Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[19/19]:
- SAT-ACT: Learning CDCL Branching from Outcome-Derived Action Preferences
Zhenchao Sun, Chongyang Tao, Ping Lu, Tongkai Lu, Jianling Gao, Shuai Ma
https://arxiv.org/abs/2610.41290 https://mastoxiv.page/@arXiv_csAI_bot/117545944677737892

- Answer Correction with Verifiable Rewards: A Gemma-Family Study of Multi-View Driving QA
T N Rickesh, Pranav Vinodh, Sowmya Kamath S
https://arxiv.org/abs/2611.00828

- Fewer Tokens, More Answers: Verifiable-Reward Tuning of an Ornith-Style VLM for Multi-View Drivin...
T N Rickesh, Pranav Vinodh, Sowmya Kamath S
https://arxiv.org/abs/2611.00833

- How Close to the Theme? Similarity-Label Conditioning for Game Music Generation
Shangxuan Luo, Zixun Guo, Jinjie Shi, Joshua Reiss
https://arxiv.org/abs/2611.01047

- Write Facts the Way Models Read Them: Lifting the Two-Hop Curse
Zhiyun Shi
https://arxiv.org/abs/2611.01519

- Seeing Why: Exact Evidence Maps for Quantum and Optical Image Classifiers
Teerawat Tongloy, Rangsan Jomtarak
https://arxiv.org/abs/2611.01993

- GatedV: Self-Gated Values for Transformer Language Models
Li-Ming Yu, Hongyu Zhou
https://arxiv.org/abs/2611.02145

- CR-Bench-v2: Evaluating the Real-World Utility of AI Code Review Agents
Kristen Pereira, Neelabh Sinha, Rajat Ghosh, Debojyoti Dutta
https://arxiv.org/abs/2611.02566

- Why Tabular Foundation Models Excel on Relational Data They Have Never Seen
Linjie Xu, Yiqun Hu, Jixiang He, David Wipf
https://arxiv.org/abs/2611.02936

toXiv_bot_toot

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[18/19]:
- Agentic Detection of Online Conspiracies
Lior Biton, Oren Tsur
https://arxiv.org/abs/2609.30250 https://mastoxiv.page/@arXiv_csCL_bot/117330879124024244

- StoreBench: A Live-Commerce Environment for Evaluating and Training Autonomous Operator Agents
Daksh Raghuvanshi, Ved Vedere, Yifan Wang
https://arxiv.org/abs/2610.10942 https://mastoxiv.page/@arXiv_csAI_bot/117409808775022673

- Scaling Laws for Multimodal Data Mixtures
Khandelwal, Tarun, Xu, Schlag, Farnadi, Reddy, Zettlemoyer, Bosselut
https://arxiv.org/abs/2610.14423 https://mastoxiv.page/@arXiv_csCL_bot/117438372633852466

- ToPA: Block-wise Toeplitz Adaptation for Expressive and Efficient Fine-Tuning
Sicong Li, Qianqian Xu, Zhiyong Yang, Zitai Wang, Longtao Huang, Xiaochun Cao, Qingming Huang
https://arxiv.org/abs/2610.22883

- SPELUNKA: A Framework for Finding Unanticipated Associations in Vision-Language Models
Parent, Agarwal, Alhamoud, Moraitaki, Javed, Gerych, Ghassemi
https://arxiv.org/abs/2610.23979 https://mastoxiv.page/@arXiv_csCV_bot/117472440829454557

- When Do Repetition Loops Lock? Truncation Sampling, Bounded Penalties, and a Blind Spot in DRY
Yichuan Chen, Xin Wang
https://arxiv.org/abs/2610.24715 https://mastoxiv.page/@arXiv_csCL_bot/117472479760640463

- Near Minimax Rates for Quantile Distributional Reinforcement Learning
Zijie Cheng, Zhihua Zhang
https://arxiv.org/abs/2610.29595 https://mastoxiv.page/@arXiv_statML_bot/117483544092824303

- No Frames, Just Frequencies: Bandwidth-Efficient Deployment-Time Adaptation for Smart Glasses
Francesco Corti, Moritz Becker, Olga Saukh
https://arxiv.org/abs/2610.29607 https://mastoxiv.page/@arXiv_csCV_bot/117483688998077135

- Pretraining Knows What, Simulation Teaches How: Compositional Generalization for Agentic Robotics
Benjamin Pikus, et al.
https://arxiv.org/abs/2610.35817 https://mastoxiv.page/@arXiv_csRO_bot/117512213764471184

- Dexterous In-Hand Object Pose Reaching with Learned Safety Filters
Ian Chuang, Hiya Shah, Vamsi Chilamkur, Iman Soltani, Claire Tomlin
https://arxiv.org/abs/2610.37652 https://mastoxiv.page/@arXiv_csRO_bot/117517717733101750

- Opening the Box Changes the Cat: LLMs Detect Chain-of-Thought Monitoring - What now?
Amir Jalilifard, Marcos Medeiros Raimundo, Anderson Rocha
https://arxiv.org/abs/2610.40946 https://mastoxiv.page/@arXiv_csAI_bot/117545762052293779

toXiv_bot_toot

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[17/19]:
- A $(3+\epsilon)$-Approximation for Fair $k$-Means and a Matching Lower Bound
Kangke Cheng, Guanlin Mo, Shihong Song, Hu Ding
https://arxiv.org/abs/2609.07974 https://mastoxiv.page/@arXiv_csCG_bot/117239910606338319

- Deposon: An Auditable, Conservation-Guaranteed, Game-Theoretically Tested Scattering Layer over L...
Qihao Yuan
https://arxiv.org/abs/2609.09001 https://mastoxiv.page/@arXiv_csAI_bot/117240633959418196

- Optimal Value Inference for Reinforcement Learning
Nan Lu, Ethan Lee, Ruicheng Ao, David Simchi-Levi, Junwei Lu
https://arxiv.org/abs/2609.09981 https://mastoxiv.page/@arXiv_statML_bot/117245778723460200

- A Sharp Barrier of Consistent Submodular Maximization: Any Improvement over $2-\sqrt{2}$ Entails ...
Shi Fu, Qixin Zhang, Dacheng Tao
https://arxiv.org/abs/2609.09986 https://mastoxiv.page/@arXiv_csDS_bot/117245609243805221

- An explicit solution of the five-expert prediction PDE and the exact optimality set of COMB
Jeff Calder, Nadejda Drenska
https://arxiv.org/abs/2609.14892 https://mastoxiv.page/@arXiv_mathAP_bot/117274376411705184

- Efficient Robust Learning at the Information-Theoretic Limit
Adam R. Klivans, Konstantinos Stavropoulos, Sergei Tikhonov, Arsen Vasilyan
https://arxiv.org/abs/2609.17655 https://mastoxiv.page/@arXiv_csDS_bot/117285300262760896

- The First-Order Oracle Complexity of Lipschitz Convex Optimization in Nondual Settings
Brian Bullins, Crist\'obal Guzm\'an, David Mart\'inez-Rubio, Mathieu Molina
https://arxiv.org/abs/2609.20687 https://mastoxiv.page/@arXiv_mathOC_bot/117291110458727186

- Stable Movement for Nondual Lipschitz Convex Optimization: Efficiency and Nearly Optimal Oracle R...
David Mart\'inez-Rubio, Crist\'obal Guzm\'an
https://arxiv.org/abs/2609.20701 https://mastoxiv.page/@arXiv_mathOC_bot/117291112029648238

- Forecasting Brain Tracer Distribution from Pre-Contrast MRI: A Comparison of Direct Regression an...
Liu, Ottesen, Nguyen, Ringstad, Mossige, Svensson, Kalstad, Bj{\o}rnerud, Eide, Emblem
https://arxiv.org/abs/2609.22377 https://mastoxiv.page/@arXiv_eessIV_bot/117313560764473916

- When Pass@$k$ Crossovers Are Real - and Why: Paired Inference and the Markov Kernel of RLVR
Chen Yang
https://arxiv.org/abs/2609.22547 https://mastoxiv.page/@arXiv_statML_bot/117313640229926373

toXiv_bot_toot

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[16/19]:
- Radial Basis Function Networks as Projection Heads in Self-Supervised Learning
Andreas Schliebitz, Heiko Tapken, Martin Atzmueller
https://arxiv.org/abs/2606.21590 https://mastoxiv.page/@arXiv_csCV_bot/116798764835237364

- Q-Score: A Quantum-Native Scoring Function for Molecular Docking
Kangyu Zheng, Yidong Zhou, Ruihao Li, Zixin Ding, Zhiding Liang, Shaohua Li
https://arxiv.org/abs/2607.09737 https://mastoxiv.page/@arXiv_physicschemph_bot/116917254999917217

- Dense Language Generation Made Simple: Deterministic, Randomized, and Multi-Order Algorithms
Ziyi Cai, Shuangping Li, Yiheng Shen, Kangning Wang, Peng Zhang
https://arxiv.org/abs/2608.01320 https://mastoxiv.page/@arXiv_csDS_bot/117036197586926565

- Behavioral Residualization for Unsupervised Intrusion Detection in Automotive CAN Networks
Chandan Hegde, Mukundh R Reddy, Dr Kumaresh Sheelavant
https://arxiv.org/abs/2608.05548 https://mastoxiv.page/@arXiv_csCR_bot/117053141891102641

- Dual-Node NVIDIA DGX Spark over Tailscale: A Remote-Access Testbed for Distributed LLM Training a...
Vasanth Iyer
https://arxiv.org/abs/2608.07226 https://mastoxiv.page/@arXiv_csAR_bot/117070043428727666

- Who Built This Model? Tracing LLM Lineage via Spectral Fingerprints in Weight Space
Yiwei Chen, Bingqi Shang, Sijia Liu
https://arxiv.org/abs/2608.07786 https://mastoxiv.page/@arXiv_csAI_bot/117075978428170060

- More Accurate, Less Human: Gestalt Grouping in Vision Models
Sudhanva Manjunath Athreya, Sai Phani Kumar Malladi
https://arxiv.org/abs/2608.10195 https://mastoxiv.page/@arXiv_csCV_bot/117081445304110205

- Fine-Tuning VLAs with Self-Demonstrated Generative Control for Multi-Task Manipulation
Prachi Garg, Steve Xing, Prahit Yaugand, Saurabh Gupta, Derek Hoiem
https://arxiv.org/abs/2608.19490 https://mastoxiv.page/@arXiv_csRO_bot/117132466493971150

- A Layered Simplex Architecture for Large Alphabets
Meir Feder, Yaniv Fogel, Ruediger Urbanke
https://arxiv.org/abs/2608.19908 https://mastoxiv.page/@arXiv_csIT_bot/117132357765327071

- Explainable Diabetic Retinopathy Classification Using Vision Foundation Models
Abhishek Verma, Anila Krishna, Abhishek Gajanan Bankar, Juan Miguel Lopez Alcaraz
https://arxiv.org/abs/2608.28207 https://mastoxiv.page/@arXiv_csCV_bot/117189175693116340

toXiv_bot_toot

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[15/19]:
- CurEvo: Curriculum-Guided Self-Evolution for Video Understanding
Guiyi Zeng, Junqing Yu, Yi-Ping Phoebe Chen, Chen Xu, Wei Yang, Zikai Song
https://arxiv.org/abs/2604.26707 https://mastoxiv.page/@arXiv_csCV_bot/116492710297370310

- MathlibPR: Pull Request Merge-Outcome Benchmark for Formal Mathematical Libraries
Zixuan Xie, Xinyu Liu, Shangtong Zhang
https://arxiv.org/abs/2605.07147 https://mastoxiv.page/@arXiv_csLO_bot/116554778895380879

- Supersampling Stable Diffusion and Beyond: Training-Free Neural Network Scaling via Signal Interp...
Md Abu Obaida Zishan, Jannatun Noor, Annajiat Alim Rasel
https://arxiv.org/abs/2605.08698 https://mastoxiv.page/@arXiv_csCV_bot/116560799446508660

- TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing
Yuanpeng Li, Gefei Lin, Annie Qu, Rui Miao
https://arxiv.org/abs/2605.11473 https://mastoxiv.page/@arXiv_csAI_bot/116566302485254482

- RecoAtlas: A Benchmark and RL Environment for LLM Recommendation Agents Optimizing Set-Level Utility
Imad Aouali, Flavian Vasile, Clijo Jose, Otmane Sakhi, Alexandre Gilotte, Benjamin Heymann
https://arxiv.org/abs/2605.18805 https://mastoxiv.page/@arXiv_csIR_bot/116605889690384443

- Distill to Think, Foresee to Act: Cognitive-Physical Reinforcement Learning for Autonomous Driving
Yang Wu, Qiang Meng, Zhaojiang Liu, Youquan Liu, Jian Yang, Jin Xie
https://arxiv.org/abs/2605.21139 https://mastoxiv.page/@arXiv_csCV_bot/116611661335850055

- DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation
Lee, Lee, Shin, Jung, Kim, Cho, Kim, Huang, Huang
https://arxiv.org/abs/2605.30350 https://mastoxiv.page/@arXiv_csRO_bot/116656911412510039

- CVE-Conditioned Exploit Generation with LLMs: A Data-Centric Study of Benchmarking and Fine-Tuning
Yiwei Chen, Lichi Li, Kai Cheung, Vinny Parla, Ganesh Sundaram
https://arxiv.org/abs/2606.15123 https://mastoxiv.page/@arXiv_csCR_bot/116758786984426359

- Sparse stochastic digital twins can outperform exact ones
Zongren Zou, Th\'eo Bourdais, Ricardo Baptista, Houman Owhadi
https://arxiv.org/abs/2606.16219 https://mastoxiv.page/@arXiv_csCE_bot/116758612391162542

- Agent trajectories as programs: fingerprinting and programming coding-agent behavior
Hamidah Oderinwale
https://arxiv.org/abs/2606.16988 https://mastoxiv.page/@arXiv_csSE_bot/116758945456715040

toXiv_bot_toot

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[14/19]:
- Helpful to a Fault: Measuring Illicit Assistance in Multi-Turn, Multilingual LLM Agents
Nivya Talokar, Ayush K Tarun, Murari Mandal, Maksym Andriushchenko, Antoine Bosselut
https://arxiv.org/abs/2602.16346 https://mastoxiv.page/@arXiv_csCL_bot/116096765030175227

- Universal Conceptual Structure in Neural Translation: Probing NLLB-200's Multilingual Geometry
Kyle Elliott Mathewson
https://arxiv.org/abs/2603.02258 https://mastoxiv.page/@arXiv_csCL_bot/116169944264485257

- Surprisal-R\'enyi Free Energy
Shion Matsumoto, Ankur Arjun Mali
https://arxiv.org/abs/2603.03405 https://mastoxiv.page/@arXiv_statML_bot/116175791078566362

- SMAT: Staged Multi-Agent Training for Co-Adaptive Exoskeleton Control
Yifei Yuan, Ghaith Androwis, Xianlian Zhou
https://arxiv.org/abs/2603.07618 https://mastoxiv.page/@arXiv_csRO_bot/116204864927890746

- Ethical Fairness in Ubiquitous Health Sensing without Known Attributes
Shaily Roy, Harshit Sharma, Daniel A. Adler, Srijan Sen, Tanzeem Choudhury, Asif Salekin
https://arxiv.org/abs/2603.13373 https://mastoxiv.page/@arXiv_csCY_bot/116243361419960819

- An Alternative Trajectory for Generative AI
Margarita Belova, Yuval Kansal, Yihao Liang, Jiaxin Xiao, Niraj K. Jha
https://arxiv.org/abs/2603.14147 https://mastoxiv.page/@arXiv_csAI_bot/116243645755735147

- Edge AI and TinyML for Resource-Constrained Agriculture: Hardware Platforms, Model Optimization, ...
Riya Samanta, Bidyut Saha, Soumya Kanti Ghosh
https://arxiv.org/abs/2603.15085 https://mastoxiv.page/@arXiv_csET_bot/116243457412600204

- Terminal Fano 4-fold Hypersurfaces via Deep Reinforcement Learning
Marc Truter
https://arxiv.org/abs/2603.15437 https://mastoxiv.page/@arXiv_mathAG_bot/116243584015191639

- Query-Conditioned Evidential Keyframe Sampling for MLLM-Based Long-Form Video Understanding
Yiheng Wang, Lichen Zhu, Yueqian Lin, Yudong Liu, Jingyang Zhang, Hai "Helen" Li, Yiran Chen
https://arxiv.org/abs/2604.01002 https://mastoxiv.page/@arXiv_csCV_bot/116334369631715332

- Score-Based Modeling of Effective Langevin Dynamics with State-Dependent Mobility
Ludovico T. Giorgini
https://arxiv.org/abs/2604.23952 https://mastoxiv.page/@arXiv_statML_bot/116481360732651123

toXiv_bot_toot

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[13/19]:
- A Deep State-Space Model Compression Method using Upper Bound on Output Error
Hiroki Sakamoto, Kazuhiro Sato
https://arxiv.org/abs/2510.14542 https://mastoxiv.page/@arXiv_eessSY_bot/115388618139792730

- DexCanvas: Bridging Human Demonstrations and Robot Learning for Dexterous Manipulation
Xu, Sun, Jing, Dai, Chen, Ma, Sun, Zhao, Yuan, Yi, Zhu, Lu
https://arxiv.org/abs/2510.15786 https://mastoxiv.page/@arXiv_csRO_bot/115405874222088082

- Recovering Geodesic Distances from Noisy Observations
Charles Fefferman, Jonathan Marty, Kevin Ren
https://arxiv.org/abs/2511.13025 https://mastoxiv.page/@arXiv_statML_bot/115570283958706195

- Structured Prompts Improve Evaluation of Language Models
Asad Aali, et al.
https://arxiv.org/abs/2511.20836 https://mastoxiv.page/@arXiv_csCL_bot/115621100060602749

- Which Deep Learner? A Systematic Evaluation of Advanced Deep Forecasting Models Accuracy and Effi...
Eilaf M. A. Babai, Aalaa M. A. Babai, Koji Okamura
https://arxiv.org/abs/2601.02694 https://mastoxiv.page/@arXiv_csNI_bot/115853185968997234

- Quantification of Tail-trimming Effects for Interval CVaR Based Nonlinear Regression
Yulei You, Junyi Liu
https://arxiv.org/abs/2601.11420 https://mastoxiv.page/@arXiv_mathOC_bot/115921112401965182

- Foundation model for particle collision data analysis
Hsu, Zhou, Liu, Xu, Li, Hou, Nachman, Hsu, Mikuni, Chou, Zhang
https://arxiv.org/abs/2601.17126 https://mastoxiv.page/@arXiv_hepex_bot/115966366081405293

- Payoff scaling shapes cooperation in LLM agents across languages
Trung-Kiet Huynh, et al.
https://arxiv.org/abs/2601.19082 https://mastoxiv.page/@arXiv_csAI_bot/115971594577465858

- Emergence of Distortions in High-Dimensional Guided Diffusion Models
Enrico Ventura, Beatrice Achilli, Luca Ambrogioni, Carlo Lucibello
https://arxiv.org/abs/2602.00716 https://mastoxiv.page/@arXiv_statML_bot/116006124035232341

- Deep Learning of Compositional Targets with Hierarchical Spectral Methods
Hugo Tabanelli, Yatin Dandi, Luca Pesce, Florent Krzakala
https://arxiv.org/abs/2602.10867 https://mastoxiv.page/@arXiv_statML_bot/116057005069213631

- JediKG: Return of the Schema
Ivan Diliso, Roberto Barile, Nicola Fanizzi, Claudia d'Amato
https://arxiv.org/abs/2602.14795 https://mastoxiv.page/@arXiv_csAI_bot/116086031280029684

toXiv_bot_toot

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[12/19]:
- Community detection in complex networks via node similarity, graph representation learning, and h...
{\L}ukasz Brzozowski, Grzegorz Siudem, Marek Gagolewski
https://arxiv.org/abs/2303.12212 https://mastoxiv.page/@arXiv_csSI_bot/110071337756537102

- TransfoRhythm: A Transformer Architecture Conductive to Blood Pressure Estimation via Solo PPG Si...
Amir Arjomand, Amin Boudesh, Farnoush Bayatmakou, Kenneth B. Kent, Arash Mohammadi
https://arxiv.org/abs/2404.15352

- Matching with Choice: Menu Design for Patient--Provider Assignment
Naveen Raman, Holly Wiberg
https://arxiv.org/abs/2502.10353 https://mastoxiv.page/@arXiv_csCY_bot/114017928156372980

- Data-Efficient Kernel Methods for Learning Differential Equations and Their Solution Operators: A...
Bamdad Hosseini, Alexander Hsu, Yasamin Jalalian, Juan Felipe Osorio Ramirez, Houman Owhadi
https://arxiv.org/abs/2503.01036 https://mastoxiv.page/@arXiv_statML_bot/114103102978627760

- A Comprehensive Benchmark of Computational Models for Antibody--Antigen Binding Affinity
Zhao, Tang, Cantu, Lee, Stogsdill, Hamdi, Ramesh, An, Jiang, Kim
https://arxiv.org/abs/2506.04235 https://mastoxiv.page/@arXiv_qbioQM_bot/114635272587692818

- LLM Analysis of 150+ Years of German Parliamentary Debates on Migration Reveals a Shift from Post...
Aida Kostikova, Ole P\"utz, Steffen Eger, Olga Sabelfeld, Benjamin Paassen
https://arxiv.org/abs/2509.07274 https://mastoxiv.page/@arXiv_csCL_bot/115179206819209123

- SpellerSSL: Self-Supervised Learning with P300 Aggregation for Speller BCIs
Jiazhen Hong, Geoff Mackellar, Soheila Ghane
https://arxiv.org/abs/2509.19401 https://mastoxiv.page/@arXiv_eessSP_bot/115264422060983320

- Reinforcement Learning based Traffic Signal Control for Queue Minimization: From Lane-based to La...
Anirud Nandakumar, Chayan Banerjee, Lelitha Devi Vanajakshi
https://arxiv.org/abs/2509.21745 https://mastoxiv.page/@arXiv_eessSY_bot/115286907166067669

- FlowDrive: moderated flow matching with data balancing for trajectory planning
Lingguang Wang, \"Omer \c{S}ahin Ta\c{s}, Marlon Steiner, Christoph Stiller
https://arxiv.org/abs/2509.21961 https://mastoxiv.page/@arXiv_csRO_bot/115286989722999762

toXiv_bot_toot

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[11/19]:
- Quantile Propagation Planning for Budgeted Tail-Risk Evaluation
Weijia Han, Zhi Huang, Lisha Qu, Yuanyuan Tan, Jiayue Meng, Wenjun Chen, Liying Liang, Bangjie Deng
https://arxiv.org/abs/2610.41351 https://mastoxiv.page/@arXiv_csLG_bot/117545968860368499

- ISBC: Interpretable Sparse Binary Coding of Pretrained Text Embeddings
Stefano Maria Iacus, Haodong Qi
https://arxiv.org/abs/2611.00999

- Infinite Worlds from One Example: What Local Generators Must Share
Amin Najafgholizadeh, Mohsen Afsharchi
https://arxiv.org/abs/2611.01048

- ReWY: Faster Backpropagation for Delta-Rule Attention - From 7 to 3 Matrix Multiplications
Yi Zhang, Zhixin Zhao, Weiwei Sun, Yitao Hu, Sheng Chen, Keqiu Li
https://arxiv.org/abs/2611.01940

- NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale
Chaoyun Zhang, et al.
https://arxiv.org/abs/2611.02102

- Beyond Unit-Circle Eigenvalues: Invariant Bases for Stable State Space Dynamics
Jiaqian Zhu, Yang Zhang, Junhua Ding, Xiaowei Yu
https://arxiv.org/abs/2611.02174

- Attribution-based diagnostics for single-cell foundation models
Jafari, Lazard, Bouzid, Bannur, Wander, Conard, Hyland, Crawford, de Castro
https://arxiv.org/abs/2611.02335

- Replay for LLM Continual Learning with Multi-Teacher On-Policy Distillation
Yiqiao Qiu
https://arxiv.org/abs/2611.02746

- DIKT: A Diagnostic and Interpretable Knowledge Tracing Framework for Prediction and Model-based L...
Yi-Qiang Wu, Shaohui Chen, Hanlin Li, Baolin Yi
https://arxiv.org/abs/2611.02774

- The Cost of Mismatch: Noise Amplification in Zeroth-Order Reinforcement Learning
Lianmin Chen, Junbin Qiu, Chenxing Wei, Yao Shu, Kun He
https://arxiv.org/abs/2611.03260

- An Axiomatic Framework for Reinforcement Learning in Open Multi-Agent Systems
Jianhong Wang, Yang Li, Samuel Kaski, Jonathan Lawry
https://arxiv.org/abs/2611.03301

toXiv_bot_toot

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[10/19]:
- On Global Joint Lower Bounds in Zeroth-Order Nonconvex Optimization
Yuxuan Xia, Xiao-Tong Yuan
https://arxiv.org/abs/2610.19652 https://mastoxiv.page/@arXiv_csLG_bot/117444077188791308

- Memorilla: Latent Semantic Memory for LLMs
Fallahpour, Idehpour, Kothapalli, Mounier, Wu, Pardis, Leskovec
https://arxiv.org/abs/2610.21375 https://mastoxiv.page/@arXiv_csLG_bot/117449740151471532

- CIS-Transolver: A Cross-layer Incremental-State Neural Operator for Fine-Scale Automotive Aerodyn...
Jianglong Liu, Zhicheng Zhu, Jia Hao, Liangyue Jia, Wenxuan He
https://arxiv.org/abs/2610.26337 https://mastoxiv.page/@arXiv_csLG_bot/117472673032915605

- Scaling Graph Reasoning in Language Models with Learnable Graph Positional Encodings
Javier Porras-Valenzuela, Arush Arora, Alejandro Ribeiro
https://arxiv.org/abs/2610.27439

- Lower Bounds for Smooth Nonconvex Zeroth-Order Optimization: The Price of Determinism under Low C...
Yuxing Peng, Zhiqing Tang, Weijia Jia
https://arxiv.org/abs/2610.27550

- TPO: Tri-level Distributionally Robust Learning for OOD Direct Preference Optimization
Chengtao Jian, Kai Yang
https://arxiv.org/abs/2610.28229

- Online Open-World Wafer Defect Discovery using Hyperdimensional Computing
Quanling Zhao, Ava Emami, Tsuyoshi Id\'e, Rajiv Joshi, Steven Holmes, Michael Passow, Tajana Rosing
https://arxiv.org/abs/2610.28949 https://mastoxiv.page/@arXiv_csLG_bot/117483654981382495

- A Sharp Dynamic Haussler Lemma
Shihao Shao, Dacheng Tao
https://arxiv.org/abs/2610.29898 https://mastoxiv.page/@arXiv_csLG_bot/117483703743815217

- The Cost of an Unknown Horizon for the Last Iterate of Clipped SGD under Heavy-Tailed Noise
Yuxing Peng, Zhiqing Tang, Weijia Jia
https://arxiv.org/abs/2610.33381

- TriTile: Three-Tier Attention for Video Diffusion Transformers
Yeonjae Kim, Omin Kwon, Seong Hoon Seo, Jae W. Lee
https://arxiv.org/abs/2610.35706

- Propose-Filter-Release: Scaling Noise to Typical Sensitivity via Private Filtering
Moshe Shenfeld, Eliad Tsfadia, Katrina Ligett
https://arxiv.org/abs/2610.40654 https://mastoxiv.page/@arXiv_csLG_bot/117529301050797240

toXiv_bot_toot

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[9/19]:
- CausalBind: Causal Modeling and Learning for Protein-Molecule Virtual Screening
Loka Li, Jin Tian, Kun Zhang
https://arxiv.org/abs/2610.07340 https://mastoxiv.page/@arXiv_csLG_bot/117398784230256732

- Shared Geometry As A Rosetta Stone: Cross-Modal Alignment Without Paired Data
Dominik Schnaus, Thomas Dag\`es, Daniel Cremers, Xi Wang, Phillip Isola
https://arxiv.org/abs/2610.09411 https://mastoxiv.page/@arXiv_csLG_bot/117404437456409207

- SPERA: Spherical Prior EEG Foundation Model with Geometry- and Frequency-Aware Latent Prediction
Minsu Kim, Ye-Sung Kim, Hyeseong Jeon, Wooseok Hyung, Joshua Lee, Chang-Hwan Im
https://arxiv.org/abs/2610.10571 https://mastoxiv.page/@arXiv_csLG_bot/117409826668555114

- Imitation Dominates Reinforcement: Direct In-Context RL Is Closer to ICL Than RL
Minchan Kwon, Seunghee Koh, Sunghyun Baek, Minsung Bae, Junmo Kim
https://arxiv.org/abs/2610.11152 https://mastoxiv.page/@arXiv_csLG_bot/117410112940577267

- Example-driven Parametrisations for Bayesian Shape Optimisation
Gabriel Diaz-Aylwin, Joseph Neighbour, Abiel Malkani Talwar, Rui-Yang Zhang, Henry B. Moss
https://arxiv.org/abs/2610.11984 https://mastoxiv.page/@arXiv_csLG_bot/117410176447359287

- S$^3$R: Fast and Faithful RL Rollouts via Self-Sparse Speculative Decoding
Yuhang He, Hongyu Ge, Zihan Lin, Siyi Liu, Yongqi Zhang
https://arxiv.org/abs/2610.13202 https://mastoxiv.page/@arXiv_csLG_bot/117427036623208593

- LeanPRM: Lean-Grounded Process Supervision for Natural Language Proof Verification
Rodney Lafuente-Mercado, Salman Rahman, Jingyan Shen, James Shiffer, Saadia Gabriel, Pavel Izmailov
https://arxiv.org/abs/2610.17697 https://mastoxiv.page/@arXiv_csLG_bot/117439184811048463

- TStruct: Learning Shared Temporal Structures for Long-Term Time Series Forecasting
Yangze Li, Zhengyang Zhou, Qihe Huang, Pengkun Wang, Binwu Wang, Yang Wang
https://arxiv.org/abs/2610.17864 https://mastoxiv.page/@arXiv_csLG_bot/117439188741246476

- Lotus: Learning to Understand Time-series by Learning to Forecast
Van Dai Do, Huu Hiep Nguyen, Minh Hoang Nguyen, Manh Nguyen, Hung Le
https://arxiv.org/abs/2610.18877 https://mastoxiv.page/@arXiv_csLG_bot/117443793080679743

toXiv_bot_toot

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[8/19]:
- Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training
Zili Wang, Zhaopeng Qiu, Yuekai Zhang, Shuang Yu, Seonjin Na, Hayate Iso, Junjie Lai
https://arxiv.org/abs/2609.07108 https://mastoxiv.page/@arXiv_csLG_bot/117240568289721339

- Literati: Towards Anytime Optimal Shape Generalized Trees via AO*
Nakul Upadhya, Eldan Cohen
https://arxiv.org/abs/2609.09299 https://mastoxiv.page/@arXiv_csLG_bot/117245640899037296

- TabPFN-3.5: Technical Report
Benjamin J\"ager, et al.
https://arxiv.org/abs/2609.17895 https://mastoxiv.page/@arXiv_csLG_bot/117285438678486611

- Uncertainty and Business-Aware Remaining Useful Life Estimation for Semiconductor Manufacturing
Davide Frizzo, Francesco Borsatti, Gian Antonio Susto
https://arxiv.org/abs/2609.22160 https://mastoxiv.page/@arXiv_csLG_bot/117313874367993434

- A Concentration Bound for Two-Timescale Actor-Critic Algorithm
Prashansa Panda, Shalabh Bhatnagar
https://arxiv.org/abs/2609.29117 https://mastoxiv.page/@arXiv_csLG_bot/117330795827167847

- Bayesian Optimization with Fisher Information Geometry: Gradient Bounds and Trust-Region Methods
Saksham Kiroriwal, Julius Pfrommer, J\"urgen Beyerer
https://arxiv.org/abs/2609.31107 https://mastoxiv.page/@arXiv_csLG_bot/117347778021662776

- From Perturbation Sensitivity to Sparse Autoencoder Feature Interpretation: An EEG Foundation-Mod...
Yucong Cao, Chenqi Li, Tingting Zhu
https://arxiv.org/abs/2609.34091 https://mastoxiv.page/@arXiv_csLG_bot/117354252497840528

- Training and Inference Dynamics of PLDR-LLMs: Row-Map Collapse, Renormalization, and Predictive R...
Burc Gokden
https://arxiv.org/abs/2609.34130 https://mastoxiv.page/@arXiv_csLG_bot/117354257806454215

- ORBIT-FMIB: Tracking Order-Resolved Epistatic Information Through ESM-2
Maryam Rahimimovassagh, Waldemar Karwowski, Ivan Garibay, Niloofar Yousefi
https://arxiv.org/abs/2610.00672 https://mastoxiv.page/@arXiv_csLG_bot/117370524972928235

- The Implicit Bias of Hyperbolic Representation Learning for Multiclass Data: A Busemann Risk Pers...
Xingrun Li, Sho Kuno, Yusuke Mukuta, Xin Yang, Tatsuya Harada
https://arxiv.org/abs/2610.07131 https://mastoxiv.page/@arXiv_csLG_bot/117398743727426999

toXiv_bot_toot

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[7/19]:
- Multi-Axis Max@K Reinforcement Learning for Representative Diversity in Text-to-Image Generation
Onoda, Parmas, Furuta, Nishimori, Oshima, Taniguchi, Matsuo
https://arxiv.org/abs/2607.14962 https://mastoxiv.page/@arXiv_csLG_bot/116934391001364119

- Volatility-Aware Extreme Event Detection in High-Frequency Financial Markets
Maorufa Zaman, Haris Md Sahed
https://arxiv.org/abs/2607.17555 https://mastoxiv.page/@arXiv_csLG_bot/116957188454978375

- Optimizing the Preconditioner: A Black-box Online-to-Nonconvex Conversion with Static Regret Mini...
Haichen Hu, David Simchi-Levi
https://arxiv.org/abs/2607.17607 https://mastoxiv.page/@arXiv_csLG_bot/116957189833200703

- Beyond Single-Episode Optimization: Sliding-Window Aware Generative Auto-Bidding for Long-Term Ad...
Binglin Wu, Chuan Yue, Yingyi Zhang, Xianneng Li, Ruyue Deng, Weiru Zhang, Xiaoyi Zeng
https://arxiv.org/abs/2607.25233 https://mastoxiv.page/@arXiv_csLG_bot/117002329324945833

- Power law graph attention: exact generalization of scaled dot-product attention, empirical collap...
Burc Gokden
https://arxiv.org/abs/2608.10288 https://mastoxiv.page/@arXiv_csLG_bot/117081574482920283

- An Efficient Minimax-Optimal Algorithm for Adversarial $m$-Set Bandits
Francesco Bacchiocchi, Tommaso Cesari, Roberto Colomboni
https://arxiv.org/abs/2608.12231 https://mastoxiv.page/@arXiv_csLG_bot/117087268662736675

- Sparse Koopman Autoencoders Identify Local Dynamical Regimes in Multibasin Systems
Aidan Li, Uday Kiran Reddy Tadipatri, Mahan Fathi, Sarath Chandar, Ross Goroshin
https://arxiv.org/abs/2608.29057 https://mastoxiv.page/@arXiv_csLG_bot/117194803564295315

- DeSyR: A decoupled symbolic recovery framework for PDEs with PINN-guided structure discovery and ...
Pancheng Niu, Jun Guo, Qiaolin He, Jingcai Guo, Yanchao Shi
https://arxiv.org/abs/2609.00530 https://mastoxiv.page/@arXiv_csLG_bot/117200544197660295

- Import What You Need: Learning When and How to Augment EHR Graphs with External Knowledge
Chen Chen, Mohsen Nayebi Kerdabadi, Dongjie Wang, Mei Liu, Zijun Yao
https://arxiv.org/abs/2609.01839 https://mastoxiv.page/@arXiv_csLG_bot/117206099553711748

- Budgeted Task-Aware Acquisition of Dynamic Networks
Zihe Zhou
https://arxiv.org/abs/2609.05862 https://mastoxiv.page/@arXiv_csLG_bot/117240210647289103

toXiv_bot_toot

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[6/19]:
- Generate in Reconstruction Space, Match in Semantic Space: Transport Geometry for One-Step Genera...
Hugues Van Assel, Edward De Brouwer, Saeed Saremi, Gabriele Scalia, Aviv Regev
https://arxiv.org/abs/2606.00514 https://mastoxiv.page/@arXiv_csLG_bot/116679745890165585

- Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards
Christian Scherer, Joe Watson, Theo Gruner, Daniel Palenicek, Ingmar Posner, Jan Peters
https://arxiv.org/abs/2606.02194 https://mastoxiv.page/@arXiv_csLG_bot/116679850491133613

- The Price of Partial Information with Switching Costs: A Complete Characterization for Feedback G...
Cesa-Bianchi, Cesari, Colomboni, Esposito, Fusco, Koren
https://arxiv.org/abs/2606.03851 https://mastoxiv.page/@arXiv_csLG_bot/116685305165353714

- How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Compositional GPs
Mark Kozdoba, Shie Mannor
https://arxiv.org/abs/2606.08218 https://mastoxiv.page/@arXiv_csLG_bot/116719383043856024

- Robust Learning under Non-Gaussian Noise with Adaptive Log-Correntropy Loss
Mainak Kundu, Ria Kanjilal, Ismail Uysal
https://arxiv.org/abs/2606.16050 https://mastoxiv.page/@arXiv_csLG_bot/116759034720186771

- Rethinking Dataset Distillation for Classification: Do Distilled Sets Outperform Coresets?
Trisha Mittal, Akshay Mehra, Joshua Kimball
https://arxiv.org/abs/2606.18209 https://mastoxiv.page/@arXiv_csLG_bot/116764533852675596

- Does Source-Free Time-Series Adaptation Really Require Updating the Encoder?
Shichang Meng, Linquan Wu, Xuan Ai, Yi Wu, Mingyang Liu, Linqi Song
https://arxiv.org/abs/2606.23120 https://mastoxiv.page/@arXiv_csLG_bot/116798871795881722

- Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
Changdae Oh, Wendi Li, Seongheon Park, Samuel Yeh, Tanwi Mallick, Sharon Li
https://arxiv.org/abs/2606.26080 https://mastoxiv.page/@arXiv_csLG_bot/116809837491106899

- Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps
OuYang, Yu, Ai, He, Boffi, Ravikumar, Hernandez-Lobato, Simchowitz, Miller, Chehab
https://arxiv.org/abs/2606.29110 https://mastoxiv.page/@arXiv_csLG_bot/116838238504933500

toXiv_bot_toot

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[5/19]:
- Scaling Limits of Long-Context Transformers
Giuseppe Bruno, Shi Chen, Zhengjiang Lin, Yury Polyanskiy, Philippe Rigollet
https://arxiv.org/abs/2605.08505 https://mastoxiv.page/@arXiv_csLG_bot/116560880451144626

- TabPFN-3: Technical Report
L\'eo Grinsztajn, et al.
https://arxiv.org/abs/2605.13986 https://mastoxiv.page/@arXiv_csLG_bot/116577588814446253

- Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning
Shin So, Kyelim Lee, Albert No
https://arxiv.org/abs/2605.14659 https://mastoxiv.page/@arXiv_csLG_bot/116577689676790324

- Tadpole: Autoencoders as Foundation Models for 3D PDEs with Online Learning
Qiang Liu, Felix Koehler, Benjamin Holzschuh, Nils Thuerey
https://arxiv.org/abs/2605.15284 https://mastoxiv.page/@arXiv_csLG_bot/116594573350823283

- PALM: Physically-Anchored Latent-timescale Mamba for Stable Representations under Distribution Shift
Sangyoon Bae, Shinjae Yoo, Jiook Cha
https://arxiv.org/abs/2605.16351 https://mastoxiv.page/@arXiv_csLG_bot/116600294437894747

- Tensor Cookbook: Mastering Tensors through Diagrams
Beheshteh T. Rakhshan, Guillaume Rabusseau
https://arxiv.org/abs/2605.16610 https://mastoxiv.page/@arXiv_csLG_bot/116600444256499212

- The Smallest Singular Directions of the Unembedding Matter Disproportionately for Next-Token Pred...
Weilun Xu
https://arxiv.org/abs/2605.17084 https://mastoxiv.page/@arXiv_csLG_bot/116600480629847521

- Alignment Dynamics in LLM Fine-Tuning
Yuhan Huang, Huanran Chen, Yinpeng Dong
https://arxiv.org/abs/2605.18309 https://mastoxiv.page/@arXiv_csLG_bot/116600527622241837

- Generating Physically Consistent Molecules with Energy-Based Models
Christoph Griesbacher, Lea Bogensperger, Andreas Habring, Thomas Pock
https://arxiv.org/abs/2605.18381 https://mastoxiv.page/@arXiv_csLG_bot/116600530571922585

- Toward Identifiable Sparse Autoencoders
Walter Nelson, Theofanis Karaletsos, Francesco Locatello
https://arxiv.org/abs/2605.31245 https://mastoxiv.page/@arXiv_csLG_bot/116673938123746274

- Beyond Augmentation: Score-Guided Pathological Prior for EEG-based Depression Detection
Xiaojing Chen, Jingqi Cheng, Xu Zhao, Wan Jiang, Jingjing Wu
https://arxiv.org/abs/2606.00180 https://mastoxiv.page/@arXiv_csLG_bot/116679630477920416

toXiv_bot_toot

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[4/19]:
- Low-Degree Learning from Localization Schemes
Gautam Chandrasekaran, Jason Gaitonde, Ankur Moitra, Arsen Vasilyan
https://arxiv.org/abs/2604.06109 https://mastoxiv.page/@arXiv_csLG_bot/116368326476063701

- How Does Machine Learning Manage Complexity?
Lance Fortnow
https://arxiv.org/abs/2604.07233 https://mastoxiv.page/@arXiv_csLG_bot/116374012030347345

- ELMoE-3D: Leveraging Intrinsic Elasticity of MoE for Hybrid-Bonding-Enabled Self-Speculative Deco...
Choi, Lee, Oh, Whang, Kim, Kim, Lee, Yoo, Kim
https://arxiv.org/abs/2604.14626 https://mastoxiv.page/@arXiv_csLG_bot/116419230589337928

- The Optimal Sample Complexity of Multiclass and List Learning
Chirag Pabbaraju
https://arxiv.org/abs/2604.24749 https://mastoxiv.page/@arXiv_csLG_bot/116481551056372339

- Zero Shot Coordination for Sparse Reward Tasks with Diverse Reward Shapings
Keenan Powell, Peihong Yu, Pratap Tokekar
https://arxiv.org/abs/2604.25076 https://mastoxiv.page/@arXiv_csLG_bot/116487037982645175

- AMGenC: Generating Charge Balanced Amorphous Materials
Yan Lin, Jilin Hu, N. M. Anoop Krishnan, Morten M. Smedskjaer
https://arxiv.org/abs/2604.27613 https://mastoxiv.page/@arXiv_csLG_bot/116498400951018442

- Estimating the expected output of wide random MLPs more efficiently than sampling
Wilson Wu, Victor Lecomte, Michael Winer, George Robinson, Jacob Hilton, Paul Christiano
https://arxiv.org/abs/2605.05179 https://mastoxiv.page/@arXiv_csLG_bot/116532374416998849

- Requests of a Feather Must Flock Together: Batch Size vs. Prefix Homogeneity in LLM Inference
Saksham Rathi, Preeti, Mythili Vutukuru
https://arxiv.org/abs/2605.06046 https://mastoxiv.page/@arXiv_csLG_bot/116538049508809303

- On the Divergence of Differential Temporal Difference Learning without Local Clocks
David Antrobius, Shangtong Zhang
https://arxiv.org/abs/2605.06874 https://mastoxiv.page/@arXiv_csLG_bot/116555002251196387

- Almost Sure Convergence Rates of Stochastic Approximation and Reinforcement Learning via a Poisso...
Xinyu Liu, Zixuan Xie, Shangtong Zhang
https://arxiv.org/abs/2605.07104 https://mastoxiv.page/@arXiv_csLG_bot/116555033316696571

- Sink vs. diagonal patterns as mechanisms for attention switch and oversmoothing prevention
Peter S\'uken\'ik, Cristina L\'opez Amado, Christoph H. Lampert, Marco Mondelli
https://arxiv.org/abs/2605.08453 https://mastoxiv.page/@arXiv_csLG_bot/116560876911975868

toXiv_bot_toot

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[3/19]:
- On the Runway Cascade of Transformers for Language Modeling
Hunjae Lee, Corey Clark
https://arxiv.org/abs/2601.14522 https://mastoxiv.page/@arXiv_csLG_bot/115938268596527193

- LoRIF: Pushing the Scalability Frontier of Training Data Attribution
Shuangqi Li, Hieu Le, Jingyi Xu, Mathieu Salzmann
https://arxiv.org/abs/2601.21929 https://mastoxiv.page/@arXiv_csLG_bot/115983801931311339

- Exact Gaussian Moment Matching for Residual Networks: a Second-Order Method
Simon Kuang, Xinfan Lin
https://arxiv.org/abs/2601.22307 https://mastoxiv.page/@arXiv_csLG_bot/116000490122699742

- Agnostic Language Identification and Generation
Mikael M{\o}ller H{\o}gsgaard, Chirag Pabbaraju
https://arxiv.org/abs/2601.23258 https://mastoxiv.page/@arXiv_csLG_bot/116000701154108553

- Dynamic Expert Sharing: Decoupling Memory from Parallelism in Mixture-of-Experts Diffusion LLMs
Chen, Mo, Lee, Wang, Li, Hu, Luk, Hospedales, Fan
https://arxiv.org/abs/2602.00879 https://mastoxiv.page/@arXiv_csLG_bot/116006961352373301

- Sparsely Supervised Diffusion
Zhao, Li, Zhao, Vali, Trapp, Pajarinen, Kannala, Solin
https://arxiv.org/abs/2602.02699

- vLLM Hook v1: A Plug-in for Programming Model Internals on vLLM
Ching-Yun Ko, Yunhua Fang, Pin-Yu Chen
https://arxiv.org/abs/2603.06588 https://mastoxiv.page/@arXiv_csLG_bot/116203736237005352

- ES-Merging: Biological MLLM Merging via Embedding Space Signals
Wonbin Lee, Dongki Kim, Sung Ju Hwang
https://arxiv.org/abs/2603.14405 https://mastoxiv.page/@arXiv_csLG_bot/116243775530253361

- FatigueFormer: A Physiology-Informed Model for Upper-Limb Muscle Fatigue Assessment
Tong Zhang, Hong Guo, Shuangzhou Yan, Dongkai Weng, Jian Wang, Hongxin Zhang
https://arxiv.org/abs/2603.26841 https://mastoxiv.page/@arXiv_csLG_bot/116322982493645347

- HISA: Efficient Hierarchical Indexing for Fine-Grained Sparse Attention
Xu, Meng, Jiang, Wang, Zhou, Wang, Wu, Pan, Tang, Pei, Liu, Yin, Sun, Zhang
https://arxiv.org/abs/2603.28458 https://mastoxiv.page/@arXiv_csLG_bot/116323287214865771

- UQ-SHRED: uncertainty quantification of shallow recurrent decoder networks for sparse sensing via...
Mars Liyao Gao, Yuxuan Bao, Amy S. Rude, Xingyue Zhang, Xinwei Shen, J. Nathan Kutz
https://arxiv.org/abs/2604.01305 https://mastoxiv.page/@arXiv_csLG_bot/116339688200261416

toXiv_bot_toot

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[2/19]:
- Free Draft-and-Verification: Toward Lossless Parallel Decoding for Diffusion Large Language Models
Shutong Wu, Jiawei Zhang
https://arxiv.org/abs/2510.00294 https://mastoxiv.page/@arXiv_csLG_bot/115304137432295494

- Re-examining low-rank adaptation for private LLM fine-tuning
Ali Dadsetan, Frank Rudzicz
https://arxiv.org/abs/2510.01137 https://mastoxiv.page/@arXiv_csLG_bot/115304263265037875

- MAGDrop: Momentum Adaptive Gradient Dropout With Provable Generalization Guarantees
Adeel Safder, Bum Jun Kim
https://arxiv.org/abs/2510.18410 https://mastoxiv.page/@arXiv_csLG_bot/115417386241489591

- SPIRE: Shared-Private Representation Learning for Continuous Multi-Region LFP under Perturbation
Rahil Soroushmojdehi, Sina Javadzadeh, Mehrnaz Asadi, Terence D. Sanger
https://arxiv.org/abs/2510.25023 https://mastoxiv.page/@arXiv_csLG_bot/115462541867603602

- Why Freeze the Encoder? A Controlled Study of End-to-End Sequence-Graph Learning for User Behavior
Chen, Wu, Sharpe, Melnyk, Nguyen, Huang, Bruss, Fathony
https://arxiv.org/abs/2510.25126 https://mastoxiv.page/@arXiv_csLG_bot/115462621168428376

- Rethinking the Unsupervised Paradigm in Time Series Anomaly Detection: An Empirical Study and Min...
Zhijie Zhong, Zhiwen Yu, Kaixiang Yang, Yongheng Liu, Jun Jiang, C. L. Philip Chen
https://arxiv.org/abs/2511.16145 https://mastoxiv.page/@arXiv_csLG_bot/115587146744864089

- SAMBA: Toward an EEG Foundation Model via Differential Mamba and Coordinate-Driven Spatial Embedding
Jiazhen Hong, Geoffrey Mackellar, Soheila Ghane
https://arxiv.org/abs/2511.18571 https://mastoxiv.page/@arXiv_csLG_bot/115610351261841663

- HOLE: Homological Observation of Latent Embeddings for Neural Network Interpretability
Sudhanva Manjunath Athreya, Paul Rosen
https://arxiv.org/abs/2512.07988 https://mastoxiv.page/@arXiv_csLG_bot/115694787044661736

- Flow Equivariant World Models: Structured Memory for Dynamic Environments
Hansen Jin Lillemark, Benhao Huang, Fangneng Zhan, Yilun Du, Thomas Anderson Keller
https://arxiv.org/abs/2601.01075 https://mastoxiv.page/@arXiv_csLG_bot/115847967800424992

- Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile ...
Liu, Li, Sun, Chen, Bian, Wang, Dong, Chen, Wang
https://arxiv.org/abs/2601.12401 https://mastoxiv.page/@arXiv_csLG_bot/115933534348605795

toXiv_bot_toot

Replaced article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[1/19]:
- Subspace Node Pruning
Joshua Offergeld, John Chidiac, Marcel van Gerven, Nasir Ahmad
https://arxiv.org/abs/2405.17506 https://mastoxiv.page/@arXiv_csLG_bot/112523058121464470

- On the growth of the parameters of approximating ReLU neural networks
Erion Morina, Martin Holler
https://arxiv.org/abs/2406.14936 https://mastoxiv.page/@arXiv_csLG_bot/112670440850652237

- Correlations Are Ruining Your Gradient Descent
Joshua Offergeld, Nasir Ahmad
https://arxiv.org/abs/2407.10780 https://mastoxiv.page/@arXiv_csLG_bot/112794889384957465

- Heterogeneous Graph Attention Network With Multimodal Feature Selection for Cancer Multiomics Int...
Sina Tabakhi, Charlotte Vandermeulen, Ian Sudbery, Haiping Lu
https://arxiv.org/abs/2408.02845 https://mastoxiv.page/@arXiv_csLG_bot/112919433471924902

- Scalable and adaptive prediction bands with kernel sum-of-squares
Louis Allain (ENSAI, CREST), S{\'e}bastien da Veiga (ENSAI, CREST, RT-UQ), Brian Staber
https://arxiv.org/abs/2505.21039 https://mastoxiv.page/@arXiv_csLG_bot/114584297300574292

- Eco-MobiLLM: Efficient LLM Fine-Tuning on the Mobile Device via Server Assisted Side-Tuning
Xingke Yang, Liang Li, Zhiyi Wan, Sicong Li, Xiaoqi Qi, Jiang Liu, Tomoaki Ohtsuki, Xin Fu, Miao Pan
https://arxiv.org/abs/2507.01216 https://mastoxiv.page/@arXiv_csLG_bot/114788773416453470

- Efficient Collaborative LLM Fine-Tuning over Heterogeneous Mobile Devices via Many Backbones to O...
Xingke Yang, Liang Li, Sicong Li, Liwei Guan, Hao Wang, Xiaoqi Qi, Jiang Liu, Xin Fu, Miao Pan
https://arxiv.org/abs/2508.06765 https://mastoxiv.page/@arXiv_csLG_bot/115015398404299085

- The Algorithm Is Not the Behavior: Learned Priors Override Look-Ahead in a Chess-Playing Neural N...
Elias Sandmann, Sebastian Lapuschkin, Wojciech Samek
https://arxiv.org/abs/2508.21380 https://mastoxiv.page/@arXiv_csLG_bot/115128391626452010

- How deep is your network? Deep vs. shallow learning of transfer operators
Mohammad Tabish, Benedict Leimkuhler, Stefan Klus
https://arxiv.org/abs/2509.19930 https://mastoxiv.page/@arXiv_csLG_bot/115264493495237945

- SLogic: Subgraph-Informed Logical Rule Learning for Knowledge Graph Completion
Trung Hoang Le, Tran Cao Son, Ishtiaq Ahmed, Huiping Cao
https://arxiv.org/abs/2510.00279 https://mastoxiv.page/@arXiv_csLG_bot/115304128256998847

toXiv_bot_toot

Crosslisted article(s) found for cs.LG. https://arxiv.org/list/cs.LG/new
[10/10]:
- Post-stratified importance sampling
Yuling Yao, Sergei Tikhonov
https://arxiv.org/abs/2611.05238 https://mastoxiv.page/@arXiv_statME_bot/117557246132682890

- Gaussian Partitioning for Reliable Learning of Multi-Index Models
Ilias Diakonikolas, Giannis Iakovidis, Daniel M. Kane, Mingchen Ma
https://arxiv.org/abs/2611.05264 https://mastoxiv.page/@arXiv_csDS_bot/117557290539492663

- Conformal Prediction at Performative Equilibrium: The Price of Performativity
Ahmed Mahrous, Roberto Di Pietro
https://arxiv.org/abs/2611.05277 https://mastoxiv.page/@arXiv_mathST_bot/117557147794897870

- Knowingly Wrong: Training LLMs Against Their Own Beliefs can Induce Misalignment
Ariana M. Villegas-Suarez, Guido Freire, Sohan Venkatesh, Bartosz Cywi\'nski
https://arxiv.org/abs/2611.05287 https://mastoxiv.page/@arXiv_csCL_bot/117557292308240152

- GSBR: Geometric Support Behavior Regularization for Online RL
Charles Xu, Jacob Berg, Liyiming Ke, Sergey Levine
https://arxiv.org/abs/2611.05295 https://mastoxiv.page/@arXiv_csRO_bot/117557321014241291

- A simple adaptive accelerated optimistic dual averaging method for unconstrained convex optimizat...
Bowen Li, Danqing Zhou, Chuan He
https://arxiv.org/abs/2611.05334 https://mastoxiv.page/@arXiv_mathOC_bot/117557249641645172

- A Circuit for In-Context Learning
Andrew Gao, William Gao
https://arxiv.org/abs/2611.05344 https://mastoxiv.page/@arXiv_csCL_bot/117557298403308419

- Reading Why: Born-Measured Attention with Exact Word Evidence on Light and Qubits
Teerawat Tongloy, Jiraporn Pongsopa, Rangsan Jomtarak
https://arxiv.org/abs/2611.05355 https://mastoxiv.page/@arXiv_quantph_bot/117557324748855452

- Suppressing Misaligned Behaviors in Language Models, Durably
Luxi He, Pengcheng Jiang, Jifan Zhang, Jiawei Han, Danqi Chen
https://arxiv.org/abs/2611.05358 https://mastoxiv.page/@arXiv_csCL_bot/117557300369697266

- GUILD: Guided Iterative Data Collection for Imitation Learning
Shivin Dass, Kevin Nguyen, Rohan Yelandur, Junhong Xu, Roberto Mart\'in-Mart\'in
https://arxiv.org/abs/2611.05368 https://mastoxiv.page/@arXiv_csRO_bot/117557326520206360

- PolicyIK: High-Precision Inverse Kinematics for Robot Arms with Reinforcement Learning
Yuhan Liu, Xinqi Liu, Zixuan Dong, Keith W. Ross, Shenji Wan
https://arxiv.org/abs/2611.05372 https://mastoxiv.page/@arXiv_csRO_bot/117557326912216720

toXiv_bot_toot