pith. sign in

archive

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

14903 papers in cs.LG · page 3

  1. cs.LG 2026-05-22 reviewed
    Prefix prompts let frozen LLMs condition flows for multi-modal forecasts

    PaP-NF: Probabilistic Long-Term Time Series Forecasting via Prefix-as-Prompt Reprogramming and Normalizing Flows

    Minju Kim +1

  2. cs.LG 2026-05-22 reviewed
    Kernel agents top out at 0.94x production baselines

    FastKernels: Benchmarking GPU Kernel Generation in Production

    Gabriele Oliaro +7

  3. cs.CV 2026-05-22 reviewed
    Homography mapping yields linear bounds for camera motion verification

    Lipschitz Optimization for Formal Verification of Homographies

    Jean-Guillaume Durand +3

  4. cs.LG 2026-05-22 reviewed
    Region quotas stop wipe-out of reasoning blocks in KV caches

    Adaptive Mass-Segmented KV Compression for Long-Context Reasoning

    Junzhe Yang +1

  5. cs.LG 2026-05-22 reviewed
    Small labeled set plus pseudo-labels prunes datasets effectively

    Label-Efficient Dataset Pruning via Semi-Supervised Pseudo-Labeling

    Yeseul Cho +3

  6. cs.LG 2026-05-22 reviewed
    Pretrained graph model improves low-data OPF accuracy

    Scalable Heterogeneous Graph Foundation Models for Data-Driven Optimal Power Flow in Smart Grids

    Massimiliano Lupo Pasini +3

  7. cs.LG 2026-05-22 reviewed
    RankElastor stabilizes rank trajectories for scaled recommenders

    Expand More, Shrink Less: Shaping Effective-Rank Dynamics for Dense Scaling in Recommendation

    Guoming Li +9

  8. cs.LG 2026-05-22 reviewed
    r-value scores shrink conformal sets by excluding unstable candidates

    Empirical Bayes Conformal Prediction for Vision and Language Models

    Jiapeng Zeng +4

  9. cs.LG 2026-05-22 reviewed
    GPI finds good policies with cost independent of state space size

    Pure Exploration for a Good Policy in Reinforcement Learning with Bandit Feedback

    Zitian Li +1

  10. cs.CL 2026-05-22 reviewed
    Optimizing prompt embeddings boosts in-context learning

    Self-Improving In-Context Learning

    Baturay Saglam +1

  11. cs.LG 2026-05-22 reviewed
    Symmetric noise lifts AlpacaEval scores from 65% to 69% in fine-tuning

    Understanding and Improving Noisy Embedding Techniques in Instruction Finetuning

    Abhay Yadav

  12. cs.CL 2026-05-22 reviewed
    LLMs drop up to 88 points when tasks move to context middle

    Positional Failures in Long-Context LLMs: A Blind Spot in Reasoning Benchmarks

    Chuyifei Zhang +3

  13. cs.CR 2026-05-22 reviewed
    10 poisoned examples hijack targeted LLM tasks at 70%+ success

    PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs

    Luze Sun +4

  14. cs.CR 2026-05-22 reviewed
    ActInv recovers inputs from LLM split-inference activations

    What Does the Server See? Understanding Privacy Leakage from Large Language Models in Split Inference

    Mingyuan Fan +3

  15. cs.LG 2026-05-22 reviewed
    Limit space makes any-size input models universal

    Any-Dimensional Invariant Universality

    Shengtai Yao +2

  16. cs.LG 2026-05-22 reviewed
    Infra-Bayesian RL records lower worst-case regret than classical agents

    Infra-Bayesian Reinforcement Learning Agents Outperform Classical RL For Worst-Case Robustness

    Manish Aryal +12

  17. stat.ML 2026-05-22 reviewed
    Gradient descent recovers true similarity metric from triplets

    Operationalizing Individual Fairness via Gradient Descent and Bradley-Terry Models

    Conlan Olson +3

  18. cs.LG 2026-05-22 reviewed
    Channel relevance steers contrastive samples for time series anomaly detection

    CALAD: Channel-Aware contrastive Learning for multivariate time series Anomaly Detection

    Jaehyeop Hong +1

  19. quant-ph 2026-05-22 reviewed
    RL selects Clifford states that boost VQA energy accuracy 3x on average

    Classical State Preparation for Variational Quantum Algorithms via Reinforcement Learning

    Gino Kwun +2

  20. cs.LG 2026-05-22 reviewed
    Taylor-mode AD powering yields exact nested copula likelihoods

    Archimedean Copula Inference via Taylor-Mode AD

    Cambridge Yang +1

  21. cs.LG 2026-05-22 reviewed
    Rayleigh quotient fixes rare switching under privacy noise

    When Determinants Are Not Enough: Private Rare Switching

    Xingyu Zhou

  22. cs.CV 2026-05-22 reviewed
    Verified prompts plus longitudinal context raise lesion tracking Dice by 4.5 points

    Exploiting Longitudinal Context in Clinician-Verified Interactive Lesion Tracking

    Yannick Kirchhoff +7

  23. cs.LG 2026-05-22 reviewed
    Gen-ROTDA adapts bike-sharing demand models across years by anchoring on few target labels

    Robust OT-Guided Generative Residual Domain Adaptation for Bike-Sharing Demand Prediction under Temporal Domain Shift

    Yiming Ma

  24. stat.ML 2026-05-21 reviewed
    LLM Sparsity Prior lets spike-and-slab models ignore bad LLM weights

    LLM Sparsity Prior for Robust Feature Selection

    Caleb Skinner +2

  25. cs.CR 2026-05-21 reviewed
    Certified bounds eliminate overflows in encrypted neural nets

    Encrypted Neural Networks without Overflows

    Philipp Kern +5

  26. cs.LG 2026-05-21 reviewed
    Jacobian penalty on latent dynamics raises sample efficiency in DreamerV3

    Dreaming Smoothly and Sample Efficiently with Gradient Penalized Latent Dynamics

    Romil V. Sonigra (1) +1

  27. cs.LG 2026-05-21 reviewed
    Depth biases networks toward low-rank softmax codes

    The Implicit Bias of Depth: From Neural Collapse to Softmax Codes

    Connall Garrod +2

  28. stat.ML 2026-05-21 reviewed
    KAN estimator converges independent of covariate dimension

    KAPLAN: Kolmogorov-Arnold Prognostic Learnable Activation Networks for Survival Analysis

    Stelios Boulitsakis Logothetis +2

  29. cs.LG 2026-05-21 reviewed
    5% FP16 blocks recover 89% of FP4-to-FP16 attention quality gap

    ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention

    Joe Sharratt

  30. cs.LG 2026-05-21 reviewed
    Attribution contract resolves ambiguity in generative model explanations

    The Attribution Contract: Feature Attribution for Generative Language Models

    Giang Nguyen

  31. cs.LG 2026-05-21 reviewed
    Global LP ranks every MoE expert to cut memory at low bits

    GEMQ: Global Expert-Level Mixed-Precision Quantization for MoE LLMs

    Jianing Deng +6

  32. cs.DC 2026-05-21 reviewed
    Orbax speeds JAX checkpoint saves up to 3.5x over PyTorch

    Orbax: Distributed Checkpointing with JAX

    Colin Gaffney +15

  33. cs.CV 2026-05-21 reviewed
    Dithering defends vision models against adversarial attacks

    Dithering Defense: Adversarial Robustness of Vision Foundation Models via Multi-Level Floyd-Steinberg Dithering

    Yury Belousov +3

  34. cs.CV 2026-05-21 reviewed
    Vertex weights let mmWave data drive accurate SMPL body fits

    Millimeter-wave Imaging for Anthropometric Body Measurement

    Miriam Senne +4

  35. cs.LG 2026-05-21 reviewed
    One config matches tuned AdamW across 1-8x horizons on LLMs

    Anytime Training with Schedule-Free Spectral Optimization

    Anuj Apte +4

  36. cs.LG 2026-05-21 reviewed
    Controller routes LLM requests to best mode for 2x speedup

    ModeSwitch-LLM: A Lightweight Phase-Aware Controller for Cross-Mode LLM Inference on a Single GPU

    Aman Sunesh +2

  37. cs.LG 2026-05-21 reviewed
    Recognition of evaluations depends on model-benchmark pairs

    Decomposing and Measuring Evaluation Awareness

    Changling Li +5

  38. cs.CL 2026-05-21 reviewed
    Compositionality rises then falls in LLM self-training

    Model Collapse as Cultural Evolution

    Dongxin Guo +2

  39. cs.CV 2026-05-21 reviewed
    Motion data alone rivals video models trained on 10000x more examples

    The TIME Machine: On The Power of Motion for Efficient Perception

    Mantas Skackauskas +2

  40. cs.LG 2026-05-21 reviewed
    Sparse query gradients steer LLM paths and feedback levels

    Steered Generation via Gradient-Based Optimization on Sparse Query Features

    Sumanta Bhattacharyya +1

  41. cs.CL 2026-05-21 reviewed
    LLMs learn what not to say via frequency competition

    Do Language Models Know What Not to Say? Causal Evidence for Statistical Preemption in LLMs

    Dongxin Guo +2

  42. cs.LG 2026-05-21 reviewed
    Open datasets and software released for thermal-fluid AI

    Open Multimodal Datasets and Open-Source Software for Data-Driven Modeling of Multiphase Transport and Thermal Systems

    Christy Dunlap +8

  43. cs.LG 2026-05-21 reviewed
    Intermediate layers hold more task info than final layers

    Uncovering the Latent Potential of Deep Intermediate Representations

    Arnesh Batra +4

  44. cs.LG 2026-05-21 reviewed
    RADAR forecasts transfer by comparing representation trajectories

    RADAR: Relative Angular Divergence Across Representations

    Xavier Cadet +2

  45. cs.LG 2026-05-21 reviewed
    Latent states let transformer adapt to time-series contexts without quadratic cost

    World Machine: Towards Generative World Modeling for Time-Series

    Elton Cardoso do Nascimento +4

  46. cs.AI 2026-05-21 reviewed
    Transformers have fixed accuracy limits set by layers and width

    The Deterministic Horizon: Impossibility Results as Design Specifications for Trustworthy AI Systems

    Dongxin Guo

  47. cs.LG 2026-05-21 reviewed
    Small models evolve their own agents via two-timescale updates

    PACE: Two-Timescale Self-Evolution for Small Language Model Agents

    Chen Ling +6

  48. cs.LG 2026-05-21 reviewed
    Lipschitz intermediaries enable approximate calibration of discrete properties

    Smoothed Elicitation Complexity for Approximate $\Gamma$-calibration of Discrete Classification Tasks

    Jessica Finocchiaro +2

  49. q-fin.TR 2026-05-21 reviewed
    LLM evolutionary optimizer boosts Bitcoin trading in backtests

    MadEvolve: Evolutionary Optimization of Trading Systems with Large Language Models

    Yurii Kvasiuk +3

  50. q-bio.NC 2026-05-21 reviewed
    Active sensing serves task control

    Active Sensing Subserves Task-Level Control

    Andrew Lamperski +5