.CV
Building interactive worlds that respond coherently to player actions has long been a shared goal of computer graphics, games, and artificial intelligence. Recent video generative models provide a data-driven route toward this goal by predicting future observations conditioned on user actions, and are increasingly…
MetaPerch: Learning from metadata for bioacoustics foundation models
Mustafa Chasmai, Vincent Dumoulin, Jenny Hamer
Published: July 15, 2026
cs.LGcs.SD
Bioacoustic foundation models rely on large-scale citizen science platforms like Xeno-Canto for geographically and ecologically diverse data. Recent work has shown that supervision alone can produce SotA species detection models when trained on this large-scale data -- however, there remains unutilized potential in the…
Screening of Biosecurity Features in Metagenomic Data with Evo 2 Probes
Jeremy Guntoro, Alexander Dack, Dylan Danno +3 more
Published: July 15, 2026
q-bio.GNcs.LG
Genomic foundation models such as Evo 2 learn rich sequence representations, but their value for biosecurity screening is largely unexplored. We ask how much biosecurity-relevant signal is linearly accessible in these representations by training minimal linear and attention probes on frozen Evo 2 layer-26 activations,…
The even-uniform hypergraph Moore bound
Afonso S. Bandeira, Dmitriy Kunisky, Petar Nizić-Nikolac +2 more
Published: July 15, 2026
math.COcs.DMcs.DS
The hypergraph Moore bound conjectured by Feige (2008) controls the size of the smallest even cover in a $k$-uniform hypergraph in terms of the average density of hyperedges. An even cover is a set of hyperedges covering each vertex an even number of times, generalizing the notion of a cycle in a graph, so the size of…
Minimax Theory of Likelihood-Based Deep Learning for Speckle Regression
Soham Jana
Published: July 15, 2026
math.STstat.ML
Speckle noise is a multiplicative noise commonly encountered in coherent imaging modalities such as synthetic aperture radar, optical coherence tomography, and digital holography. Although deep learning methods, in practice, have achieved state-of-the-art performance for speckle denoising, their fundamental statistical…
Adaptivity in Local Kernel Based Methods for Approximating Solutions to the Poisson Equation
Jonah A. Reeger, Anders R. Johnson, Shelby W. Woodrum
Published: July 15, 2026
math.NA
Expanding on the recent development of adaptive local kernel methods for approximating the action of linear operators, a local estimate of the error and an adaptive procedure for approximating solutions to the Poisson equation is developed. The error estimate is used in the midst of the adaptive procedure to determine…
Fast Cascaded Recursive Filtering via a Block-Matrix Reformulation
Haotian Zhai, Bernd-Peter Paris
Published: July 15, 2026
eess.SP
Recursive (IIR) filters realized as cascaded second-order sections (biquads) offer both design generality and robustness against coefficient quantization. However, their inherent sample-to-sample feedback dependency poses a fundamental obstacle to parallel computation. This paper reformulates the biquad difference…
Hindcast: Replaying Prediction Markets to Evaluate LLM Forecasters
Xiao Ye, Jacob Dineen, Evan Zhu +3 more
Published: July 15, 2026
cs.CL
Forecasters are evaluated by backtesting, which replays resolved questions and grades the probability the system would have assigned before the outcome was known. For LLMs, two channels leak the answer into this test. A model that retrieves can surface reports written after the event, turning forecasting into a lookup,…
Deep Interaction: An Efficient Human-AI Interaction Method for Large Reasoning Models
Hefeng Zhou, Jinxuan Zhang, Jiong Lou +4 more
Published: July 15, 2026
cs.AI
The emergence of Chain-of-Thought (CoT) reasoning has significantly enhanced the ability of large language models (LLMs) to tackle complex, multi-step tasks. However, when errors occur, current interaction approaches typically involve re-generating another response that may make mistakes again, or users laboriously…
Earthquaker-AI: A Retrieval-Augmented Generation Framework with Rubric-Based Assessment for Primary School Earthquake Education
Xanthi Kokkinou, Chaido Mizeli, Nafsika Koulaxidou +2 more
Published: July 15, 2026
cs.AI
This paper presents Earthquaker-AI, a hybrid educational framework building upon a previously implemented educational robotics project by integrating a conversational AI assistant based on Retrieval-Augmented Generation. It aims to enhance earthquake preparedness and conscious action among primary-school students. The…
AI-accelerated End-to-End Framework for Rapid Professional Upskilling
Tam Nguyen, Hung Nguyen, Robert Ogburn
Published: July 15, 2026
cs.AI
By 2030, 59 of every 100 workers will need reskilling or upskilling, yet the average time to close an enterprise skills gap grew from roughly 3 days in 2014 to 36 days in 2018. Most current frameworks accelerate single stages of upskilling programs and generally lack industry validation. We present an end-to-end…
Multi-Expert Routing for Multi-Domain Low-Resource OCR: A Manchu Case Study
Zhan Chen, Jiqiao Ma, Chih-wen Kuo
Published: July 15, 2026
cs.CVcs.AIcs.LG
Historical Manchu OCR must accommodate various visually distinct writing styles, including regular script, running script, and the semi-cursive chancery hand used in palace memorials, despite limited labeled data. We study a multi-expert system that reuses checkpoints from an iterative fine-tuning process as domain…
Can an Old Dog Be Taught New Tricks? Taking LLMs Beyond Sentence Level Translation
Alaina Brandt
Published: July 15, 2026
cs.CL
Automatic translation systems, from CAT tools to MT, overwhelmingly treat translation as a sentence-by-sentence act. This paper asks whether LLMs can be moved beyond that paradigm through whole-document, corpus-informed translation. We present PAT (Pragmatic Auto-Translator), a RAG-based system that pairs…
Early Adoption of Agentic Coding Tools by GitHub Projects
Maliha Noushin Raida, Daqing Hou
Published: July 15, 2026
cs.SEcs.AIcs.CY
Agentic coding tools are increasingly capable of generating and submitting pull requests (PRs) to software projects, introducing new forms of human-agent collaboration in software development. While prior studies have examined PR-level outcomes of agent-generated contributions, less is known about how agentic coding…
Exploiting Graph Structure for Near-Optimal Broadcasting
Rudranarayan Kar, Praneet Kumar Patra, Diya Roy +1 more
Published: July 15, 2026
cs.DS
Telephone broadcasting is a classical model for spreading information in a network. Given a connected graph $G(V,E)$ with source vertex $s$, each informed vertex may inform exactly one uninformed neighbor in every time step. The \textsc{Broadcasting} problem asks whether all vertices can be informed within $t$ steps;…
SPECS: Speciated Evolutionary Circuit Synthesis
Yağız Gençer, Stefan Uhlich, Andrea Bonetti +3 more
Published: July 15, 2026
cs.NE
We propose SPECS, a genetic algorithm for automated analog circuit synthesis with joint topology and sizing optimization. SPECS is inspired by NeuroEvolution of Augmenting Topologies (NEAT), an evolutionary algorithm originally developed to synthesize neural networks. By reformulating the genome representation and…
Improving Wind and Solar Power Prediction with Efficient Wrapper-based Feature Selection: An Empirical Study
Daniel Grillmeyer, Marius Hadry, Michael Stenger +3 more
Published: July 15, 2026
cs.LGcs.AI
With rising global energy demand and growing awareness of climate change and its impacts, the share of renewable energies in the global energy mix continues to grow. Unlike conventional power generation, the output of renewable energy sources cannot be controlled as consistently due to their dependence on environmental…
Transforming Rank: How Architecture Navigates the Spectral Pathologies of Depth
Katie Everett
Published: July 15, 2026
cs.LGcs.AI
We investigate how each component of the Transformer feedforward block architecture design determines how much rank survives across depth at initialization. We reinterpret skip connections and normalization, long understood as controlling magnitude, as mechanisms for preserving gradient rank across depth, since the…
Square-Root Law for Covert Communication with Warden-Favorable Side Information
Hossein Ahmadi, Christian Deppe, Boulat A. Bash +1 more
Published: July 15, 2026
cs.IT
Covert communication enables Alice to transmit to Bob while making the transmission difficult for Willie to detect. We study a scalar Gaussian covert-overlay model in which Alice's low-power covert signal is superimposed on an aggregate public component generated by Alice or other trackable sources. Willie is given all…
Lighthouse RL: Sample-Efficient Circuit Optimization via Strategic Reset Points
Mustafa Emre Gürsoy, Stefan Uhlich, Ryoga Matsuo +6 more
Published: July 15, 2026
cs.LGcs.AR
In this paper, we introduce Lighthouse RL, a sample-efficient reinforcement learning (RL) approach for analog circuit sizing. Traditional methods lack generalization across different performance targets, while standard RL approaches waste resources exploring unpromising regions. Our method addresses these…