pith. sign in

archive

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

14903 papers in cs.LG · page 9

  1. cs.LG 2026-05-20 reviewed
    Dropout creates two scaling-law classes by activation type

    Dropout Universality: Scaling Laws and Optimal Scheduling at the Edge-of-Chaos

    Lucas Fernandez Sarmiento

  2. cs.LG 2026-05-20 reviewed
    Feature importance keeps prototype explanation fidelity steady

    Alike Parts: A Feature-Informed Approach to Local and Global Prototype Explanations

    Jacek Karolczak +1

  3. cs.LG 2026-05-20 reviewed
    Transformer locates centromeres in Hi-C data across species

    $\textit{BlockFormer}$ : Transformer-based inference from interaction maps

    Elo\"ise Touron +4

  4. cs.CR 2026-05-20 reviewed
    Dataset unifies 73k binaries with build variations and CVE history

    ASSEMBLAGE-DEEPHISTORY: A Cross-Build Binary Dataset with Temporal Coverage

    Chang Liu +5

  5. cs.HC 2026-05-20 reviewed
    LLMs beat semantic similarity at scoring self-explanations

    Exploring the Effectiveness of Using LLMs for Automated Assessment of Student Self Explanations in Programming Education

    Arun-Balajiee Lekshmi-Narayanan +2

  6. cs.CV 2026-05-20 reviewed
    Text rendered on masks improves images and halves inference cost

    UniVL: Unified Vision-Language Embedding for Spatially Grounded Contextual Image Generation

    Jiayun Wang +4

  7. cs.LG 2026-05-20 reviewed
    AgForce makes antibody design respond to specific antigens

    AgForce Enables Antigen-conditioned Generative Antibody Design

    Mansoor Ahmed +1

  8. cs.LG 2026-05-20 reviewed
    Position weighting lifts AIME scores by over 1 point in distillation

    When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning

    Xiaogeng Liu +4

  9. cs.LG 2026-05-20 reviewed
    Contact prediction step improves CDR design quality

    ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning

    Mansoor Ahmed +5

  10. cs.LG 2026-05-20 reviewed
    Amortized noise sampling cuts diffusion teacher variance 10x

    Variance Reduction for Expectations with Diffusion Teachers

    Jesse Bettencourt +4

  11. cs.LG 2026-05-20 reviewed
    Amortized resampling yields 2-3x compute gains for diffusion teachers

    Variance Reduction for Expectations with Diffusion Teachers

    Jesse Bettencourt +4

  12. cs.LG 2026-05-20 reviewed
    Attractors let iterative nets scale to 99% on extreme Sudoku

    Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning

    Benhao Huang +2

  13. cs.LG 2026-05-20 reviewed
    Embedding learning rate boost replicates muP transfer

    Quantifying Hyperparameter Transfer and the Importance of Embedding Layer Learning Rate

    Dayal Singh Kalra +1

  14. cs.LG 2026-05-20 reviewed
    Adapter restores evolutionary diversity to GNN antibody design

    EvoStruct: Bridging Evolutionary and Structural Priors for Antibody CDR Design via Protein Language Model Adaptation

    Mansoor Ahmed +3

  15. astro-ph.CO 2026-05-20 reviewed
    Symmetry match lifts velocity reconstruction accuracy 35%

    Velocityformer: Broken-Symmetry-Matched Equivariant Graph Transformers for Cosmological Velocity Reconstruction

    Tilman Tr\"oster +3

  16. cs.AI 2026-05-20 reviewed
    Platform lets humans and AIs co-author and iterate on papers

    AiraXiv: An AI-Driven Open-Access Platform for Human and AI Scientists

    Junshu Pan +7

  17. cs.LG 2026-05-20 reviewed
    Learnable graphs can replace fixed schemas for relational deep learning

    Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learning

    Yi Huang +4

  18. cs.LG 2026-05-20 reviewed
    JIT compilation speeds web agents by 10 times

    Agent JIT Compilation for Latency-Optimizing Web Agent Planning and Scheduling

    Caleb Winston +3

  19. cs.LG 2026-05-20 reviewed
    Rank-1 line from first 50 steps matches full RLVR at 15% cost

    You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories

    Zhepei Wei +5

  20. cs.LG 2026-05-20 reviewed
    DelTA raises math scores by over 3 points on 8B models

    DelTA: Discriminative Token Credit Assignment for Reinforcement Learning from Verifiable Rewards

    Kaiyi Zhang +2

  21. cs.LG 2026-05-20 reviewed
    ML weights GNSS signals to cut urban positioning errors

    A Machine Learning Framework for Weighted Least Squares GNSS Positioning based on Activation Functions

    Pin-Hsun Lee +1

  22. cs.AI 2026-05-20 reviewed
    Randomization fixes simulator shift but reachability gaps persist

    Mind the Sim-to-Real Gap & Think Like a Scientist

    Harsh Parikh +3

  23. cs.LG 2026-05-20 reviewed
    Rubric embeddings cut disparities in admissions models

    Mitigating Label Bias with Interpretable Rubric Embeddings

    Calvin Isley +2

  24. cs.LG 2026-05-20 reviewed
    Deeper networks approximate structured functions with fewer parameters

    Approximation Theory for Neural Networks: Old and New

    Soumendu Sundar Mukherjee +1

  25. cs.LG 2026-05-20 reviewed
    Fitzhugh-Nagumo networks admit equilibrium propagation via self-adjoint operators

    Equilibrium Propagation and Hamiltonian Inference in the Diffusive Fitzhugh-Nagumo Model

    Jack Kendall

  26. cs.LG 2026-05-20 reviewed
    PyTorch library matches specialized tools in LLM tuning

    torchtune: PyTorch native post-training library

    Mark Obozov +10

  27. physics.geo-ph 2026-05-20 reviewed
    Per-cell dispersion cuts tail forecast error 12.5 percent

    Neural Negative Binomial Regression for Weekly Seismicity Forecasting: Per-Cell Dispersion Estimation and Tail Risk Assessment

    Alim Igilik

  28. cs.LG 2026-05-20 reviewed
    New Laplacian lets GNNs keep Gaussian means and covariances intact

    Gaussian Sheaf Neural Networks

    Andr\'e Ribeiro +3

  29. cs.RO 2026-05-20 reviewed
    Blind agents rotate Baoding balls 13 times in 10 seconds

    roto 2.0: The Robot Tactile Olympiad

    Elle Miller +6

  30. cs.LG 2026-05-20 reviewed
    Presents new structural results and pairwise improper-learning frameworks for…

    Polynomial-Time Robust Multiclass Linear Classification under Gaussian Marginals

    Ilias Diakonikolas +2

  31. cs.LG 2026-05-20 reviewed
    Channel-wise repair boosts 90% sparse ResNet accuracy to 55.6%

    Adaptive Signal Resuscitation: Channel-wise Post-Pruning Repair for Sparse Vision Networks

    Qishi Zhan +2

  32. cs.LG 2026-05-20 reviewed
    Preference weighting improves data selection for LLM fine-tuning

    PRISM: Preference-Aware Influence Function Based Data Selection Method for Efficient Fine-Tuning

    Qihao Lin +3

  33. cs.LG 2026-05-20 reviewed
    One embedding predicts conditions and retrieves precedents

    HiRes: Inspectable Precedent Memory for Reaction Condition Recommendation

    Shreyas Vinaya Sathyanarayana +2

  34. cs.LG 2026-05-20 reviewed
    Gossip-based critic sharing lifts multi-cell OFDMA sum-rates in 6G

    FedCritic: Serverless Federated Critic Learning-based Resource Allocation for Multi-Cell OFDMA in 6G

    Amin Farajzadeh +1

  35. cs.LG 2026-05-20 reviewed
    CKD models perfect internally fail on new data

    Calibration, Uncertainty Communication, and Deployment Readiness in CKD Risk Prediction: A Framework Evaluation Study

    Michael O. Eniolade

  36. cs.LG 2026-05-20 reviewed
    Curriculum learning cuts modality imbalance in emotion chats

    Leveraging Self-Paced Curriculum Learning for Enhanced Modality Balance in Multimodal Conversational Emotion Recognition

    Phuong-Anh Nguyen +3

  37. cs.LG 2026-05-20 reviewed
    LLM agent benchmarks disclose only 38 percent of evaluation details

    What Twelve LLM Agent Benchmark Papers Disclose About Themselves: A Pilot Audit and an Open Scoring Schema

    Mahdi Naser Moghadasi (BrightMind AI +2

  38. stat.ML 2026-05-20 reviewed
    Models converge without recovering main latent factors

    Memorisation, convergence and generalisation in generative models

    Antoine Maillard +1

  39. cs.AI 2026-05-20 reviewed
    One foundation model to run all 6G tasks autonomously

    Towards Resilient and Autonomous Networks: A BlueSky Vision on AI-Native 6G

    Liang Wu +3

  40. cs.LG 2026-05-20 reviewed
    Transport maps to PDE measures are Hölder continuous

    On the Regularity and Generalization of One-Step Wasserstein-guided Generative Models for PDE-Induced Measures

    Likun Lin +3

  41. cs.CV 2026-05-20 reviewed
    One model shifts image restoration from precise to creative

    Disentangling Generation and Regression in Stochastic Interpolants for Controllable Image Restoration

    Yi Liu +5

  42. cs.CV 2026-05-20 reviewed
    Simulation feedback picks best synthetic scenes for driving models

    Closed Loop Dynamic Driving Data Mixture for Real-Synthetic Co-Training

    Hongzhi Ruan +7

  43. cs.LG 2026-05-20 reviewed
    Personalised method raises iron deficiency prediction at two clinics

    Embedding-Based Federated Learning with Runtime Governance for Iron Deficiency Prediction

    Fan Zhang +12

  44. cs.LG 2026-05-20 reviewed
    CNNs classify six PD source types under switching voltage at 96% accuracy

    Classification of Single and Mixed Partial Discharges under Switching Voltage Using an AWA-CNN Framework

    Md Rafid Kaysar Shagor +3

  45. cs.AI 2026-05-20 reviewed
    Multi-agent reports raise LLM scaffold performance by 30 points

    Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents

    Akshay Manglik +8

  46. cs.LG 2026-05-20 reviewed
    PDE residual selects training data to cut neural operator costs

    Data-Efficient Neural Operator Training via Physics-Based Active Learning

    Alicja Polanska +3

  47. cs.AI 2026-05-20 reviewed
    Multi-agent system turns full LLM traces into evidence-backed insights

    Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents

    Akshay Manglik +8

  48. stat.ML 2026-05-20 reviewed
    Debiasing fixes bias in bilevel hypergradients

    Semiparametric Efficient Bilevel Gradient Estimation

    Fares El Khoury +4

  49. cs.AI 2026-05-20 reviewed
    43M-paper graph gives AI agents deterministic cross-field links

    SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research

    Shuofei Qiao +10

  50. cs.LG 2026-05-20 reviewed
    Delta-Rule linear transformers gain up to 4.3× speed on NPUs

    Fast and Stable Triangular Inversion for Delta-Rule Linear Transformers

    Aleksandros Sobczyk +6