Machine Learning (ML) Papers

New Machine Learning (ML) papers from supervised, unsupervised. Thank you to arXiv for use of its open access interoperability.

[Machine Learning (ML) Papers @Memoirs]

Gate-Zero Growth: A Geometric Framework for Function-Preserving Continual Learning

Dante Lok
https://t.co/fPTV6BLT53 [𝚌𝚜.𝙻𝙶 𝚌𝚜.𝙰𝙸]

[Machine Learning (ML) Papers @Memoirs]

Probabilistic Physics-Informed Neural Networks for Estimating Heterogeneous Elastic Properties from Low-Resolution and Noisy Displacement Data

Tatthapong Srikitrungruang, Jaesung Lee
https://t.co/F0ZoFXZnyS [𝚌𝚜.𝙻𝙶 𝚜𝚝𝚊𝚝.𝙼𝙻]

[Machine Learning (ML) Papers @Memoirs]

CASP: Learning-Augmented Offline Approximation with Verifiable Certificates and Bounded-Loss PAC Guarantees

Haifeng Li, Mo Hai
https://t.co/Mtbt8utX4U [𝚌𝚜.𝙻𝙶]

[Machine Learning (ML) Papers @Memoirs]

Muse: Representation Geometry of Muon Beyond Normalized Momentum

Da Chang, Qiankun Shi, Lvgang Zhang, Di He, Yaoshuai Ma, Ganzhao Yuan, Yongxiang Liu
https://t.co/lXBQ84YLYY [𝚌𝚜.𝙻𝙶]

[Machine Learning (ML) Papers @Memoirs]

xHC: Expanded Hyper-Connections

Xiangdong Zhang, Xiaohan Qin, Sunan Zou, Tuo Dai, Xiaoming Shi, Huaijin Wu, Yebin Yang, Zhuo Xia, Shaofeng Zhang, Lin Yao, Yuliang Liu, Yu Cheng, Junchi Yan
https://t.co/mGyLnv73DN [𝚌𝚜.𝙻𝙶 𝚌𝚜.𝙲𝙻]
💬Project: https://t.co/h8anThNj40

[Machine Learning (ML) Papers @Memoirs]

A Continuous-Time Reinforcement Learning Framework for Fine-Tuning Discrete Diffusion Models

Zikun Zhang, Jiayuan Sheng, David D. Yao, Wenpin Tang
https://t.co/CGeQ7cpGTc [𝚌𝚜.𝙻𝙶]

[Machine Learning (ML) Papers @Memoirs]

Adaptive Runge-Kutta Step Control Buys Training Loss, Not Generalization: An Honest Compute-Matched Study of RK-Adam Optimizers

Akhilesh Gogikar
https://t.co/NLbTkIv9e1 [𝚌𝚜.𝙻𝙶 𝚖𝚊𝚝𝚑.𝙾𝙲 𝚜𝚝𝚊𝚝.𝙼𝙻]
💬Code: https://t.co/ricGlN2Qly

[Machine Learning (ML) Papers @Memoirs]

Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards

Yuxuan Zhu, Rohan Alur, Daniel Kang
https://t.co/sLNBTZC2jt [𝚌𝚜.𝙻𝙶 𝚌𝚜.𝙰𝙸]

[Machine Learning (ML) Papers @Memoirs]

Interleaved Noise Injection Improves Clean, Corrupted, and OOD Performance

Matt L. Wiemann, Peter Melchior, Andrew K. Saydjari
https://t.co/4q91soM7fp [𝚌𝚜.𝙻𝙶]

[Machine Learning (ML) Papers @Memoirs]

Depth-Dependent Hidden-State Collapse in Dynamical System Autoencoders for LiDAR Point-Cloud Classification

Patricia Medina, Hy P. G. Lam
https://t.co/kGSULvHul0 [𝚌𝚜.𝙻𝙶 𝚌𝚜.𝙲𝚅]
💬Submitted to the 2026 IEEE High Performance Extreme Computing Conference (HPEC 2026)

[Machine Learning (ML) Papers @Memoirs]

Active Real-World Factor-Based Evaluation for Generalist Robot Policies

Andrew Liao, Hanchen Cui, Karthik Desingh, Aryan Deshwal
https://t.co/lh29hRan1u [𝚌𝚜.𝙻𝙶 𝚌𝚜.𝚁𝙾]

[Machine Learning (ML) Papers @Memoirs]

HyperShadow: A Benchmark for Detecting 3D Projections of Higher-Dimensional Spatial Objects

Akshay Sasi
https://t.co/CRY3LhqqvI [𝚌𝚜.𝙻𝙶 𝚌𝚜.𝙲𝙶]
💬Code: https://t.co/GDBVAoMwG3.

[Machine Learning (ML) Papers @Memoirs]

Adaptive Ad Load Design for Sponsored Search Markets: Evidence, Theory, and Deployment

Mohammad Rashid, Hema Yoganarasimhan
https://t.co/sVkOMN3MFF [𝚌𝚜.𝙻𝙶 𝚎𝚌𝚘𝚗.𝙶𝙽]

[Machine Learning (ML) Papers @Memoirs]

LATTICE: Graph Self-Supervised Learning for Multimodal Spatial Omics Integration

Jagan Mohan Reddy Dwarampudi, Veena Kochat, Suresh Satpati, Kunal Rai, Tania Banerjee
https://t.co/u45yyvsmKW [𝚌𝚜.𝙻𝙶 𝚚-𝚋𝚒𝚘.𝙶𝙽]

[Machine Learning (ML) Papers @Memoirs]

Integration Matters: Rollout-Based Training for Constrained Diffusion Models

Xiaoxuan Liang, Saeid Naderiparizi, Berend Zwartsenberg, Frank Wood
https://t.co/JosVP6XIky [𝚌𝚜.𝙻𝙶 𝚌𝚜.𝙰𝙸]

[Machine Learning (ML) Papers @Memoirs]

A Noise-Robust Elicit-to-Optimize Framework for Distortion Riskmetrics via Inverse Reinforcement Learning

Yang Liu, Yuhao Liu, Yunran Wei
https://t.co/x1lIQV8Zjh [𝚌𝚜.𝙻𝙶 𝚚-𝚏𝚒𝚗.𝚁𝙼]

[Machine Learning (ML) Papers @Memoirs]

Supervised Fine-Tuning vs. In-Context Learning: An Equilibrium Analysis of LLM Personalization under Congestion

Fengzhuo Zhang, Zhuoran Yang, Dirk Bergemann
https://t.co/UxSLZCWnq8 [𝚌𝚜.𝙻𝙶 𝚎𝚌𝚘𝚗.𝚃𝙷 𝚜𝚝𝚊𝚝.𝙼𝙻]

[Machine Learning (ML) Papers @Memoirs]

Dysco: Dynamic Subspace Boosting to Mitigate LoRA Interference in Federated Learning

Haobo Zhang, Jiankun Wang, Suraj Rajendran, Weishen Pan, Lam Tsoi, Yong Chen, Fei Wang, Jiayu Zhou
https://t.co/WWmGxNoWTo [𝚌𝚜.𝙻𝙶]

[Machine Learning (ML) Papers @Memoirs]

Learning Who to Treat When Treatment is Missing

Johnna Sundberg, Rayid Ghani, Eli Ben-Michael, Edward Kennedy
https://t.co/ePwYoRaoyu [𝚌𝚜.𝙻𝙶 𝚜𝚝𝚊𝚝.𝙼𝙴]

[Machine Learning (ML) Papers @Memoirs]

Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values

Jan Betley, Johannes Treutlein, Jan Dubiński, Harry Mayne, Karol Gałązka, Niels Warncke, Anna Sztyber-Betley, Owain Evans
https://t.co/YsVz4Ujbpi [𝚌𝚜.𝙻𝙶 𝚌𝚜.𝙰𝙸 𝚌𝚜.𝙲𝚁]