pith. sign in

archive

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

14903 papers in cs.LG · page 6

  1. quant-ph 2026-05-21 reviewed
    RL cuts ion shuttling operations by 36 percent

    Reinforcement learning for ion shuttling on trapped-ion quantum computers

    Maximilian Schier +6

  2. cs.CV 2026-05-21 reviewed
    Synthetic RAW data yields same low-light detection metrics as real

    Making the Discrete Continuous: Synthetic RAW Augmentations for Fine-Grained Evaluation of Person Detection Performance in Low Light

    Valeria Pais +5

  3. cs.LG 2026-05-21 reviewed
    Rehearsal of stored Q-values cuts forgetting in repeated RL tasks

    Don't Forget the Critic: Value-Based Data Rehearsal for Multi-Cyclic Continual Reinforcement Learning

    Benjamin Poole +3

  4. stat.ML 2026-05-21 reviewed
    Algorithms achieve optimal bidding rates despite feedback shilling

    Do Not Trust The Auctioneer: Learning to Bid in Feedback-Manipulated Auctions

    Luigi Foscari +2

  5. cs.CR 2026-05-21 reviewed
    EM pulses trigger persistent accuracy collapse on NCS2 until reload

    Characterizing the Fault Response of the Intel Neural Compute Stick 2 Under Single-Pulse Electromagnetic Fault Injection

    \v{S}tefan Ku\v{c}er\'ak +2

  6. cs.LG 2026-05-21 reviewed
    AMUSE blends Muon speed with schedule-free stability without learning rate schedules

    AMUSE: Anytime Muon with Stable Gradient Evaluation

    Jueun Kim +5

  7. cs.LG 2026-05-21 reviewed
    Separate physical pools for KV and SSM caches cut OOMs 7.6% and raise throughput up to 13x

    Asymmetric Virtual Memory Paging for Hybrid Mamba-Transformer Inference

    An Xuan Nguyen

  8. cs.CL 2026-05-21 reviewed
    Query-time RL turns noisy memory into accurate evidence

    DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA

    Jianing Yin +1

  9. cs.LG 2026-05-21 reviewed
    MDL granular-ball tree regularizes spectral clustering graphs

    Minimum Description Length based Granular-Ball Tree Regularization for Spectral Clustering

    Zeqiang Xian +3

  10. cs.LG 2026-05-21 reviewed
    Early visual alignment conserved across species but IT rankings diverge

    Cross-Species RSA Reveals Conserved Early Visual Alignment but Divergent Higher-Area Rankings Across Human fMRI and Macaque Electrophysiology

    Nils Leutenegger

  11. cs.LG 2026-05-21 reviewed
    Law of total variance splits wind forecast uncertainty

    A Posterior-Predictive Variance Decomposition for Epistemic and Aleatoric Uncertainty in Wind Power Forecasting

    Yinsong Chen +2

  12. cs.LG 2026-05-21 reviewed
    Hybrid model cuts NEM electricity price forecast errors by 12%

    Hybrid Kolmogorov-Arnold Network and XGBoost Framework for Week-Ahead Price Forecasting in Australia's National Electricity Market

    Houxuan Zhou +4

  13. cs.LG 2026-05-21 reviewed
    Message passing makes GNN-LRP subgraph scores linear in depth

    Efficient Higher-order Subgraph Attribution via Message Passing

    Ping Xiong +4

  14. cs.CL 2026-05-21 reviewed
    Multi-stage pipeline cuts false positives in Indic abusive comment detection

    Multi-Stage Training for Abusive Comment Detection in Indic Languages

    Pranshu Rastogi +3

  15. cs.HC 2026-05-21 reviewed
    Local EEG segment matching raises cross-subject emotion accuracy

    Cross-Subject EEG Emotion Recognition Based on Temporal Asynchronous Alignment Contrastive Learning

    Ying Xie +4

  16. cs.LG 2026-05-21 reviewed
    BERT layer 8 activates on content words over structure

    Towards Explainability of SLMs by investigating Token Level Activation

    Sayantani Ghosh +3

  17. cs.LG 2026-05-21 reviewed
    Bellman alignment selects better source data than transition similarity

    Target-Aligned Bellman Backup for Cross-domain Offline Reinforcement Learning

    Wei Liu +1

  18. cs.LG 2026-05-21 reviewed
    Boundary attacks recover 19% of safety classifier training data

    Boundary-targeted Membership Inference Attacks on Safety Classifiers

    Anthony Hughes +5

  19. cs.LG 2026-05-21 reviewed
    Attack recovers 19% of safety classifier distress data

    Boundary-targeted Membership Inference Attacks on Safety Classifiers

    Anthony Hughes +5

  20. cs.LG 2026-05-21 reviewed
    Attention sink pruning accelerates Vision Transformers by 48%

    ASAP: Attention Sink Anchored Pruning

    Jaehyuk Lee +3

  21. cs.LG 2026-05-21 reviewed
    Adversarial scaling reveals LLM code weaknesses

    VeriScale: Adversarial Test-Suite Scaling for Verifiable Code Generation

    Yifan Bai +9

  22. cs.CR 2026-05-21 reviewed
    TimeGuard boosts backdoor resistance in time series forecasts by 1.96x

    TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting

    Quang Duc Nguyen +4

  23. cs.CL 2026-05-21 reviewed
    LLMs learn to plan transit routes from records alone

    TransitLM: A Large-Scale Dataset and Benchmark for Map-Free Transit Route Generation

    Hanyu Guo +5

  24. cs.LG 2026-05-21 reviewed
    Selective neuron fusion trades ensemble accuracy for lower cost

    Partial Fusion of Neural Networks: Efficient Tradeoffs Between Ensembles and Weight Aggregation

    Fabian Morelli +1

  25. stat.ML 2026-05-21 reviewed
    Regular graphs make ASE and LSE subspaces identical

    The ASE-LSE Disagreement Landscape: An End-to-End Characterisation of Extremes and Structural Drivers

    Minh Triet Pham +1

  26. cs.LG 2026-05-21 reviewed
    Boundary layers drive one-third power-law error decay in online softmax training

    A Boundary-Layer Mechanism for One-Third Scaling in Online Softmax Classification

    Marcel K\"uhn +2

  27. cs.LG 2026-05-21 reviewed
    Flow matching reconstructs cell trajectories from snapshots

    From Snapshots to Trajectories: Learning Single-Cell Gene Expression Dynamics via Conditional Flow Matching

    Siyu Pu +9

  28. cs.LG 2026-05-21 reviewed
    Generative solver enforces conservation laws during sampling

    Physics-Informed Generative Solver: Bridging Data-Driven Priors and Conservation Laws for Stable Spatiotemporal Field Reconstruction

    Ziyuan Zhu +12

  29. cs.LG 2026-05-21 reviewed
    Learned causal order improves tabular predictions after interventions

    Learning Causal Orderings for In-Context Tabular Prediction

    Sascha Xu +2

  30. cs.LG 2026-05-21 reviewed
    Off-log map turns fMRI correlations into standard statistics

    Riemannian geometry meets fMRI: the advantages of modeling correlation manifolds and eigenvector subspaces

    Mario Severino +3

  31. cs.LG 2026-05-21 reviewed
    Scaling sepsis AI replicas to CPU threads halves detection latency

    SepsisAI Orchestrator: A Containerized and Scalable Platform for Deploying AI Models and Real-Time Monitoring in Early Sepsis Detection

    Santiago Ospitia +2

  32. cs.LG 2026-05-21 reviewed
    Chebyshev policies solve Mountain Car optimally with 277x fewer parameters

    Chebyshev Policies and the Mountain Car Problem: Reinforcement Learning for Low-Dimensional Control Tasks

    Stefan Huber +3

  33. cs.AI 2026-05-21 reviewed
    Benchmark compares 12 pipelines for knowledge graph integration

    Evaluation of Pipelines for Data Integration into Knowledge Graphs

    Marvin Hofer +1

  34. cs.AI 2026-05-21 reviewed
    Benchmarks reveal when AI coordination improves scientific inference

    Cross-domain benchmarks reveal when coordinated AI agents improve scientific inference from partial evidence

    Fiona Y. Wong +1

  35. cs.LG 2026-05-21 reviewed
    Heavy-tailed spectra set per-layer rates to speed LLM training 1.5x

    One LR Doesn't Fit All: Heavy-Tail Guided Layerwise Learning Rates for LLMs

    Di He +4

  36. cs.LG 2026-05-21 reviewed
    Decomposition restores long-term fairness despite selective labels

    Long-term Fairness with Selective Labels

    Giovani Valdrighi +2

  37. cs.LG 2026-05-21 reviewed
    EmoTrack cuts depression prediction error 13.5% on single sessions

    EmoTrack: Robust Depression Tracking from Counseling Transcripts across Session Regimes

    Zhaomin Wu +2

  38. cs.LG 2026-05-21 reviewed
    Adaptive allocation of noisy kernel entries improves SVM accuracy

    Adaptive Measurement Allocation for Learning Kernelized SVMs Under Noisy Observations

    Artur Miroszewski

  39. cs.LG 2026-05-21 reviewed
    Probe set partitions flag atypical federated clients

    Detecting Atypical Clients in Federated Learning via Representation-Level Divergence

    Cristian P\'erez-Corral +4

  40. cs.LG 2026-05-21 reviewed
    Adaptive distillation preserves exploration for better LLM math scores

    Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning

    Hongbin Zhang +6

  41. cs.SD 2026-05-21 reviewed
    Audio denoiser infers scene to keep relevant sounds

    Automatic Contextual Audio Denoising

    Diep Luong +3

  42. cs.LG 2026-05-21 reviewed
    Evidence hierarchy lifts Bayesian threat classification to 95%

    An Evidence Hierarchy for Bayesian Object Classification via OSINT-Aided Heterogeneous Sensor Fusion

    Jan Nausner +1

  43. cs.LG 2026-05-21 reviewed
    Rewriting equivalents at test time stabilizes LLM theorem proving

    What are the Right Symmetries for Formal Theorem Proving?

    Krzysztof Olejniczak +5

  44. cs.LG 2026-05-21 reviewed
    Physical decompositions boost climate emulator OOD performance

    No Epoch Like the Present: Robust Climate Emulation Requires Out-of-Distribution Generalisation

    Bradley Stanley-Clamp +3

  45. cs.LG 2026-05-21 reviewed
    AI recommender lifts Cox fall-risk model C-index from 0.805 to 0.815

    Explainable AI for Data-Driven Design of High-Dimensional Predictive Studies

    Junyu Yan +6

  46. cs.LG 2026-05-21 reviewed
    Perturbations regulate decorrelation rates in Lorenz '96 ensembles

    Decomposing Ensemble Spread in Lorenz '96 With Learned Stochastic Parameterizations

    Birgit K\"uhbacher +2

  47. cs.CR 2026-05-21 reviewed
    Quadratic ReLU replacement keeps decisions intact for FHE inference

    Decision-Aware Quadratic ReLU Replacement for HE-Friendly Inference

    Rui Li +2

  48. cs.CR 2026-05-21 reviewed
    Quadratic ReLU replacement preserves calibration decisions

    Decision-Aware Quadratic ReLU Replacement for HE-Friendly Inference

    Rui Li +2

  49. cs.LG 2026-05-21 reviewed
    KAN neural ODE recovers exact symbolic equations for holomorphic fractals

    Holomorphic Neural ODEs with Kolmogorov-Arnold Networks for Interpretable Discovery of Complex Dynamics

    Bhaskar Ranjan Karn +1

  50. cs.LG 2026-05-21 reviewed
    Transformer output sequences grow linearly with prompt length

    How Many Different Outputs Can a Transformer Generate?

    Maxime Meyer +3