pith. sign in

archive

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

14903 papers in cs.LG · page 12

  1. cs.AI 2026-05-20 reviewed
    Taxonomy-based generator yields verifiable planning data for LLMs

    PlanningBench: Generating Scalable and Verifiable Planning Data for Evaluating and Training Large Language Models

    Ziliang Zhao +9

  2. cs.LG 2026-05-20 reviewed
    Gradient moment method cuts 3D Gaussian count by 85-97%

    CAdam: Context-Adaptive Moment Estimation for 3D Gaussian Densification in Generative Distillation

    SeungJeh Chung +3

  3. cs.LG 2026-05-20 reviewed
    Runtime bounds certify quantized KV attention with exact fallback

    Runtime-Certified Bounded-Error Quantized Attention

    Dean Calver

  4. cs.LG 2026-05-20 reviewed
    LOSCAR-SGD overlaps local steps with sparse delayed updates

    LOSCAR-SGD: Local SGD with Communication-Computation Overlap and Delay-Corrected Sparse Model Averaging

    Yassine Maziane +3

  5. cs.LG 2026-05-20 reviewed
    N-step correction tightens PPO bound for RL with verifiable rewards

    Multi-Step Likelihood-Ratio Correction for Reinforcement Learning with Verifiable Rewards

    Deokgyu Yoon +6

  6. cs.DC 2026-05-20 reviewed
    Cluster runtime cuts RLVR GPU costs up to 37.58%

    PlexRL: Cluster-Level Orchestration of Serviceized LLM Execution for RLVR

    Yiqi Zhang +15

  7. cs.RO 2026-05-20 reviewed
    Hypernetwork generates full robot policies from instructions alone

    DISC: Decoupling Instruction from State-Conditioned Control via Policy Generation

    Hanxiang Ren +3

  8. cs.LG 2026-05-20 reviewed
    DualOptim+ bridges shared and delta states to balance LLM forgetting and retention

    DualOptim+: Bridging Shared and Decoupled Optimizer States for Better Machine Unlearning in Large Language Models

    Xuyang Zhong +3

  9. cs.LG 2026-05-20 reviewed
    ReMax proves first sublinear regret bound for M=2 Gaussian bandits

    Finite-Time Regret Analysis of Retry-Aware Bandits

    Bingkui Tong +3

  10. cs.CV 2026-05-20 reviewed
    Polynomial alternatives match activation-based vision models

    Activation-Free Backbones for Image Recognition: Polynomial Alternatives within MetaFormer-Style Vision Models

    Jeffrey Wang +2

  11. cs.AI 2026-05-20 reviewed
    DPO matches RLHF only if optimal policy favors human responses

    Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment

    Zhiqin Yang +5

  12. cs.LG 2026-05-20 reviewed
    Patching state centroids aligns transformer outputs with HMM counterfactuals

    Markovian Circuit Tracing for Transformer State Dynamic

    Abdullah X

  13. cs.CL 2026-05-20 reviewed
    7B open LLMs run GraphRAG locally for EHR schema queries

    GraphRAG on Consumer Hardware: Benchmarking Local LLMs for Healthcare EHR Schema Retrieval

    Peter Fernandes +1

  14. cs.CV 2026-05-20 reviewed
    OlmoEarth models cut training GPU hours by 1.7x

    OlmoEarth v1.1: A more efficient family of OlmoEarth models

    Gabriel Tseng +9

  15. cs.LG 2026-05-20 reviewed
    Preference vector tunes task balance in merged continual learning models

    Tunable MAGMAX: Preference-Aware Model Merging for Continual Learning

    Kei Hiroshima +2

  16. cs.DC 2026-05-20 reviewed
    Two GPU counters match MFU within 2 points at fleet scale

    Instant GPU Efficiency Visibility at Fleet Scale

    Connor Pedersen +4

  17. cs.LG 2026-05-20 reviewed
    Contour images let CNNs pick black-box optimizers

    Beyond Numerical Features: CNN-Driven Algorithm Selection via Contour Plots for Continuous Black-Box Optimization

    Yiliang Yuan +2

  18. cs.LG 2026-05-20 reviewed
    Only two of 20 Transformer modifications transfer at 1-3B

    Most Transformer Modifications Still Do Not Transfer at 1-3B: A 2020-2026 Update to Narang et al. (2021) with Downstream Evaluation and a Noise Floor

    Yang Zhao +4

  19. cs.AI 2026-05-20 reviewed
    Local writes accumulate into global solutions in recursive reasoners

    Interaction Locality in Hierarchical Recursive Reasoning

    Yosuke Miyanishi +1

  20. cs.LG 2026-05-20 reviewed
    Intermediate alignment cuts physics residuals by 66% in diffusion models

    Learning to Think in Physics: Breaking Shortcut Learning in Scientific Diffusion via Representation Alignment

    Haozhe Jia +8

  21. cs.LG 2026-05-20 reviewed
    Meta-learning from queries builds cumulative bias against spurious correlations

    Cumulative Meta-Learning from Active Learning Queries for Robustness to Spurious Correlations

    Kin Whye Chew +1

  22. cs.CL 2026-05-20 reviewed
    LLM interventions create user drift that biases simulated experiments

    The Illusion of Intervention: Your LLM-Simulated Experiment is an Observational Study

    Victoria Lin +5

  23. cs.LG 2026-05-20 reviewed
    Benchmark reveals optimizer rankings flip across shape problems

    ShapeBench: A Scalable Benchmark and Diagnostic Suite for Standardized Evaluation in Aerodynamic Shape Optimization

    Shaghayegh Fazliani +5

  24. cs.AI 2026-05-20 reviewed
    New guidance resolves gradient conflicts in flow models

    Conflict-Aware Additive Guidance for Flow Models under Compositional Rewards

    Xuehui Yu +4

  25. cs.LG 2026-05-20 reviewed
    Bias correction cuts pretraining loss in AdamW and similar optimizers

    Correcting Stochastic Update Bias in Preconditioned Language Model Optimizers

    Nikhil Nayak +9

  26. cs.LG 2026-05-20 reviewed
    Distillation from richer pseudo-samples improves sparse glucose estimates

    PACD-Net: Pseudo-Augmented Contrastive Distillation for Glycemic Control Estimation from SMBG

    Canyu Lei +2

  27. cs.LG 2026-05-20 reviewed
    GLU shrinks NTK condition number for faster convergence

    The Devil is in the Condition Numbers: Why is GLU Better than non-GLU Structure?

    Xingyu Lyu +4

  28. q-bio.GN 2026-05-20 reviewed
    Machine learning ties lncRNA features to type 2 diabetes

    Multi-Modal Machine Learning for Population- and Subject-Specific lncRNA-Type 2 Diabetes Association Analysis

    Ashwani Siwach +2

  29. cs.LG 2026-05-20 reviewed
    Hidden states at paragraph boundaries tune verifier strictness

    The Hidden Signal of Verifier Strictness: Controlling and Improving Step-Wise Verification via Selective Latent Steering

    Yefan Zhou +5

  30. cs.LG 2026-05-20 reviewed
    Testbed embeds detectable hacks for automatic reward-gaming checks

    Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale

    Amit Roth +4

  31. cs.LG 2026-05-20 reviewed
    RL scores full distributions to fix LLM regression

    Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression

    Jungsoo Park +6

  32. cs.CV 2026-05-20 reviewed
    Open-source iris algorithms pass first official IREX evaluation

    Lowering the Barrier to IREX Participation: Open-Source Algorithms, Toolkit, and Benchmarking for Iris Recognition

    Siamul Karim Khan +2

  33. stat.ME 2026-05-20 reviewed
    Conformal tests bound false discoveries for every possible threshold

    Everywhere Valid Bounds on False Discovery Proportions in Conformal Inference

    Ziang Song +2

  34. cs.LG 2026-05-20 reviewed
    Android crowds run large DNNs at 43 MB RAM per phone

    Memory-Efficient Partitioned DNN Inference on Resource-Constrained Android Crowds

    Lakshani Manamperi +4

  35. cs.LG 2026-05-20 reviewed
    Group statistics adapt clipping and temperature to lift LLM math scores

    AGPO: Adaptive Group Policy Optimization with Dual Statistical Feedback

    Miaobo Hu +7

  36. cs.LG 2026-05-20 reviewed
    GMM calibration lets recommenders use all noisy feedback

    Robust Recommendation from Noisy Implicit Feedback: A GMM-Weighted Bayes-label Transition Matrix Framework

    Zongyu Li +5

  37. cs.LG 2026-05-20 reviewed
    Decision path flips raise random forest accuracy

    Decision-Path Patterns as Tree Reliability Signals: Path-based Adaptive Weighting for Random Forest Classification

    Youngjoon Park

  38. cs.LG 2026-05-20 reviewed
    Decision-path flips yield unbiased per-sample weights for random forests

    Decision-Path Patterns as Tree Reliability Signals: Path-based Adaptive Weighting for Random Forest Classification

    Youngjoon Park

  39. cs.CV 2026-05-20 reviewed
    SAVER selectively activates vision to boost F1 and cut latency in multimodal IE

    SAVER: Selective As-Needed Vision Evidence for Multimodal Information Extraction

    Miaobo Hu +7

  40. cs.LG 2026-05-20 reviewed
    Neural solver matches SOTA hypervolume at 40% less time

    WeCon: An Efficient Weight-Conditioned Neural Solver for Multi-Objective Combinatorial Optimization Problems

    Xuan Wu +9

  41. cs.DC 2026-05-20 reviewed
    WebGPU backend cuts LLM memory use by 29-33% in browsers

    Llamas on the Web: Memory-Efficient, Performance-Portable, and Multi-Precision LLM Inference with WebGPU

    Reese Levine +7

  42. cs.AI 2026-05-20 reviewed
    Agentic system solves 8 of 10 research math problems

    RMA: an Agentic System for Research-Level Mathematical Problems

    Zelin Zhao +3

  43. cs.LG 2026-05-20 reviewed
    DPO converges in distributed settings with rates set by communication and heterogeneity

    Distributed Direct Preference Optimization

    Zhanhong Jiang

  44. cs.CL 2026-05-20 reviewed
    Self-limiting losses compress embeddings without overfitting

    DIVE: Embedding Compression via Self-Limiting Gradient Updates

    Dongfang Zhao

  45. eess.IV 2026-05-20 reviewed
    Deep learning clears motion in free-breathing heart MRI

    Motion-Robust Deep Reconstruction for Free-Breathing Cardiac Cine MRI

    Mahmut Yurt +10

  46. stat.ME 2026-05-20 reviewed
    Scale calibration makes median-of-means work for distributed PCA

    Scale-Calibrated Median-of-Means for Robust Distributed Principal Component Analysis

    Kisung You

  47. cs.LG 2026-05-20 reviewed
    Dynamic experts cut error on shifting time series

    Dynamic TMoE: A Drift-Aware Dynamic Mixture of Experts Framework for Non-Stationary Time Series Forecasting

    Jiawen Zhu +3

  48. cs.LG 2026-05-20 reviewed
    Frozen encoders plus tabular models hit SOTA on multimodal tasks

    Modular Multimodal Classification Without Fine-Tuning: A Simple Compositional Approach

    Herman Bergstr\"om +2

  49. cs.LG 2026-05-20 reviewed
    Looped transformers run linearly and outperform standard versions

    LT2: Linear-Time Looped Transformers

    Chunyuan Deng +6

  50. cs.CL 2026-05-20 reviewed
    AI reviewer beats top human on Nature papers

    On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists

    Seungone Kim +57