pith. sign in

archive

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

14903 papers in cs.LG · page 17

  1. cs.AI 2026-05-19 reviewed
    Context management determines real-world Transformer Turing-completeness

    Position: The Turing-Completeness of Autoregressive Transformers Relies Heavily on Context Management

    Guanyu Cui +2

  2. cs.RO 2026-05-19 reviewed
    Game creatures become RL testbeds in new MuJoCo suite

    ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders

    Carlo Romeo +1

  3. cs.RO 2026-05-19 reviewed
    One reward function trains policies for four game robots

    ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiders

    Carlo Romeo +1

  4. cs.LG 2026-05-19 reviewed
    Two time scales in SGD cause memorization in generative models

    Adynamical systems view of training generativemodels and the memorization phenomenon

    Siva Athreya +2

  5. cs.CL 2026-05-19 reviewed
    TokenDrift cuts Gen-PPL by 89% at 4 steps in DDLMs

    Drifting Objectives for Refining Discrete Diffusion Language Models

    Daisuke Oba +2

  6. cs.LG 2026-05-19 reviewed
    Finite dynamics samples enforce safety during RL learning

    Sampling-Based Safe Reinforcement Learning

    Luca Vignola +6

  7. cs.LG 2026-05-19 reviewed
    Pre-training boosts time series detection by 375% but not forecasting

    Quantifying the Pre-training Dividend: Generative versus Latent Self-Supervised Learning for Time Series Foundation Models

    Noam Major +2

  8. cs.LG 2026-05-19 reviewed
    Mirror maps reach same max-margin with sparse or dense features

    Implicit Bias of Mirror Flow in Homogeneous Neural Networks: Sparse and Dense Feature Learning

    Tom Jacobs +1

  9. cs.LG 2026-05-19 reviewed
    Spiking blocks replace Transformer nonlinearities with <1% accuracy drop

    Plug-and-Play Spiking Operators: Breaking the Nonlinearity Bottleneck in Spiking Transformers

    Xinzhe Yuan (1) +6

  10. cs.LG 2026-05-19 reviewed
    Majority vote locks wrong answers after brief correct window in TTRL

    Detecting and Mitigating the Correct-Answer Extinction Window in Test-Time Reinforcement Learning with Majority Voting

    Hongxiang Lin +3

  11. cs.LG 2026-05-19 reviewed
    CEPO boosts math reasoning to 43.43% at 2B and 60.56% at 4B

    CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization

    Ahmed Heakl +6

  12. cs.LG 2026-05-19 reviewed
    Model fuses layout and netlist to predict cell delay at 0.92% error

    FusionCell: Cross-Attentive Fusion of Layout Geometry and Netlist Topology for Standard-Cell Performance Prediction

    Haoyi Zhang +4

  13. cs.LG 2026-05-19 reviewed
    Output-layer gradient norm gates reuse to cut RLVR samples by 2.93x

    When to Stop Reusing: Dynamic Gradient Gating for Sample-Efficient RLVR

    Yuchun Miao +6

  14. eess.SP 2026-05-19 reviewed
    Pilot-only model beats full-CSI baselines across frequencies

    PilotWiMAE: Pilot-Native Representation Learning for Wireless Channels

    Berkay Guler +2

  15. cs.CR 2026-05-19 reviewed
    Adaptive tuning raises LLM jailbreak harm scores from 6% to 70%

    Adaptive Probe-based Steering for Robust LLM Jailbreaking

    Junxi Chen +2

  16. cs.LG 2026-05-19 reviewed
    Feedback prefixing improves LLM scaling by up to 2.8x efficiency

    Introspective X Training: Feedback Conditioning Improves Scaling Across all LLM Training Stages

    Brandon Cui +9

  17. cs.LG 2026-05-19 reviewed
    ODE traces low-loss paths for sequential model merging

    Unlocking the Potential of Continual Model Merging: An ODE Perspective

    Lihong Lin +1

  18. cs.LG 2026-05-19 reviewed
    ODE paths limit forgetting when merging models sequentially

    Unlocking the Potential of Continual Model Merging: An ODE Perspective

    Lihong Lin +1

  19. cs.LG 2026-05-19 reviewed
    Large models improve with unfiltered low-quality data

    A Bitter Lesson for Data Filtering

    Christopher Mohri +2

  20. cs.LG 2026-05-19 reviewed
    TIDE halves training time and lifts perturbed ImageNet accuracy by 1.65%

    TIDE: Asymmetric Neural Circuits for Stabilized Temporal Inhibitory-Excitatory Dynamics

    Alexander Kyuroson +2

  21. cs.CV 2026-05-19 reviewed
    JUDO outperforms GPT-4o on industrial anomaly QA with normal image references

    JUDO: A Juxtaposed Domain-Oriented Multimodal Reasoner for Industrial Anomaly QA

    Hyunju Kang +3

  22. cs.CV 2026-05-19 reviewed
    Variance penalty on penultimate neurons cuts medical AI bias

    Neuron Incidence Redistribution for Fairness in Medical Image Classification

    Abin Shoby +2

  23. cs.LG 2026-05-19 reviewed
    Adam momentum reverses roles in zero-sum games

    Understanding Dynamics of Adam in Zero-Sum Games: An ODE Approach

    Yi Feng +2

  24. stat.ML 2026-05-19 reviewed
    Tweedie formulae now cover non-Gaussian diffusions

    Tweedie's Formulae and Diffusion Generative Models Beyond Gaussian

    Wenpin Tang +3

  25. econ.GN 2026-05-19 reviewed
    AI inference costs multiply Phillips curve slope by lambda-bar

    The Economics of AI Inference: Inflation Dynamics, Welfare Costs, and Optimal Monetary Policy under the Inference-Cost Phillips Curve

    Gustav Olaf Yunus Laitinen-Fredriksson Lundstr\"om-Imanov

  26. cs.LG 2026-05-19 reviewed
    LLM safety benchmarks are orbits under group actions

    The Evaluation Game: Beyond Static LLM Benchmarking

    Paul Wang +3

  27. cs.CV 2026-05-19 reviewed
    Concept ontology filters noisy negatives to lift chest X-ray zero-shot tasks

    Concept-Guided Noisy Negative Suppression for Zero-Shot Classification and Grounding of Chest X-Ray Findings

    Chenyu Lian +3

  28. cs.LG 2026-05-19 reviewed
    Deep learning outperforms physics models on floods and weather

    Accurate, Efficient, and Explainable Deep Learning Approaches for Environmental Science Problems

    Jimeng Shi

  29. cs.CV 2026-05-19 reviewed
    Optical pass checks 15 deepfake videos simultaneously

    Scalable, Energy-Efficient Optical-Neural Architecture for Multiplexed Deepfake Video Detection

    Parnian Ghapandar Kashani +2

  30. cs.CV 2026-05-19 reviewed
    Atlas text boosts mammography BI-RADS accuracy

    MAM-CLIP: Vision-Language Pretraining on Mammography Atlases for BI-RADS Classification

    Halil Ibrahim Gulluk +1

  31. econ.GN 2026-05-19 reviewed
    Closed-form subsidy maximizes welfare under model collapse

    The Economics of Model Collapse: Equilibrium, Welfare, and Optimal Provenance Subsidies in Synthetic Data Markets

    Gustav Olaf Yunus Laitinen-Fredriksson Lundstr\"om-Imanov

  32. cs.GR 2026-05-19 reviewed
    Repositioned anchors keep motion contacts across body shapes

    Skinned Motion Retargeting with Spatially Adaptive Interaction Guidance

    Soojin Choi +5

  33. q-bio.NC 2026-05-19 reviewed
    Action models align asymmetrically with brain action signals

    Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay

    Subba Reddy Oota +6

  34. cs.GR 2026-05-19 reviewed
    Bounding box layouts generate editable 3D parts

    CompoSE: Compositional Synthesis and Editing of 3D Shapes via Part-Aware Control

    Habib Slim +4

  35. cs.LG 2026-05-19 reviewed
    Claim differences as RL rewards balance caption hallucinations and omissions

    ClaimDiff-RL: Fine-Grained Caption Reinforcement Learning through Visual Claim Comparison

    Tianle Li +9

  36. cs.CL 2026-05-19 reviewed
    Supreme Court quashes 18 points more matrimonial petitions than Karnataka HC

    IMLJD: A Computational Dataset for Indian Matrimonial Litigation Analysis

    Joy Bose

  37. cs.LG 2026-05-19 reviewed
    Disentangling signals improves single-cell perturbation forecasts

    What Makes a Representation Good for Single-Cell Perturbation Prediction?

    Wenkang Jiang +7

  38. cs.CL 2026-05-19 reviewed
    Benchmark labels hallucinations via explicit reference worlds

    HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models

    Emmy Liu +6

    5 Piths
  39. q-bio.QM 2026-05-19 reviewed
    Protein Thoughts ranks true binders at mean position 11.2

    Protein Thoughts: Interpretable Reasoning with Tree of Thoughts and Embedding-Space Flow Matching for Protein-Protein Interaction Discovery

    Kingsley Yeon +2

  40. cs.LG 2026-05-19 reviewed
    Unified signals close the gap between centralized and federated learning

    OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization

    Wei-Bin Kou +6

  41. cs.GT 2026-05-19 reviewed
    LLMs close 99% of deals but earn low profits in hidden pricing

    PrefBench: Evaluating Zero-Shot LLM Agents in Hidden-Preference Personalized Pricing Negotiations

    Yingjie Lei

  42. cs.AI 2026-05-19 reviewed
    MOCHA improves agent skill correctness on every task

    MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization

    Md Mehrab Tanjim +8

  43. cs.LG 2026-05-19 reviewed
    Exterior rotation improves NMF convergence and accuracy

    An Exterior Method for Nonnegative Matrix Factorization

    Qiujing Lu +4

  44. cs.LG 2026-05-19 reviewed
    Sheaf neural ODE forecasts brain dynamics from graphs

    BrainDyn: A Sheaf Neural ODE for Generative Brain Dynamics

    Siddharth Viswanath +5

  45. cs.LG 2026-05-19 reviewed
    Partial re-noising raises Sudoku accuracy from 56% to 75%

    Inference-Time Scaling in Diffusion Models through Iterative Partial Refinement

    Taegu Kang +2

  46. stat.ML 2026-05-19 reviewed
    Method clusters subjects and learns their distinct causal graphs

    A Unified Framework for Structure-Aware Clustering and Heterogeneous Causal Graph Learning

    Honglin Du +2

  47. cs.LG 2026-05-19 reviewed
    LSTM needs more noise separation than EM for reliable classification

    An Objective Performance Evaluation of the LSTM Networks in Time Series Classification

    Sooraj Sunil +1

  48. cs.LG 2026-05-19 reviewed
    Adaptive penalty proves convergence for feasible Pareto hypernetworks

    A Two-Phase Adaptive Balanced Penalty Method for Controllable Pareto Front Learning under Split Feasibility Conditions

    Nguyen Viet Hoang +2

  49. cs.GR 2026-05-19 reviewed
    Matérn noise gives flow matching triangulation-agnostic behavior

    Mat\'ern Noise for Triangulation-Agnostic Flow Matching on Meshes

    Tianshu Kuai +3

  50. cs.LG 2026-05-19 reviewed
    RF and DNN share knowledge in both directions effectively

    Cross-Paradigm Knowledge Distillation: A Comprehensive Study of Bidirectional Transfer Between Random Forests and Deep Neural Networks for Big Data Applications

    Mahdi Naser Moghadasi