pith. sign in

archive

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

14903 papers in cs.LG · page 13

  1. cs.CV 2026-05-20 reviewed
    RoPeSLR cuts DiT FLOPs 10x at 90% sparsity

    RoPeSLR: 3D RoPE-driven Sparse-LowRank Attention for Efficient Diffusion Transformers

    Yuxi Liu +5

  2. cs.LG 2026-05-20 reviewed
    Reflector embeds reflection to block indirect jailbreaks

    REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak

    Jiachen Ma +5

  3. cs.LG 2026-05-20 reviewed
    Early entropy drop signals when CoT reasoning helps LLMs

    When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions

    Wei Xia +3

  4. eess.SP 2026-05-20 reviewed
    Attention model doubles perfect multi-user Wi-Fi activity predictions

    AMAR: Lightweight Attention-Based Multi-User Activity Recognition from Wi-Fi CSI

    Amirhossein Mohammadi +1

  5. cs.LG 2026-05-20 reviewed
    RL method produces ready-to-bend pipes for aeroengines

    Design for Manufacturing: A Manufacturability Knowledge-Integrated Reinforcement Learning Framework for Free-Form Pipe Routing in Aeroengines

    Caicheng Wang +6

  6. cs.LG 2026-05-20 reviewed
    Self-distillation balances consensus across views to cut noise from privileged signals

    AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals

    Duy Nguyen +9

  7. cs.LG 2026-05-20 reviewed
    Hard labels beat soft labels with sparse annotator votes

    Same Target, Different Basins: Hard vs. Soft Labels for Annotator Distributions

    Mirerfan Gheibi +1

  8. cs.CR 2026-05-20 reviewed
    LLM compilation creates hidden backdoor attack surface

    Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs

    Yifei Wang +5

  9. math.OC 2026-05-20 reviewed
    Weak-form latent models cut PDE optimization time by five orders

    Time-Dependent PDE-Constrained Optimization via Weak-Form Latent Dynamics

    April Tran +3

  10. cs.LG 2026-05-20 reviewed
    Localization method builds Transformers from local kernels

    The General Theory of Localization Methods

    Congwei Song

  11. cs.CV 2026-05-20 reviewed
    Autoregressive diffusion cuts video restoration latency to seconds

    Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models

    Taesung Kwon +3

  12. cs.LG 2026-05-20 reviewed
    Local updates cut Shapley recompute cost by 1000 times

    Dynamic Shapley Computation

    Xuan Yang +3

  13. cs.LG 2026-05-20 reviewed
    CDF inversion fixes uneven Pareto front sampling

    SURF: Steering the Scalarization Weight to Uniformly Traverse the Pareto Front

    Liuyuan Jiang +2

  14. cs.LG 2026-05-20 reviewed
    Nested concept models reduce intervention costs to O(log K)

    Matryoshka Concept Bottleneck Models

    Ziye Chen +4

  15. cs.LG 2026-05-20 reviewed
    Latent analogies compose optimal plans for unseen goals in offline RL

    Compositional Transduction with Latent Analogies for Offline Goal-Conditioned Reinforcement Learning

    Junseok Kim +3

  16. cs.LG 2026-05-20 reviewed
    Vision model separates content from style to assure landing safety

    Mechanistic Interpretability for Learning Assurance of a Vision-Based Landing System

    Romeo Valentin +3

  17. cs.CL 2026-05-20 reviewed
    Self-training amplifies surface markers while deep syntax dies

    Self-Training Doesn't Flatten Language -- It Restructures It: Surface Markers Amplify While Deep Syntax Dies

    Ming Liu

  18. cs.LG 2026-05-20 reviewed
    Failure notes lift diagnostic AI accuracy up to 7%

    MedExpMem: Adapting Experience Memory for Differential Diagnosis

    Qianhan Feng +6

  19. cs.LG 2026-05-20 reviewed
    Unlearning by shifting erased points to retained semantic neighbors

    Approximate Machine Unlearning through Manifold Representation Forgetting Guided by Self Mode Connectivity

    Weiqi Wang +4

  20. stat.ML 2026-05-20 reviewed
    Adaptive kernels and LOOCV improve RBF KAN models

    Adaptive RBF-KAN: A Comparative Evaluation of Dynamic Shape Parameters in Kolmogorov-Arnold Networks

    Roberto Cavoretto +3

  21. cs.LG 2026-05-20 reviewed
    Five features and six moves classify upper-limb EMG for prosthetics

    Unsupervised clustering and classification of upper limb EMG signals during functional movements: a data-driven

    L. F. Salazar \'Alvarez +3

  22. cs.LG 2026-05-20 reviewed
    Reversed updates raise Q-learning rewards from 9% to 79% in hard MDPs

    ReversedQ: Opportunities for Faster Q-Learning in Episodic Online Reinforcement Learning

    Sofia R. Miskala-Dinc +1

  23. cs.LG 2026-05-20 reviewed
    Three-stream GNN cuts MLIP energy errors by 57% at 20K samples

    TriForces: Augmenting Atomistic GNNs for Transferable Representations

    Ali Ramlaoui +6

  24. cs.LG 2026-05-20 reviewed
    AI surrogate emulates ocean tipping 465 times faster

    Deep Learning Surrogates for Emulating Stochastic Climate Tipping Dynamics

    Adeline Hillier +5

  25. cs.AI 2026-05-20 reviewed
    JAX simulator runs Mahjong at 2 million steps per second

    Mahjax: A GPU-Accelerated Mahjong Simulator for Reinforcement Learning in JAX

    Soichiro Nishimori +5

  26. cs.LG 2026-05-20 reviewed
    Small models copy last CoT number for 89-92% of arithmetic accuracy

    The Readout Shortcut: Positional Number Copying Dominates Arithmetic CoT Readout in Small Language Models

    Ming Liu

  27. cs.MA 2026-05-19 reviewed
    State management beats workspace isolation in multi-agent tasks

    Multi-agent Collaboration with State Management

    Mengyang Liu +4

  28. stat.ML 2026-05-19 reviewed
    Overlapping nuclear norms recover subgroup low-rank geometry

    Group-Aware Matrix Estimation and Latent Subspace Recovery

    Hamza Golubovic +3

  29. cs.LG 2026-05-19 reviewed
    Logit averaging in GRPO matches KL-regularized accuracy

    Complementing reinforcement learning with SFT through logit averaging in the post training of LLMs

    Xingwei Gan +1

  30. stat.ML 2026-05-19 reviewed
    Bandits learn smooth graph payoffs scaling only with effective dimension

    Spectral bandits for smooth graph functions with applications in recommender systems

    Tom\'a\v{s} Koc\'ak +4

  31. cs.LG 2026-05-19 reviewed
    Learn image-space generators matching latent-process marginals

    Latent Process Generator Matching

    Lukas Billera +2

  32. stat.ML 2026-05-19 reviewed
    Transfer learning reaches O(m^(-(α+1)/d)) rate for d>3

    Sample Complexity of Transfer Learning: An Optimal Transport Approach

    Haoyang Cao +3

  33. cs.LG 2026-05-19 reviewed
    Open seismic dataset trains generative models for inversion

    OpenSeisML: Open Large-Scale Real Seismic and well-log Dataset for Generative AI

    Ipsita Bhar +4

  34. cs.LG 2026-05-19 reviewed
    Geometric axioms explain neural network mechanisms

    Axiomatizing Neural Networks via Pursuit of Subspaces

    Mehmet Yamac +6

  35. cs.LG 2026-05-19 reviewed
    SVD preconditioning beats full fine-tuning at equal parameter count

    FuRA: Full-Rank Parameter-Efficient Fine-Tuning with Spectral Preconditioning

    Yequan Zhao +5

  36. cs.LG 2026-05-19 reviewed
    Optimizer mixes local and global moments to blend AdamW and SGD

    Ada2MS: A Hybrid Optimization Algorithm Based on Exponential Mixing of Elementwise and Global Second-Moment Estimates

    Meng Zhu +2

  37. cs.LO 2026-05-19 reviewed
    Proofs verified by checking natural language modules separately

    Pseudo-Formalization for Automatic Proof Verification

    Slim Barkallah +4

  38. cs.AI 2026-05-19 reviewed
    LLM agent accuracy drops to 0.54-0.62 without labels

    AgentAtlas: Beyond Outcome Leaderboards for LLM Agents

    Parsa Mazaheri +1

  39. cs.LG 2026-05-19 reviewed
    Tri-stage training cuts multimodal edge energy by 33x

    FusionSense: Tri-Stage Near-Sensor Learning for Runtime-Adaptive Multimodal Edge Intelligence

    Sanggeon Yun +7

  40. cs.CV 2026-05-19 reviewed
    AI models lag behind text-only on 3D brain MRI benchmark

    NeuroQA: A Large-Scale Image-Grounded Benchmark for 3D Brain MRI Understanding

    Mohammad H. Abbasi +14

    5 Piths
  41. cs.LG 2026-05-19 reviewed
    Compact neural net edges FIB-4 on advanced MASLD fibrosis detection

    Machine-Learning-Enhanced Non-Invasive Testing for MASLD Fibrosis: Shallow-Deep Neural Networks Versus FIB-4, Tabular Foundation Models, and Large Language Models

    Athanasios Angelakis +3

  42. cs.LG 2026-05-19 reviewed
    Quadratic approx yields private fine-tuning via exact normal sampling

    An exponential mechanism based on quadratic approximations for fine-tuning machine learning models with privacy guarantees

    Hoang Tran +5

  43. cs.LG 2026-05-19 reviewed
    Online conformal prediction can keep its calibration guarantees when feedback about past…

    Online Conformal Prediction with Corrupted Feedback

    Bowen Wang +2

  44. cs.LG 2026-05-19 reviewed
    Neurons encode exact Maxwell solutions for fast sparse field reconstruction

    Fast Reconstruction of Exact Maxwell Dynamics from Sparse Data

    Dan DeGenaro +6

  45. cs.LG 2026-05-19 reviewed
    Verbal feedback in RL makes LLM simulations more human-like

    Reinforcing Human Behavior Simulation via Verbal Feedback

    Weiwei Sun +15

  46. cs.LG 2026-05-19 reviewed
    Min-gate fuses diffusion models to catch all four OOD shifts

    Tippett-minimum Fusion of Representation-space Diffusion Models for Multi-Encoder Out-of-Distribution Detection

    Neelkamal Bhuyan

  47. cs.LG 2026-05-19 reviewed
    10,000-year cyclone catalog reproduces observed track densities

    A 10,000-Year Global Stochastic Tropical Cyclone Catalog with Wind-Dependent Track Transitions (WHITS)

    Jennifer Nakamura +1

  48. cs.AI 2026-05-19 reviewed
    New metrics score uncertainty-augmented systems as one proper rule

    ECUAS$_n$: A family of metrics for principled evaluation of uncertainty-augmented systems

    Lautaro Estienne +4

  49. cs.AI 2026-05-19 reviewed
    ECUAS_n metrics score uncertainty-augmented systems with one tunable rule

    ECUAS$_n$: A family of metrics for principled evaluation of uncertainty-augmented systems

    Lautaro Estienne +4

  50. cs.LG 2026-05-19 reviewed
    ZEBRA keeps 94% of quality on half an LLM budget

    ZEBRA: Zero-shot Budgeted Resource Allocation for LLM Orchestration

    May Hamri +1