| 1 | BrainWideBench: Benchmarking large-scale pretraining and across-animal transfer in multi-region neural recordings | Alexandre Andre, Shivashriganesh P. Mahato, Vinam Arora +39 | cs.LG | 2026-09-18 |
| 2 | Abstention and Noise Filtering: Two Missing Primitives of Softmax Attention | Richard Zhe Wang | cs.LG | 2026-09-18 |
| 3 | GALA: Geometry-Aware Latent Action Modeling for Vision-Language-Action Model Pretraining across Embodiments | Yichen Liu, Puzhen Yuan, Xiang Zhu +2 | cs.RO | 2026-09-18 |
| #4 | Joint Remaining Useful Life Prediction and Capacity Estimation of Lithium-Ion Batteries Using Partial-Charging Data | Khoa Tran, Ho-Si-Hung Nguyen, Phone Wai Yan Moe +2 | cs.LG | 2026-09-18 |
| #5 | Detecting Pretraining Data in Large Language Models from a Free-Energy Perspective | Chenye Ke, Zirui Liu, Qi Liu +4 | cs.LG | 2026-09-18 |
| #6 | From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention | Sichang Su, Benjamin Yang, Zhiyun Deng +4 | cs.RO | 2026-09-18 |
| #7 | Beyond Benchmark Scores: Auditing Medical Vision-Language Models for Chest X-Ray Tuberculosis Screening | Mushir Akhtar, M. Tanveer, Mohd. Arshad | cs.CV | 2026-09-18 |
| #8 | MT-WAM: Reorienting the One-Pass Predictive Representation Toward Action Generation | Yiguang Yang, Jiankun Peng, Xiaoming Wang +2 | cs.CV | 2026-09-18 |
| #9 | AtomEgo: Exploring Ego-Robot Integration for Embodied Foundation Model Pretraining | Di Wu, Dongchen Zheng, Junhe Sheng +8 | cs.RO | 2026-09-18 |
| #10 | Tracing the Evidence Behind Zero-Shot Time-Series Forecasting: A Source-First Taxonomy and Audit Framework | Delun Kong, Wanyun Ling, Chenxi Liu +1 | cs.LG | 2026-09-18 |
| #11 | Beyond Atomic Tokens: Factorizing Syllables for Language Model Pretraining | Nghia Hieu Nguyen, Thai Bao Huynh, Binh-An Dinh-Le +4 | cs.CL | 2026-09-18 |
| #12 | Multi-Subject Pretraining Enables Short-Calibration Personalization for Closed-Corpus Surface EMG Speech Decoding | Chenqian Le, Beatrice Fumagalli, Yasamin Esmaeili +5 | cs.LG | 2026-09-18 |
| #13 | Not All Irregularity Is Equal: Causally Isolating a Rare Failure Mode in Japanese Morphological Inflection | Wen Zhang | cs.CL | 2026-09-18 |
| #14 | How Does Distribution Shift Shape Pretraining Gains in Neural PDE Surrogates? | Pochinapeddi Sai Bhargav, Nithin Somasekharan, Rohit Sunil Kanchi +2 | physics.comp-ph | 2026-09-17 |
| #15 | FreqCondNorm: Towards Cross-domain Predictive Maintenance through a Frequency-Conditioned Transformer Foundation Model | Zaynab Raounak, Camille LHermine, Zhiguo Zeng | cs.AI | 2026-09-17 |
| #16 | Automated Goldsmith's Mark Retrieval in Silverware | Atmik Tiwari, Vincent Christlein, Mark Fichtner +5 | cs.CV | 2026-09-17 |
| #17 | Stress-testing Alignment Midtraining | Sid Baines, Jonathan Bostock, Maria Angelica Martinez +3 | cs.CL | 2026-09-17 |
| #18 | Compact Vision Models for Iris Presentation Attack Detection under Presentation Attack Instrument Shift and Environmental Degradation | Athanasios Angelakis, Marta Gomez-Barrero | cs.CV | 2026-09-17 |
| #19 | A Free Lunch? Adapting PP-OCRv6 for Historical Text Recognition | Benjamin Kiessling | cs.CV | 2026-09-17 |
| #20 | Improving Cross-embodiment Transfer in Latent Action Models with Action-Similarity Supervision | Maxime Alvarez, Renzo Caballero, Tatsuya Matsushima +2 | cs.RO | 2026-09-17 |
| #21 | Form Over Content In Gradient-Based Data Attribution Methods | Sunwoo Kim, Seokwon Jung, Sohyung Kim +2 | cs.CL | 2026-09-17 |
| #22 | Why Pretraining Fails to Share Cross-Lingual Knowledge | Adam Gaber, Uriel Dolev, Elisabeth Fittschen +3 | cs.CL | 2026-09-16 |
| #23 | Infinite-Parameter LLMs: Generating and Adapting Weights from Live Data | Jinli Hu, Ross M. Clarke, Yichuan Zhang +1 | cs.AI | 2026-09-16 |
| #24 | Open ultrasound foundation model for robust segmentation and clinical measurement across heterogeneous settings | Chao Qin, Fahad Shahbaz Khan, Salman Khan +4 | cs.CV | 2026-09-16 |
| #25 | CSWAM: Better Causal Semantic Representations for Out-of-Distribution Generalization in World Action Models | Tianbin Liu, Jian Zhu, Taiyi Su +4 | cs.CV | 2026-09-16 |
| #26 | Knowledge-Graph Based Augmentation versus Retrieval Augmented Generation for Cultural-Related Question Answering | Pablo Poulenard, Yannis Karmim, Valentin Barrière | cs.CL | 2026-09-16 |
| #27 | Lumen: Parameter-Efficient Alignment of Pretrained Vision and Language Encoders for Zero-Shot Computational Pathology | Kiarash Tajbakhsh, Abdelrahman Faqieh, Michael Jopiti +9 | cs.CV | 2026-09-15 |
| #28 | Procedural Pretraining for Molecular Property Prediction | Moritz Friedemann, Zachary Shinnick, Philip Torr +1 | cs.LG | 2026-09-15 |
| #29 | FreqSpaNet: Frequency and Spatial Learning of SFPF for Physical Layer Hardware Integrity Detection | Xiaoxuan Huang, Jinlong Xu, YiZhe Wang +3 | cs.LG | 2026-09-15 |
| #30 | LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence | Xingxuan Zhang, Gang Ren, Hao Yuan +57 | cs.AI | 2026-09-15 |
| #31 | OPEN-1B: A Fully Auditable Training Run | John Donaghy, Brian Wilcox, Oğuzhan Ersoy +6 | cs.LG | 2026-09-15 |
| #32 | Robust and Efficient AI Frameworks for Scalable Material Design and Property Prediction | Kishalay Das | cond-mat.mtrl-sci | 2026-09-15 |
| #33 | DecoGS: Adaptive Static-Dynamic Decoupling of 3D Gaussians for Free-Viewpoint Video Streaming | Idil Sulo, Alexey Supikov, Ilke Demir +1 | cs.CV | 2026-09-15 |
| #34 | GeoLAM: Learning Geometry-Grounded Latent Actions from Unlabeled Human Videos | Yifan Xie, Hekun Tian, Jinkun Liu +3 | cs.CV | 2026-09-15 |
| #35 | Beyond In-Distribution Metrics: A Systematic Out-of-Distribution Evaluation of Congenital Heart Disease Segmentation | Aniketh Vijesh, Shrisharanyan Vasu, Abhijit Ramesh +5 | cs.CV | 2026-09-15 |
| #36 | HyCoSeq: Contextual Hyperbolic Representation Learning for Genomic Sequences | Chenhao Zeng, Zhibin Pu, Shufei Ge | cs.LG | 2026-09-15 |
| #37 | Measuring Annotation Efficiency for Handwritten Devanagari Recognition: Sample-Complexity Curves for Four Pretraining Regimes | Manglesh Kumar Pandey, Sumit Kumar Banshal | cs.CV | 2026-09-15 |
| #38 | Hyper-RED: Scalable Event Pre-training via Semantic Hypergraph Distillation | Meisen Wang, Zhiqiang Tian, Wei Bao +3 | cs.CV | 2026-09-15 |
| #39 | Bridging the Perceptual Gap: Residual-Enhanced Downscaling and Manifold-Aware Perception Alignment Adaptation for NR-IQA | Yu Li, Zhengran Shen, Yachun Mi +2 | cs.CV | 2026-09-15 |
| #40 | GrowMTP: Can RL Grow Its Own Draft Head? | Minghua He, Lingzhe Zhang, Yuan Liu +2 | cs.LG | 2026-09-15 |
| #41 | Which Pretext Task Transfers? Self-Supervised Pretraining Objectives for Lung Ultrasound | Moein Heidari, Junbo Rao, Jai Choraria +3 | cs.CV | 2026-09-15 |
| #42 | Style-Debiased DPO: Updating LLM Knowledge with Factuality-Aware Synthetic Preference Data | Takayuki Yamamoto, Daisuke Kawahara | cs.CL | 2026-09-15 |
| #43 | Drift Field Net: Learning Ocean Lagrangian advection fields from in-situ and satellite observations | Théo Archambault, Pierre Garcia, Mattia Romero +2 | cs.LG | 2026-09-14 |
| #44 | Compute-Optimal Pretrain--Fine-tune in Ridge Gradient Descent | Alex Buna, Fanghui Liu, Patrick Rebeschini | stat.ML | 2026-09-14 |
| #45 | Disentangling Representation Evolution in Transformers through Directional Decomposition | Shwai He, Haichao Zhang, Shen Yan | cs.CL | 2026-09-14 |
| #46 | Multi-View Molecular Representation Learning with Hierarchical Graphs and Contextualized Fingerprints | Gwang-Hyeon Yun, Jong-Hoon Park, Bing Hu +3 | cs.LG | 2026-09-14 |
| #47 | A Unified Vision-Language Model for PSMA PET/CT Report Generation, Visual Question Answering, and Lesion Segmentation | Yang Xing, Jiong Wu, Savas Ozdemir +11 | cs.CV | 2026-09-14 |
| #48 | To Each Language Its Tokenizer: Modular Tokenizers for Efficient Multilingual LLMs | Franck Signe, Hippolyte Pilchen, François Yvon +1 | cs.CL | 2026-09-14 |
| #49 | MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-Training | Tianyi Xu, Daniel Pimentel-Alarcón, Zuzana Buřivalová +1 | cs.SD | 2026-09-14 |
| #50 | MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup | Muchen Li, Leonid Sigal, Renjie Liao | cs.CL | 2026-09-14 |