pith. sign in

archive

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

14903 papers in cs.LG · page 15

  1. cs.LG 2026-05-19 reviewed
    Per-instance shapelets beat population averages on time-series tasks

    INSHAPE: Instance-Level Shapelets for Interpretable Time-Series Classification

    Seongjun Lee +2

  2. cs.NE 2026-05-19 reviewed
    Evolutionary code agents gain by recycling deleted lines

    What Do Evolutionary Coding Agents Evolve?

    Nico Pelleriti +6

  3. cs.CV 2026-05-19 reviewed
    Adaptive Manifold Guidance conserves probability during strong guidance

    Probability-Conserving Flow Guidance

    Parsa Esmati +4

  4. cs.LG 2026-05-19 reviewed
    Linear representation hypothesis enables efficient distillation to DP-aligned networks

    Towards Distillation Guarantees under Algorithmic Alignment for Combinatorial Optimization

    Thien Le +1

  5. cs.LG 2026-05-19 reviewed
    This paper proposes the Clipped Linear Lottery

    Smooth Partial Lotteries for Stable Randomized Selection

    Alexander Goldberg +2

  6. cs.LG 2026-05-19 reviewed
    Clipped Linear Lottery stabilizes randomized picks with near-optimal regret

    Smooth Partial Lotteries for Stable Randomized Selection

    Alexander Goldberg +2

  7. stat.ML 2026-05-19 reviewed
    Soft-log transform lets flow matching handle heavy tails

    Tail Annealing for Heavy-Tailed Flow Matching

    Jean Pachebat

  8. cs.CV 2026-05-19 reviewed
    SDM improves adversarial attack performance and efficiency by reconstructing the…

    SDM: A Powerful Tool for Evaluating Model Robustness

    Xinlei Liu +5

  9. cs.LG 2026-05-19 reviewed
    Active sampling achieves sqrt(n/T) ||p||_{2/3} regret bound

    Active Context Selection Improves Simple Regret in Contextual Bandits

    Mohammad Shahverdikondori +2

  10. cs.LG 2026-05-19 reviewed
    Critic disagreement guides reward poisoning in RIS networks

    When Critics Disagree: Adaptive Reward Poisoning Attacks in RIS-Aided Wireless Control System

    Deemah H. Tashman +1

  11. cs.LG 2026-05-19 reviewed
    Diffusion model plans ride-hailing subsidies from past data alone

    D$^3$-Subsidy: Online and Sequential Driver Subsidy Decision-Making for Large-Scale Ride-Hailing Market

    Taijie Chen +8

  12. cs.LG 2026-05-19 reviewed
    Diffusion planner lifts rides and GMV in ride-hailing under caps

    D$^3$-Subsidy: Online and Sequential Driver Subsidy Decision-Making for Large-Scale Ride-Hailing Market

    Taijie Chen +8

  13. cs.LG 2026-05-19 reviewed
    Diffusion model raises ride-hailing rides and GMV under subsidy caps

    D$^3$-Subsidy: Online and Sequential Driver Subsidy Decision-Making for Large-Scale Ride-Hailing Market

    Taijie Chen +8

  14. cs.LG 2026-05-19 reviewed
    Mixture of experts catches text-camouflaged fraud in graphs

    CAMERA: Adapting to Semantic Camouflage in Unsupervised Text-Attributed Graph Fraud Detection

    Junjun Pan +5

  15. cs.LG 2026-05-19 reviewed
    Pointwise rejection costs replace global budgets in partial OT

    Take It or Leave It: Intent-Controlled Partial Optimal Transport

    Salil Parth Tripathi +4

  16. cs.LG 2026-05-19 reviewed
    Diffusion emulators make optimal particle filters training-free

    Training-Free Bayesian Filtering with Generative Emulators

    Thomas Savary +2

  17. cs.LG 2026-05-19 reviewed
    Two antagonistic Bayesian processes set the optimal learning rate

    Training Neural Networks with Optimal Double-Bayesian Learning

    Vy Bui +4

  18. cs.LG 2026-05-19 reviewed
    Loss-adaptive rates cut forgetting by 93% in fine-tuning

    Fine-Tuning Without Forgetting via Loss-Adaptive Learning Rates

    Parjanya Prajakta Prashant +3

  19. cs.LG 2026-05-19 reviewed
    LLM benchmarks can be made unlearnable to stop contamination

    LLM Benchmark Datasets Should Be Contamination-Resistant

    Ali Al-Lawati +3

  20. eess.IV 2026-05-19 reviewed
    CryoNet maps debris-covered glaciers at 90 percent IoU

    CryoNet: A Deep Learning Framework for Multi-Modal Debris-Covered Glacier Mapping. A Case Study of the Poiqu Basin, Central Himalaya

    Farzaneh Barzegar +3

  21. cs.RO 2026-05-19 reviewed
    Four photodiodes replace cameras for robot odometry

    Minimalist Visual Inertial Odometry

    Francesco Pasti +3

  22. cs.RO 2026-05-19 reviewed
    Visual encoder spatial detail fix unlocks precise robot tasks

    Beyond Binary Success: A Diagnostic Meta-Evaluation Framework for Fine-Grained Manipulation

    He-Yang Xu +7

  23. cs.LG 2026-05-19 reviewed
    Lookahead training improves neural routing policies

    Learning with Foresight: Enhancing Neural Routing Policy via Multi-Node Lookahead Prediction

    Xia Jiang +3

  24. cs.LG 2026-05-19 reviewed
    Block-sphere quantizer lowers MSE and inner-product error

    Block-Sphere Vector Quantization

    Heesang Ann +2

  25. cs.LG 2026-05-19 reviewed
    Neighbors catch backdoors by sharing and comparing triggers

    Your Neighbors Know: Leveraging Local Neighborhoods for Backdoor Detection in Decentralized Learning

    Sayan Biswas +9

  26. cs.LG 2026-05-19 reviewed
    Entropy change-point detection spots fluent LLM jailbreaks

    Detecting Fluent Optimization-Based Adversarial Prompts via Sequential Entropy Changes

    Mohammed Alshaalan +1

  27. cs.LG 2026-05-19 reviewed
    Local plasticity separates mixed signals by maximizing predictive entropy

    Normative Networks for Source Separation via Local Plasticity and Dendritic Computation

    Bariscan Bozkurt +3

  28. cs.LG 2026-05-19 reviewed
    Local rules recover sources from noisy mixtures

    Normative Networks for Source Separation via Local Plasticity and Dendritic Computation

    Bariscan Bozkurt +3

  29. cs.LG 2026-05-19 reviewed
    Rank-2 neural generators reach any orthonormal basis from Fourier

    Learning Orthonormal Bases for Function Spaces

    Hamidreza Kamkari +2

  30. cs.CV 2026-05-19 reviewed
    VLMs and agents miss over half the score on wild road damage

    WildRoadBench: A Wild Aerial Road-Damage Grounding Benchmark for Vision-Language Models and Autonomous Agents

    Bingnan Liu +9

  31. cs.LG 2026-05-19 reviewed
    Non-negative weights make true DAG the unique minimizer

    Exploiting Non-Negativity in DAG Structure Learning

    Samuel Rey +2

  32. cs.LG 2026-05-19 reviewed
    Position-dependent attention fixes constant risk on shifted reasoning

    A Measure-Theoretic Analysis of Reasoning: Structural Generalization and Approximation Limits

    Yuyang Zhang +3

  33. stat.ME 2026-05-19 reviewed
    Gated estimator cuts manifold density error by 22-36%

    Variance-Reduced Manifold Sampling via Polynomial-Maximization Density Estimation

    Serhii Zabolotnii

  34. cs.AI 2026-05-19 reviewed
    Context map cache raises LLM agent accuracy 6-34% on recurring tasks

    PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents

    Zhuohan Gu +3

  35. cs.CV 2026-05-19 reviewed
    Model fuses lidar and plot data for lower-bias forest biomass maps

    StruMPL: Multi-task Dense Regression under Disjoint Partial Supervision and MNAR Labels

    Reza M. Asiyabi +4

  36. cs.GT 2026-05-19 reviewed
    Parallel CFR runs 3.3 times faster on billion-history poker trees

    Real-Time Parallel Counterfactual Regret Minimization

    Boning Li +1

  37. cs.LG 2026-05-19 reviewed
    JAXenstein speeds first-person RL benchmarks several times

    JAXenstein: Accelerated Benchmarking for First-Person Environments

    Ruo Yu Tao +1

  38. cs.LG 2026-05-19 reviewed
    Fast method learns node reps from labels without features

    Fast and Featureless Node Representation Learning with Partial Pairwise Supervision

    Sujan Chakraborty +1

  39. cs.LG 2026-05-19 reviewed
    Contrastive learning separates local and global signals for multi-domain binding

    Hierarchical Contrastive Learning for Multi-Domain Protein-Ligand Binding

    Shuo Zhang +3

  40. cs.LG 2026-05-19 reviewed
    Post-backprop rescaling fixes gradient scales in deep nets without BatchNorm

    StableGrad: Backward Scale Control without Batch Normalization

    Jose I. Mestre +4

  41. cs.CR 2026-05-19 reviewed
    Colluding accounts scale RAG privacy loss by sqrt(k)

    Auditing Privacy in Multi-Tenant RAG under Account Collusion

    Florian A. D. Burnat +1

  42. cs.LG 2026-05-19 reviewed
    Slice-wise tensorization yields near-lossless network compression

    Fast Tensorization of Neural Networks via Slice-wise Feature Distillation

    Safa Hamreras +2

  43. cs.LG 2026-05-19 reviewed
    Framework fuses sensor data with physics rules for better passenger counts

    A Closed-loop, State-centric, Multi-agent Framework for Passenger Load Estimation from Heterogeneous Data Streams

    Yiyao Xu +3

  44. cs.LG 2026-05-19 reviewed
    Diffusion model makes valid airfoils with lift and drag control

    AirfoilGen: A valid-by-construction and performance-aware latent diffusion model for airfoil generation

    Zhijie Yang +3

  45. cs.LG 2026-05-19 reviewed
    Latent diffusion generates valid airfoils conditioned on lift and drag

    AirfoilGen: A valid-by-construction and performance-aware latent diffusion model for airfoil generation

    Zhijie Yang +3

  46. cs.LG 2026-05-19 reviewed
    Set-valued policies output treatment sets instead of singles

    Set-Valued Policy Learning

    Laura Fuentes-Vicente +5

  47. cs.LG 2026-05-19 reviewed
    Domain cuts let neural operators handle PDE discontinuities

    Smooth Piecewise Cutting for Neural Operator to Handle Discontinuities and Sharp Transitions

    Ha Dang +2

  48. cs.LG 2026-05-19 reviewed
    Explainer splits stable and changing links for temporal GNNs

    ST-TGExplainer: Disentangling Stability and Transition Patterns for Temporal GNN Interpretability

    Hongjiang Chen +7

  49. cs.LG 2026-05-19 reviewed
    Privacy budget sets floor on federated estimation error

    General Lower Bounds for Differentially Private Federated Learning with Arbitrary Public-Transcript Interactions

    Yicheng Li

    2 Piths
  50. cs.LG 2026-05-19 reviewed
    Benchmark separates ML models on flux extrapolation via tail errors

    FLUXtrapolation: A benchmark on extrapolating ecosystem fluxes

    Anya Fries +4