pith. sign in

archive

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

14903 papers in cs.LG · page 14

  1. cs.LG 2026-05-19 reviewed
    Tighter quadratic bounds cut conservatism in neural net reachability

    Quadratic Characterizations for Reachability Analysis of Neural Networks

    Elias Khalife +2

  2. cs.CV 2026-05-19 reviewed
    A single predictor transfers oracle hyperparameter labels from variational denoisers to…

    Oracle Supervision Transfers for Hyperparameter Prediction in Model-Based Image Denoising

    Jianmin Liao +2

  3. cs.LG 2026-05-19 reviewed
    Trained reflectors improve language agents on new tasks

    Training Language Agents to Learn from Experience

    Yuval Shalev +2

  4. cs.SE 2026-05-19 reviewed
    Code gen picks winner by clustering behaviors on auto-generated inputs

    Code Generation by Differential Test Time Scaling

    Yifeng He +4

  5. cs.LG 2026-05-19 reviewed
    Classifier uncertainty narrows conformal intervals by 39% for confident cases

    CASCADE Conformal Prediction: Uncertainty-Adaptive Prediction Intervals for Two-Stage Clinical Decision Support

    Ricardo Diaz-Rincon +3

  6. cs.LG 2026-05-19 reviewed
    Spectral memory branch lifts DP-SGD accuracy on CIFAR

    SMA-DP: Spectral Memory-Aware Differential Privacy for Deep Learning

    Mohammad Partohaghighi +1

  7. cs.LG 2026-05-19 reviewed
    Linear probes on frozen LLMs forecast time series without supervision

    LLM Pretraining Shapes a Generalizable Manifold: Insights into Cross-Modal Transfer to Time Series

    Alexis Roger +6

  8. cs.CV 2026-05-19 reviewed
    VLMs rearrange visible objects at 53-97% but fail occlusion at 6-45%

    Do Vision--Language Models Understand 3D Scenes or Just Catalogue Objects?

    Animesh Maheshwari +2

  9. cs.LG 2026-05-19 reviewed
    Weight decay separates memorization

    Weight Decay Regimes in Grokking Transformers: Cheap Online Diagnostics

    Lucky Verma

  10. cs.LG 2026-05-19 reviewed
    Tensor algebra recovers angular-momentum rules from molecules alone

    Group-Algebraic Tensors: Provably-optimal Equivariant Learning and Physical Symmetry Discovery

    Paulina Hoyos +7

  11. cs.LG 2026-05-19 reviewed
    Users beat AI by fixing its systematic errors

    Can Conversational XAI Improve User Performance? An Experimental Study

    Sven Kruschel +4

  12. cs.AI 2026-05-19 reviewed
    Routing weights produce hierarchical attributions at zero cost

    BOHM: Zero-Cost Hierarchical Attribution for Compound AI Systems

    Joss Armstrong

  13. stat.ML 2026-05-19 reviewed
    Contradiction graph decides VC dimension threshold for any m

    Contradiction Graphs Determine VC Dimension

    Jesse Campbell +2

    5 Piths
  14. cs.LG 2026-05-19 reviewed
    Model update paths yield better uncertainty than final probabilities

    Reading Calibrated Uncertainty from Language Model Trajectories

    Aliai Eusebi +5

  15. cs.LG 2026-05-19 reviewed
    13 MB adapter beats larger cache translators for LLMs

    Latent Cache Flow: Model-to-Model Communication Without Text

    Maximillian Rossi +2

  16. cs.LG 2026-05-19 reviewed
    MLLMs infer fracture planes with Miller indices and reject invalid cases

    Miller-Index-Based Latent Crystallographic Fracture Plane Reasoning and generation with Vision-Language Models

    Qinwu Xu +2

  17. cs.LG 2026-05-19 reviewed
    Supervised LDA boosts separability to 0.197 in plant phenomics data

    Supervised Latent Restructuring for Small-Data Quantum Learning in Plant Phenomics

    Alakananda Mitra +3

  18. cs.LG 2026-05-19 reviewed
    Spectral basis in LLMs allows online merging of preference policies

    Spectral Souping: A Unified Framework for Online Preference Alignment

    Yinlam Chow +6

  19. cs.LG 2026-05-19 reviewed
    MXFP4 error splits into three parts for targeted RL fixes

    Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor

    Xiaocan Li +2

  20. cs.LG 2026-05-19 reviewed
    MXFP4 error splits into three parts each fixing a different RL failure

    Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor

    Xiaocan Li +2

  21. stat.AP 2026-05-19 reviewed
    Negative random effects group shows 400x larger causal effects

    Understanding Deterioration Random Effects for Causal Discovery in Infrastructure Management

    Takato Yasuno

  22. cs.LG 2026-05-19 reviewed
    Scoring functions recover causal graphs with latent variables

    Score-Based Causal Discovery of Latent Variable Causal Models

    Ignavier Ng +5

  23. cs.CR 2026-05-19 reviewed
    Tor network maintains fixed nine-dimensional structure over 67 days

    Latent Geometry as a Structural Monitor: Eigenspace Alignment for Anomaly Detection in Anonymity Networks

    Vaibhav Chhabra

  24. cs.CV 2026-05-19 reviewed
    Bigger 3D models trained on 50M driving scenes top Waymo leaderboard

    STELLAR: Scaling 3D Perception Large Models for Autonomous Driving

    Yingwei Li +15

  25. cs.LG 2026-05-19 reviewed
    Integral operators gain from longer windows in fMRI tasks

    Nonlocal operator learning for fMRI encoding and decoding tasks

    Andreas Kramer +3

  26. cs.CL 2026-05-19 reviewed
    DEL raises LLM number prediction accuracy on math benchmarks

    DEL: Digit Entropy Loss for Numerical Learning of Large Language Models

    Zhaohui Zheng +5

  27. cs.LG 2026-05-19 reviewed
    Per-sample temperatures make teacher soft labels consistent

    Consistently Informative Soft-Label Temperature for Knowledge Distillation

    Hoang-Chau Luong +3

  28. cs.RO 2026-05-19 reviewed
    Nudges to learnable states yield 7x larger skill gains than standard AI sharing

    Proximal State Nudging: Reducing Skill Atrophy from AI Assistance

    Megha Srivastava +8

  29. cs.LG 2026-05-19 reviewed
    Symmetrized cross-entropy produces unique convex multi-class unhinged loss

    Symmetrization of Loss Functions for Robust Training of Neural Networks in the Presence of Noisy Labels

    Alexandre Lemire Paquin +2

  30. stat.ML 2026-05-19 reviewed
    Importance sampling corrects ILA to recover true posteriors

    Corrected Integrated Laplace Approximation for Bayesian Inference in Latent Gaussian Models

    Jinlin Lai +2

  31. cs.LG 2026-05-19 reviewed
    Krylov approximation unlearns data 48x faster than retraining

    Causal Unlearning in Collaborative Optimization: Exact and Approximate Influence Reversal under Adversarial Contributions

    Ali Mahdavi +3

  32. cs.LG 2026-05-19 reviewed
    EEG microstates from one clustering step outperform traditional features on multiple tasks

    Atoms of Thought: Universal EEG Representation Learning with Microstates

    Xinyang Tian +5

  33. cs.CV 2026-05-19 reviewed
    AUDITS benchmark tests detectors on 530K manipulated images

    Multi-axis Analysis of Image Manipulation Localization

    Keanu Nichols +5

  34. cs.AI 2026-05-19 reviewed
    ML ensemble forecasts haor floods 72 hours ahead with 89.6% accuracy

    HaorFloodAlert: Deseasonalized ML Ensemble for 72-Hour Flood Prediction in Bangladesh Haor Wetlands

    Salma Hoque Talukdar Koli +3

  35. cs.CV 2026-05-19 reviewed
    Prototype layer matches ResNet accuracy on composite X-ray defects

    Interpretable Computer Vision for Defect Detection in X-ray Tomography of Aerospace SiC/SiC Composites

    Antonio Pe\~na Corredor +4

  36. cs.LG 2026-05-19 reviewed
    Gating ensemble harvests reliable negatives for fraud models

    SAGE: Scalable Automatic Gating Ensemble for Confident Negative Harvesting in Fraud Detection

    Sudheer Tubati +1

  37. cs.LG 2026-05-19 reviewed
    Graph topology decides when models collapse

    When Does Model Collapse Occur in Structured Interactive Learning?

    Yuchen Wu +2

  38. stat.ML 2026-05-19 reviewed
    Post-hoc calibration sharpens GP lower tails for optimization

    Goal-Oriented Lower-Tail Calibration of Gaussian Processes for Bayesian Optimization

    Aur\'elien Pion +1

  39. cs.LG 2026-05-19 reviewed
    Repeating smaller datasets speeds up training

    Less Data, Faster Training: repeating smaller datasets speeds up learning via sampling biases

    Jingwen Liu +3

  40. cs.LG 2026-05-19 reviewed
    Frozen encoder beats task-specific models on four trajectory tasks

    TrajTok: Adaptive Spatial Tokenization for Trajectory Representation Learning

    Zhen Xiong +2

  41. physics.geo-ph 2026-05-19 reviewed
    Streaming abstraction unifies DAS interactive analysis and production

    FiLark: a streaming-first software framework for end-to-end exploration, annotation, and algorithm integration in distributed acoustic sensing

    Jintao Li +3

  42. q-bio.NC 2026-05-19 reviewed
    Recovery profiles reveal brain dimensions models miss despite high accuracy

    Beyond Prediction Accuracy: Target-Space Recovery Profiles for Evaluating Model-Brain Alignment

    Ken Nakamura +4

  43. stat.ML 2026-05-19 reviewed
    Grid sketch achieves optimal Wasserstein runtime for smooth laws

    Optimizing Computational-Statistical Runtime for Wasserstein Distance Estimation

    Peter Matthew Jacobs +1

  44. cs.LG 2026-05-19 reviewed
    Single recipe scales time series models from 4M to 2.5B parameters

    Toto 2.0: Time Series Forecasting Enters the Scaling Era

    Emaad Khwaja +12

  45. eess.SY 2026-05-19 reviewed
    Single trajectory yields neural k-inductive barriers for unknown dynamics

    k-Inductive Neural Barrier Certificates for Unknown Nonlinear Dynamics

    Ben Wooding +3

  46. cs.LG 2026-05-19 reviewed
    AutoML for health risk prediction reduces to few key components

    A Reproducible Log-Driven AutoML Framework for Interpretable Pipeline Optimization in Healthcare Risk Prediction

    Rui Huang +1

  47. cs.LG 2026-05-19 reviewed
    No fixed marginal covariance is safe for all geometries in JEPAs

    Beyond Isotropy in JEPAs: Hamiltonian Geometry and Symplectic Prediction

    Robert Jenkinson Alvarez

  48. cs.LG 2026-05-19 reviewed
    Optimal representation size shrinks with abundant pretraining data

    Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing

    Valentina Njaradi +4

  49. cs.LG 2026-05-19 reviewed
    Pruning plus retrieval yields up to 5.41× speculative decoding speedups

    Draft Less, Retrieve More: Hybrid Tree Construction for Speculative Decoding

    Yuhao Shen +11

  50. cs.LG 2026-05-19 reviewed
    Coupled graph model boosts damage localization in unseen plate areas

    WaveGraphNet: Physics-Consistent Guided-Wave Damage Localization through Coupled Inverse-Forward Graph Learning

    Vinay Sharma +2