Machine Learning

Papers filed under cs.LG on arXiv, each one already summarized by Paperlayer. Open any of them to read the summary beside the original PDF, with every point linked to the line, figure, or table it came from.

Search paper metadata (including unsummarized papers)

19,741 to 19,800 of 19,970

MuScriptor: An Open Model for Multi-Instrument Music Transcription
Simon Rouard, Michael Krause, Axel Roebel +2
cs.SDcs.LGarXiv:2607.08168v22026
On Locality and Length Generalization in Visual Reasoning
Pulkit Madan, Sanjay Haresh, Reza Ebrahimi +3
cs.CVcs.AIcs.LGarXiv:2607.09061v12026
Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes
Minh-Quan Le, Armand Comas, Alexandros Lattas +7
cs.LGarXiv:2607.13188v12026
Smarter and Cheaper at Once: Byte-Exact KV-Cache Grafting Turns a Frozen Small Model into a Verified-Knowledge Flywheel
Sietse Schelpe
cs.CLcs.AIcs.LGarXiv:2607.14431v12026
Understanding Reasoning from Pretraining to Post-Training
Jingyan Shen, Ang Li, Salman Rahman +4
cs.LGcs.AIcs.CLarXiv:2607.16097v22026
Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization
Weiwen Xu, Jia Liu, Hou Pong Chan +4
cs.LGcs.AIcs.CLarXiv:2607.14614v12026
When Does Muon Help Agentic Reinforcement Learning?
Kai Ruan, Jinghao Lin, Zihe Huang +4
cs.LGcs.AIarXiv:2607.16169v42026
Generated Contents Enrichment
Mahdi Naseri, Jiayan Qiu, Zhou Wang
cs.CVcs.LGarXiv:2405.03650v42024
PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation
Ebenezer Tarubinga
cs.CVcs.AIcs.LGarXiv:2607.03068v12026
Exploring the Design Space of Reward Backpropagation for Flow Matching
Ruoyu Wang, Boye Niu, Xiangxin Zhou +3
cs.LGarXiv:2606.11075v12026
RL-Index: Reinforcement Learning for Retrieval Index Reasoning
Yongjia Lei, Nedim Lipka, Zhisheng Qi +7
cs.IRcs.AIcs.LGarXiv:2606.16316v22026
Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation
Zhilin Huang, Hang Gao, Ziqiang Dong +6
cs.LGarXiv:2606.18844v12026
Demystifying Training-Time Augmentation for Data-Constrained Language Model Pretraining
Michael K. Chen, Xikun Zhang, Fan Bai +2
cs.LGcs.AIcs.CLarXiv:2606.16246v22026
Improving Text-to-Music Generation with Human Preference Rewards
Yonghyun Kim, Junwon Lee, Haiwen Xia +2
cs.SDcs.AIcs.LGarXiv:2606.21670v12026
RoPE-Aware Bit Allocation for KV-Cache Quantization
Fengfeng Liang, Yuechen Zhang, Jiaya Jia
cs.LGcs.CLarXiv:2606.24033v12026
Fast LeWorldModel
Yuntian Gao, Xiangyu Xu
cs.LGcs.CVcs.ROarXiv:2606.26217v12026
Hallucination in World Models is Predictable and Preventable
Nicklas Hansen, Xiaolong Wang
cs.LGcs.CVcs.ROarXiv:2606.27326v12026
Taste-aware music retrieval from audio embeddings
Matteo Spanio, Antonio Rodà
cs.SDcs.IRcs.LGarXiv:2607.03296v12026
ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation
Kaifeng Zhao, Mathis Petrovich, Haotian Zhang +3
cs.GRcs.CVcs.LGarXiv:2607.08741v12026
A Sovereign, Open-Source Foundation Model for German and English
Soofi-Team, :, Benedikt Droste +30
cs.CLcs.AIcs.LGarXiv:2607.09424v32026
PAST-TIDE: Prototype-Anchored Statement Tuning with Topic-Invariant Normalization for Stance Detection
Md. Shakhoyat Rahman Shujon, MD Jahid Hasan Jim, Md. Milon Islam +2
cs.CLcs.LGarXiv:2607.04690v12026
Simplified Sparse Attention via Gist Tokens
Yuzhen Mao, Michael Y. Li, Emily B. Fox
cs.LGarXiv:2604.20920v22026
Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction
Chenguang Wang, Ming Li, Xinyue Zeng +4
cs.CLcs.AIcs.CYarXiv:2606.28186v32026
SPEAR: A Simulator for Photorealistic Embodied AI Research
Mike Roberts, Renhan Wang, Rushikesh Zawar +10
cs.CVcs.AIcs.GRarXiv:2607.06701v12026
Wan-Streamer v0.2: Higher Resolution, Same Latency
Lianghua Huang, Zhi-Fan Wu, Yupeng Shi +23
cs.CVcs.AIcs.GRarXiv:2607.04443v32026
SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History
Zhiwei Li, Yong Hu
cs.LGarXiv:2606.08671v32026
LLM Program Optimization via Retrieval Augmented Search
Sagnik Anupam, Alexander Shypula, Osbert Bastani
cs.LGarXiv:2501.18916v22025
When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time Scaling
Yong Yi Bay, Kathleen A. Yearick
cs.LGcs.AIcs.CLarXiv:2606.28661v12026
Parameter-Efficient Quantum-Inspired Fast Weight Programmers for Traffic-Matrix Forecasting
Kuo-Chung Peng, Jiun-Cheng Jiang, Chun-Hua Lin +3
quant-phcs.AIcs.LGarXiv:2606.27821v12026
SciForma: Structure-Faithful Generation of Scientific Diagrams
Yuxuan Luo, Peng Zhang, Xinjie Zhang +3
cs.CVcs.GRcs.LGarXiv:2607.18091v12026
Hard Cases, Bad Labels: Testing Error Exposure and Error Location in Uncertainty Sampling Under Bounded Label Noise
John Myron Uy
cs.LGarXiv:2608.13601v12026
No Universal Signal Predicts Sample-Level LLM Regression under Version Updates
Jia Sheng, Yiwei Lu
cs.AIcs.CLcs.LGarXiv:2608.13607v12026
HI-MeshGraphNets: Efficient and Accurate Mesh-based Physics Learning with Hierarchical Multi-scale Graph Neural Networks
SiHun Lee, Dong-Hyuk Park, Taesoo Bang +1
cs.LGarXiv:2608.13827v12026
Trajectory Dynamics in Self-Supervised Learning Latent Space for Audio Deepfake Detection
Tomás Andrade Weber
eess.AScs.LGcs.SDarXiv:2608.13817v12026
Language-Specific Gaps in AI Safety Training Datasets
Chialuka Prisca-Mary Onuoha, Bright Etornam Sunu, Rashidat Sikiru
cs.CYcs.LGarXiv:2608.13695v12026
The Integer Alibi: Localizing Cross-Kernel Divergence in INT8-Quantized LLM Inference
Teng-Ruei Chen
cs.LGarXiv:2608.13756v12026
Does ISO-Grounded NFR Specification Improve LLM Code Generation? A Comparison of Rich and Structured Interventions against a Natural-Language Baseline
Joào Pedro Monteiro Pereira, Vinicius Cardoso Garcia
cs.SEcs.AIcs.LGarXiv:2608.13742v12026
A Calibrated Test of Internal Action Maps: State Signals Without Global Affine Closure
Dekun Yang
cs.AIcs.CLcs.LGarXiv:2608.13626v12026
High-dimensional nonparametric changepoint detection via low-rank degree-two density projection
Guoqing Zhang, Zhaixin Chen
cs.LGstat.MLarXiv:2608.13922v12026
How Fast Can Reward Models Score? A Systems Study of C++ and PyTorch Inference Runtimes for RLHF
Venkata Naga Sai Vishnu Rohit Pulipaka, Anish Katta, Deva Rohit Reddy Peddireddy
cs.LGarXiv:2607.19712v12026
FlashRT: Agent Harness for Guiding Agents to Deploy Real-Time Multimodal Applications
Krish Agarwal, Zhuoming Chen, Yanyuan Qin +3
cs.LGarXiv:2607.18171v22026
Differentiable Logic Gate Networks for Low-Latency EEG Classification on Edge Devices
Shyamal Y. Dharia, Stephen D. Smith, Camilo E. Valderrama
cs.LGcs.AIarXiv:2607.18149v12026
Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift
Zitong Huang, Gustavo Lucas Carvalho, Deqing Fu +1
cs.CLcs.LGarXiv:2607.17524v12026
DriveDNA: A Large-Scale Multimodal Naturalistic Driving Dataset and Benchmark for Driving Style Identification
Yuhang Wang, Lingyao Li, Hao Zhou
cs.LGarXiv:2607.23822v12026
AMRD: Adaptive Multi-Teacher Relational Distillation for Lightweight Speech Emotion Recognition
Yuqi Li, Yi-Cheng Lin, Xianglong Wang +5
cs.LGarXiv:2607.25289v12026
Where Quality Breaks in Compressed Short-Text Generation: Staged Bottleneck Localization
Alexey Gavrilov, Alan-Barsag Gazzaev, Sergey Muravyov
cs.CLcs.LGarXiv:2607.24176v12026
A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever
Sietse Schelpe
cs.CLcs.AIcs.IRarXiv:2607.23806v12026
Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations
Pere Martra, Eugenio Martínez Cámara, Alfonso Ureña López
cs.CLcs.CYcs.LGarXiv:2607.28319v12026
H$^2$SD: Hybrid Hindsight Self-Distillation
Qiye Cai, Yichuan Ma, Peiji Li +6
cs.LGcs.CLarXiv:2607.18955v42026
WorldDiT: A Unified Diffusion Architecture for World and Action Modeling
Sen Wang, R. Gnana Praveen, Bidhan Roy +1
cs.LGcs.ROarXiv:2607.23909v22026
Where Should Optimizer State Live? Tiered State Allocation for Memory-Efficient Mixture-of-Experts Training
Nuemaan Malik
cs.LGcs.AIarXiv:2607.19058v22026
OPERA: Offline Policy-guided Expert Routing and Adaptation for Universal Biomedical Image Analysis
Zihan Li, Feiyang Liu, Dandan Shan +2
cs.CVcs.AIcs.LGarXiv:2607.25108v12026
LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks
Tianzhu Ye, Li Dong, Guanheng Chen +4
cs.LGcs.CLarXiv:2607.18110v12026
Distilled Reinforcement Learning for LLM Post-training
Chen Wang, Zhaochun Li, Jionghao Bai +4
cs.LGcs.AIarXiv:2607.17247v12026
CriPO: Enhancing Rubric-based RL via Self-Distillation
Mingxuan Xia, Yuhang Yang, Chao Ye +7
cs.LGcs.AIarXiv:2607.18082v32026
WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting
Zhaokai Wang, Tianlin Gui, Jiayuan Rao +3
cs.AIcs.CLcs.LGarXiv:2607.18084v12026
DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations
Jiazhen Jiang, Boxi Cao, Lingyong Yan +6
cs.AIcs.CLcs.LGarXiv:2607.19865v12026
Codifying the Judge: Scalable Evaluation via Program Distillation
Tzu-Heng Huang, Shengqi Qiu, Frederic Sala
cs.AIcs.LGarXiv:2607.22561v12026
Towards Robust Reinforcement Learning for Small-Scale Language Model Agents
Md Rezwanul Haque, Md. Milon Islam, Fakhri Karray
cs.AIcs.CLcs.LGarXiv:2607.25091v12026
DataPrep-Bench: Benchmarking LLMs as Training Data Preparators
Hao Liang, Qifeng Cai, Yibo Lin +11
cs.LGcs.CLarXiv:2607.20465v12026

Machine Learning

MuScriptor: An Open Model for Multi-Instrument Music Transcription

On Locality and Length Generalization in Visual Reasoning

Concurrent Image Understanding and Generation: Self-Correcting Coupled Markov Jump Processes

Smarter and Cheaper at Once: Byte-Exact KV-Cache Grafting Turns a Frozen Small Model into a Verified-Knowledge Flywheel

Understanding Reasoning from Pretraining to Post-Training

Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization

When Does Muon Help Agentic Reinforcement Learning?

Generated Contents Enrichment

PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation

Exploring the Design Space of Reward Backpropagation for Flow Matching

RL-Index: Reinforcement Learning for Retrieval Index Reasoning

Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation

Demystifying Training-Time Augmentation for Data-Constrained Language Model Pretraining

Improving Text-to-Music Generation with Human Preference Rewards

RoPE-Aware Bit Allocation for KV-Cache Quantization

Fast LeWorldModel

Hallucination in World Models is Predictable and Preventable

Taste-aware music retrieval from audio embeddings

ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation

A Sovereign, Open-Source Foundation Model for German and English

PAST-TIDE: Prototype-Anchored Statement Tuning with Topic-Invariant Normalization for Stance Detection

Simplified Sparse Attention via Gist Tokens

Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction

SPEAR: A Simulator for Photorealistic Embodied AI Research

Wan-Streamer v0.2: Higher Resolution, Same Latency

SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History

LLM Program Optimization via Retrieval Augmented Search

When More Sampling Hurts: The Modal Ceiling and Correlation Ceiling of Test-Time Scaling

Parameter-Efficient Quantum-Inspired Fast Weight Programmers for Traffic-Matrix Forecasting

SciForma: Structure-Faithful Generation of Scientific Diagrams

Hard Cases, Bad Labels: Testing Error Exposure and Error Location in Uncertainty Sampling Under Bounded Label Noise

No Universal Signal Predicts Sample-Level LLM Regression under Version Updates

HI-MeshGraphNets: Efficient and Accurate Mesh-based Physics Learning with Hierarchical Multi-scale Graph Neural Networks

Trajectory Dynamics in Self-Supervised Learning Latent Space for Audio Deepfake Detection

Language-Specific Gaps in AI Safety Training Datasets

The Integer Alibi: Localizing Cross-Kernel Divergence in INT8-Quantized LLM Inference

Does ISO-Grounded NFR Specification Improve LLM Code Generation? A Comparison of Rich and Structured Interventions against a Natural-Language Baseline

A Calibrated Test of Internal Action Maps: State Signals Without Global Affine Closure

High-dimensional nonparametric changepoint detection via low-rank degree-two density projection

How Fast Can Reward Models Score? A Systems Study of C++ and PyTorch Inference Runtimes for RLHF

FlashRT: Agent Harness for Guiding Agents to Deploy Real-Time Multimodal Applications

Differentiable Logic Gate Networks for Low-Latency EEG Classification on Edge Devices

Token-Level Off-Policy Learning for Faithful Generation Under Distribution Shift

DriveDNA: A Large-Scale Multimodal Naturalistic Driving Dataset and Benchmark for Driving Style Identification

AMRD: Adaptive Multi-Teacher Relational Distillation for Lightweight Speech Emotion Recognition

Where Quality Breaks in Compressed Short-Text Generation: Staged Bottleneck Localization

A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever

Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations

H$^2$SD: Hybrid Hindsight Self-Distillation

WorldDiT: A Unified Diffusion Architecture for World and Action Modeling

Where Should Optimizer State Live? Tiered State Allocation for Memory-Efficient Mixture-of-Experts Training

OPERA: Offline Policy-guided Expert Routing and Adaptation for Universal Biomedical Image Analysis

LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks

Distilled Reinforcement Learning for LLM Post-training

CriPO: Enhancing Rubric-based RL via Self-Distillation

WorldCupArena: Fine-Grained Evaluation of Language Models and Deep-Research Agents on Football Forecasting

DocOps: A Verifiable Benchmark for Autonomous Agents in Complex Document Operations

Codifying the Judge: Scalable Evaluation via Program Distillation

Towards Robust Reinforcement Learning for Small-Scale Language Model Agents

DataPrep-Bench: Benchmarking LLMs as Training Data Preparators