pith. sign in

archive

Every paper Pith has read. Search by title, abstract, or pith.

14903 papers in cs.LG · page 5

  1. cs.LG 2026-05-21 reviewed
    Fibonacci ring aggregation outperforms FedAvg in federated learning

    FIRMA: FIbonacci Ring Model Aggregation for Privacy-preserving Federated Learning

    Rachid Hedjam

  2. cs.CV 2026-05-21 reviewed
    Sparse autoencoder links reasoning steps to image masks

    SegCompass: Exploring Interpretable Alignment with Sparse Autoencoders for Enhanced Reasoning Segmentation

    Zhenyu Lu +6

  3. cs.DS 2026-05-21 reviewed
    Timed precursor lifts secretary success above 50 percent

    The Secretary Problem with a Stochastic Precursor

    Franziska Eberle +1

  4. cs.CV 2026-05-21 reviewed
    Causal model matches age changes in spine DXA images

    From Baseline to Follow-Up: Counterfactual Spine DXA Image Synthesis in UK Biobank Using a Causal Hierarchical Variational Autoencoder

    Yilin Zhang +3

  5. cs.LG 2026-05-21 reviewed
    SGD variance grows unbounded along flat directions

    Why SGD is not Brownian Motion: A New Perspective on Stochastic Dynamics

    Igor Ignashin +9

  6. cs.CL 2026-05-21 reviewed
    Moral knowledge retrieval beats extra context for political value detection

    More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts

    V\'ictor Yeste +1

  7. cs.CL 2026-05-21 reviewed
    Moral knowledge beats extra context and model scaling for value detection

    More Context, Larger Models, or Moral Knowledge? A Systematic Study of Schwartz Value Detection in Political Texts

    V\'ictor Yeste +1

  8. cs.LG 2026-05-21 reviewed
    CAME-Grad optimizer lifts radiology reports by 2 percent

    The Double Dilemma in Multi-Task Radiology Report Generation: A Gradient Dynamics Analysis and Solution

    Erjian Zhang +3

  9. cs.LG 2026-05-21 reviewed
    CAME-Grad fixes gradient double dilemma in report generation

    The Double Dilemma in Multi-Task Radiology Report Generation: A Gradient Dynamics Analysis and Solution

    Erjian Zhang +3

  10. cs.LG 2026-05-21 reviewed
    Frozen LLM corrections improve predictions within but not across protocols

    From Residuals to Reasons: LLM-Guided Mechanism Inference from Tabular Data

    Mohammad R. Rezaei +1

  11. cs.LG 2026-05-21 reviewed
    WPO converges linearly to optimum under entropy regularization

    A note on convergence of Wasserstein policy optimization

    David \v{S}i\v{s}ka +1

  12. cs.CR 2026-05-21 reviewed
    Hybrid detector catches unseen network attacks above 98% F1

    UNAD+: An Explainable Hybrid Framework for Unknown Network Attack Detection

    Saif Alzubi +1

  13. cs.LG 2026-05-21 reviewed
    Dual rewards stabilize unsupervised LLM reasoning

    Two is better than one: A Collapse-free Multi-Reward RLIF Training Framework

    Shourov Joarder +4

  14. cs.LG 2026-05-21 reviewed
    Shared program evolution then adaptation beats single-task search

    Evolutionary Multi-Task Optimization for LLM-Guided Program Discovery

    Halil Alperen Gozeten +5

  15. cs.CY 2026-05-21 reviewed
    Healthcare LLM benchmarks fail because of hidden user assumptions

    Healthcare LLM Benchmarks Are Only as Good as Their Explicit Assumptions

    Naveen Raman +4

  16. cs.LG 2026-05-21 reviewed
    Data characteristics drive ML performance in PICU stewardship

    Benchmarking Machine Learning Architectures for Antimicrobial Stewardship in Pediatric ICUs

    Niklas Raehse +2

  17. cs.RO 2026-05-21 reviewed
    Agentic-VLA speeds VLA convergence 2.4x with adaptive rewards

    Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models

    Ruofan Jin +1

  18. cs.CR 2026-05-21 reviewed
    AI Framework Secures Cardless Banking Against Fraud

    Innovations in Cardless Artificial Intelligence Banking: A Comprehensive Framework for Cyber Secure and Fraud Mitigation using Machine Learning Algorithms

    Md Israfeel

  19. cs.LG 2026-05-21 reviewed
    Residual stress learning narrows real-to-sim gap in dynamics

    MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics via Learning Residual Anisotropy

    Jiaxu Wang +7

  20. cs.LG 2026-05-21 reviewed
    Single network generalizes robot control to new factor mixes

    Factored Diffusion Policies:Compositionally Generalized Robot Control with a Single Score Network

    Sayan Mitra +3

  21. cs.LG 2026-05-21 reviewed
    Ensembles add little uncertainty value for graph neural networks

    Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?

    Pedro C. Vieira +2

  22. cs.LG 2026-05-21 reviewed
    Noise prediction loss matches score matching up to constant

    A Tutorial on Diffusion Theory: From Differential Equations to Diffusion Models

    Jiayi Fu +1

  23. cs.CV 2026-05-21 reviewed
    3D reconstruction turns floorplan localization into alignment task

    SceneAligner: 3D-Grounded Floorplan Localization in the Wild

    Junhyeong Cho +2

  24. cs.LG 2026-05-21 reviewed
    Graph of atomic ops boosts LLM agent accuracy and cuts memory 4x

    GraphFlow: A Graph-Based Workflow Management for Efficient LLM-Agent Serving

    Ao Li +5

  25. cs.CL 2026-05-21 reviewed
    Multiple metrics required to judge synthetic data for tool-calling agents

    SynAE: A Framework for Measuring the Quality of Synthetic Data for Tool-Calling Agent Evaluations

    Shuaiqi Wang +3

  26. cs.LG 2026-05-21 reviewed
    Tighter regret bounds let BO stop with optimality guarantees

    Regret-Based $(\epsilon,\delta)$-optimal Stopping Criteria for Bayesian Optimization

    Haowei Wang +2

  27. cs.LG 2026-05-21 reviewed
    Neural flows approximate any operator on function spaces

    Neural Flow Operators can Approximate any Operator: Abstract Frameworks and Universal Approximations

    Shuang Chen +2

  28. cs.LG 2026-05-21 reviewed
    Wavelet-guided neural terrain models reach 66 dB PSNR

    ImplicitTerrainV2: Wavelet-Guided Spatially Adaptive Neural Terrain Representation

    Haoan Feng +2

  29. stat.ML 2026-05-21 reviewed
    Martingale kernel tests replace permutations with normal quantiles

    A Martingale Kernel Independence Test

    Felix Laumann +2

  30. cs.LG 2026-05-21 reviewed
    Filtered sampling lets diverse models train together in GRPO

    F-TIS: Harnessing Diverse Models in Collaborative GRPO

    Nikolay Blagoev +3

  31. cs.LG 2026-05-21 reviewed
    Linear maps predict object embeddings from subject embeddings

    Relational Linear Properties in Language Models: An Empirical Investigation

    Giovanni Valer +3

  32. cs.LG 2026-05-21 reviewed
    RICA defines local disentanglement with a Hessian-Ricci tensor

    Disentanglement Beyond Generative Models with Riemannian ICA

    Edmond Cunningham

    5 Piths
  33. cs.LG 2026-05-21 reviewed
    Multicollinearity inflates AI explanation variance in cybersecurity

    Stabilising Explainability Fragility in Cybersecurity AI: The Impact and Mitigation of Multicollinearity in Public Benchmark Datasets

    Ioannis J. Vourganas +1

  34. cs.GR 2026-05-21 reviewed
    Joint token diffusion policy scales language humanoid control

    SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-based Humanoid Control

    Jingyan Zhang +8

  35. eess.SP 2026-05-21 reviewed
    New EEG dataset benchmarks meditation state and technique classification

    L-FAME: Longitudinal Focused Attention Meditation EEG Dataset and Benchmark

    Angqi Li +5

  36. q-fin.RM 2026-05-21 reviewed
    TabPFN lags behind GLM and XGBoost in insurance pricing tests

    Is TabPFN the Silver Bullet for Insurance Pricing?

    Bruno Deprez +2

  37. cs.LG 2026-05-21 reviewed
    Value functions create straight paths for generative transport

    Generative Modeling by Value-Driven Transport

    Pablo Moreno-Mu\~noz +2

  38. cs.CR 2026-05-21 reviewed
    Benign references anchor clustering to filter variable poisoning

    EnCAgg: Enhanced Clustering Aggregation for Robust Federated Learning against Dynamic Model Poisoning

    Tianyun Zhang +4

  39. cs.AI 2026-05-21 reviewed
    Workflows baked into small model weights cut agent costs 100x

    Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost

    Simon Dennis +3

  40. cs.LG 2026-05-21 reviewed
    Compiler turns programs into exact neural modules

    The Neural Compiler: Program-to-Network Translation for Hybrid Scientific Machine Learning

    Lucas Sheneman

  41. cs.LG 2026-05-21 reviewed
    Flows detect OOD via atypical latent noise

    The Signal in the Noise: OOD Detection Through Goodness-of-Fit Testing in Factorised Latent Spaces

    Philipp Bomatter +2

  42. cs.LG 2026-05-21 reviewed
    Multimodal policies fail differently depending on latent or generative setup

    Understanding Multimodal Failure in Action-Chunking Behavioral Cloning

    Lorenzo Mazza +5

  43. cs.LG 2026-05-21 reviewed
    Transformer represents arithmetic intermediates without causal use

    Represented Is Not Computed: A Causal Test of Candidate Algorithmic Intermediates in a Transformer

    Ishita Darade +1

  44. cs.LG 2026-05-21 reviewed
    Stronger backdoor triggers can raise clean accuracy in high dimensions

    When Stronger Triggers Backfire: A High-Dimensional Theory of Backdoor Attacks

    Donald Flynn +3

    5 Piths
  45. cs.LG 2026-05-21 reviewed
    Random node sampling matches full GNN training on most datasets

    Implicit Regularization of Mini-Batch Training in Graph Neural Networks

    Clement Wang +3

  46. cs.LG 2026-05-21 reviewed
    Blockwise resolvent attention runs entity tracking in O(n to 4/3 d) time

    Structured-Sparse Attention for Entity Tracking with Subquadratic Sequence Complexity

    Hangyue Zhao +3

  47. cs.LG 2026-05-21 reviewed
    WTA bottleneck forces symbolic feature encodings

    Winner-Take-All bottlenecks enforce disentangled symbolic representations in multi-task learning

    Julian Gutheil (1) +2

  48. cs.LG 2026-05-21 reviewed
    Graph tokenization fixes transformer depth for structure recovery

    Lost in Tokenization: Fundamental Trade-offs in Graph Tokenization for Transformers

    Maya Bechler-Speicher +5

    5 Piths
  49. cs.LG 2026-05-21 reviewed
    Point estimators narrow spectra in multimodal inverse problems

    Pointwise Metrics Mislead: An Evaluation Protocol for Multimodal Inverse Problems

    Mads H. Baattrup +6

  50. cs.LG 2026-05-21 reviewed
    Spectral alignment boosts cross-subject F1 in biomedical signals

    BioFormer: Rethinking Cross-Subject Generalization via Spectral Structural Alignment in Biomedical Time-Series

    Guikang Du +5