Papers

Find your next good read.

Search all papers in this category, newest first.

About these papers

The catalogue includes arXiv metadata from three computer science categories. Full-text assessment is limited to CC BY, CC BY-SA, and CC0 papers. Methodology and coverage

Machine learning

20+ papers · Newest first

  • Submitted

    General Quantification of Covariate and Concept Shifts

    Hongbo Chen, Li Charlie Xia

    Abstract excerpt: Generalization under distribution shift remains a core challenge in modern machine learning, yet existing learning bound theory is limited to narrow, idealized settings and is non-estimable from samples. In this paper, we bridge the gap between theory and practical applications. We first show that existing definition of concept shift breaks when the source…

    Read paper Sign in to savearXiv:2609.11918v1
  • Submitted

    Data Scarcity and Model Sparsity: Mixtures-of-Experts Overfit More to Repeated Data

    Atindra Jha, Margaret Li, Jure Leskovec, et al.

    Abstract excerpt: As the supply of human-written text is exhausted, it has become standard practice to repeat language model training data. Prior work has studied data repetition for densely activated Transformers, but the effects of data repetition remains largely unexplored for recently dominant sparse architectures such as Mixture-of-Experts (MoE), despite their increased…

    Read paper Sign in to savearXiv:2609.11917v1
  • Submitted

    Generative Marketing Mix Modeling: A Causal Inference Framework Linking GEO and GEM to Business Impact

    Masahiro Kato, Daiki Honma, Taka Kato

    Abstract excerpt: Generative artificial intelligence changes how firms reach customers, but standard marketing data do not record how often users see and notice a firm's name in generated answers. We develop Generative Marketing Mix Modeling (GMMM) to estimate the causal effects of Generative Engine Optimization (GEO) and Generative Engine Marketing (GEM). For GEO, GMMM comb…

    Read paper Sign in to savearXiv:2609.11915v1
  • Submitted

    From Protocols to Evidence: Bounded Claims for AI in Service of the Common Good

    Nitesh V. Chawla, Paulo Benanti

    Abstract excerpt: Artificial Intelligence does more than create a governance problem. It can also reveal where institutions have already failed to provide responsiveness, belonging, care, and accountability. Once deployed, AI becomes an intervention in those conditions. It can repair, compound, substitute for, or conceal the failures it encounters. Responsible AI must theref…

    Read paper Sign in to savearXiv:2609.11910v1
  • Submitted

    TART: A Modular Tool for Technique-Aware Audio-to-Tablature Guitar Transcription

    Akshaj Gupta, Hwi Joo Park, Andrea Guzman, et al.

    Abstract excerpt: Automatic Music Transcription (AMT) for guitar remains limited by three challenges: existing systems often fail to capture expressive techniques such as slides, bends, and percussive hits; they often assign notes to incorrect string-fret combinations; and they are typically trained on clean recordings, limiting their generalization to noisy real-world audio…

    Read paper Sign in to savearXiv:2609.11904v1
  • Submitted

    CausalArena: Benchmarking Causal Discovery in the Foundation Model Era

    Zi-Rong Li, Si-Yang Liu, Tian-Zuo Wang, et al.

    Abstract excerpt: Causal discovery aims to uncover causal structures from data and is fundamental to scientific reasoning and intervention-based decision making. Its evaluation relies heavily on structural causal models (SCMs), which specify a causal graph together with the mechanisms that generate data, yet existing studies differ substantially in graph families, mechanisms…

    Read paper Sign in to savearXiv:2609.11897v1
  • Submitted

    3D Point Splatting for mmWave Radar Novel View Synthesis

    Adnan Armouti, Yixuan Gao, Rajalakshmi Nandakumar

    Abstract excerpt: Solving novel view synthesis (NVS) for millimeter-wave (mmWave) radar requires a renderer that is physically faithful, complex-valued, and multi-viewpoint-tractable. No prior method achieves these three properties simultaneously. Differentiable Monte Carlo (MC) ray tracers implement the radar forward model directly with explicit material modeling and comple…

    Read paper Sign in to savearXiv:2609.11894v1
  • Submitted

    CoRA-NAS: Coarse Ranking and Anchor-Residual Refinement for Neural Architecture Search

    Yifan Yang, Zhaoyan Wang, Zheng Gao, et al.

    Abstract excerpt: Zero-cost proxies rank architectures cheaply, but their reliability varies across search spaces. We introduce CoRA-NAS (COarse Ranking + Anchor-residual), a two-stage framework combining a static ranking prior with low-cost learning-curve refinement. CoRA-Rank aggregates capacity and structure-at-initialization proxies through an equal-weight log-rank conse…

    Read paper Sign in to savearXiv:2609.11884v1
  • Submitted

    Domain-Specific Hallucination Detection in Large Language Models

    Varun Teja Chundru, Debasmita Biswas

    Abstract excerpt: Large language models generate fluent text that can contain unfaithful claims -- a phenomenon known as hallucination. We present a multi-signal detection pipeline combining fine-tuned DeBERTa-v3 classification, Monte Carlo (MC) Dropout uncertainty quantification, and temperature-scaled calibration for response-level hallucination detection. Evaluated on the…

    Read paper Sign in to savearXiv:2609.11878v1
  • Submitted

    The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement

    Yi Duan, Ying Liu, Zirui Tang, et al.

    Abstract excerpt: Recursive self-improvement (RSI) enables AI systems to turn experience and feedback into persistent changes that improve both their capabilities and the process of future improvement. We first use the Headroom-Closed Index (HCI) to reveal the problems of existing LLMs, then introduce the RSI concept and its development roadmap: from improvement-execution au…

    Read paper Sign in to savearXiv:2609.11873v1
  • Submitted

    Evaluating Time-Series Foundation Models and Multimodal Dietary Context for CGM Forecasting

    Bowen Zhang, Hsiu-Wen Cheng, Hongyu Yang, et al.

    Abstract excerpt: Continuous glucose monitoring (CGM) provides high-frequency measurements of glucose dynamics and enables short-term glucose forecasting for diabetes management. Although time-series foundation models have shown strong general forecasting ability, their effectiveness for CGM prediction and the added value of multimodal dietary context remain unclear. We cond…

    Read paper Sign in to savearXiv:2609.11872v1
  • Submitted

    AdamX: Cosine similarity meets gradient descent

    Francisco Caldas, Ruben Belo, Cláudia Soares

    Abstract excerpt: We introduce AdamX, a first-order optimizer that incorporates cosine similarity as an adaptive mechanism for controlling update magnitudes. The proposed method is scalable, model-agnostic, and straightforward to integrate into existing training pipelines. We further introduce a variance rectification scheme that promotes smoother optimization during the ear…

    Read paper Sign in to savearXiv:2609.11867v1
  • Submitted

    Explainability Assistant: A Conversational XAI Interface for Interpreting Energy Consumption Models

    Rodion Krjutškov, Eduard Barbu, Nikos Sakkas, et al.

    Abstract excerpt: Energy consumption forecasting relies on increasingly complex machine learning (ML) models, such as Genetic Programming-based symbolic regressors, whose predictions can be difficult for facility managers and building operators to interpret. Explainable Artificial Intelligence (XAI) techniques address this opacity, but traditional XAI dashboards require subs…

    Read paper Sign in to savearXiv:2609.11860v1
  • Submitted

    Model-Aware Schedules Improve Generation via Fiberwise Optimal Transport

    Luyi Jia, Boyan Zhang, Yilun Liu, et al.

    Abstract excerpt: Diffusion and flow-matching schedules control the signal and noise coefficients that mix data and noise along affine probability paths. Minimizing a kinetic action defined on coefficient paths, motivated by optimal transport, helps explain strong baselines but remains model-agnostic and ignores prediction error. Here we introduce a model-aware schedule cons…

    Read paper Sign in to savearXiv:2609.11842v1
  • Submitted

    Near-Optimal Reinforcement Learning with Multi-Step Transition Lookahead

    Corentin Pla, Hugo Richard, Marc Abeille, et al.

    Abstract excerpt: We study reinforcement learning (RL) with transition look-ahead, where the agent may observe which states would be visited upon playing any sequence of $\ell$ actions before deciding its course of action. Although look-ahead can substantially improve achievable performance, it is known that optimal planning with multi-step transition look-ahead is NP-hard,…

    Read paper Sign in to savearXiv:2609.11807v1
  • Submitted

    Logit Refiner: Improving Visual Autoregressive Models via Intra-Scale Dependency Modeling

    Meimingwei Li, Stefan Andreas Baumann, Felix Krause, et al.

    Abstract excerpt: Visual Autoregressive Models (VAR) generate images through next-scale prediction, producing all tokens within each scale in parallel. We show that this parallel decoding constitutes a mean-field-style approximation that discards spatial dependencies among same-scale tokens, causing locally incoherent samples regardless of backbone capacity -- a limitation o…

    Read paper Sign in to savearXiv:2609.11804v1
  • Submitted

    Thinking with Looped Flows

    Ayhan Suleymanzade, Chanhyuk Lee, Floor Eijkelboom, et al.

    Abstract excerpt: Humans and machines often solve harder problems by spending more time on computation. In deep learning, looped models implement this idea during inference by recurrently updating a hidden state. In practice, however, their training backpropagates through only one or a few updates, making it hard to train early updates to support future ones. We propose loop…

    Read paper Sign in to savearXiv:2609.11801v1
  • Submitted

    Dynamic language model representations for multi-objective reaction optimisation

    Joshua W. Sin, David Ming Segura, Bojana Ranković, et al.

    Abstract excerpt: Optimising chemical reactions across multiple objectives, such as yield, selectivity, and safety, is central to chemical synthesis, and model-driven approaches depend critically on how reaction components are represented. Established featurisations are either chemically uninformative, as with one-hot encodings, or, as with molecular descriptors, do not read…

    Read paper Sign in to savearXiv:2609.11790v1
  • Submitted

    Predicting Privacy Leakage from Weight Spectral Density

    Richard J. Preen, Jim Smith

    Abstract excerpt: Membership inference attacks (MIAs) are widely used to audit the privacy disclosure risk of machine learning models, however current state-of-the-art attacks require training computationally expensive shadow models, making large-scale privacy evaluation impractical. In this work, we investigate whether inexpensive spectral metrics derived from the heavy-tai…

    Read paper Sign in to savearXiv:2609.11780v1
  • Submitted

    Differentially Private EEG Feature Anonymization: A Privacy-Utility Case Study in Clinical Neurophysiology

    Noman Sadiq, Mohsen Toorani

    Abstract excerpt: Clinical electroencephalography (EEG) data are valuable for healthcare research and for developing artificial intelligence (AI)-based clinical decision-support systems, but EEG recordings and derived features may contain sensitive patient-specific information. This creates privacy risks when data are reused, analyzed, or shared across clinical and research…

    Read paper Sign in to savearXiv:2609.11777v1