PaperScope
LIVE · 2026-09-21 05:40 UTC

pretraining 12 papers this week · +30% WoW

papers mentioning "pretraining" in title/abstract · 30d window

Latestcs.CLcs.LGcs.AIcs.CV

Mentions per Day (30d)

Latest Papers

#TitleAuthorsCatDate
1BrainWideBench: Benchmarking large-scale pretraining and across-animal transfer in multi-region neural recordingsAlexandre Andre, Shivashriganesh P. Mahato, Vinam Arora +39cs.LG2026-09-18
2Abstention and Noise Filtering: Two Missing Primitives of Softmax AttentionRichard Zhe Wangcs.LG2026-09-18
3GALA: Geometry-Aware Latent Action Modeling for Vision-Language-Action Model Pretraining across EmbodimentsYichen Liu, Puzhen Yuan, Xiang Zhu +2cs.RO2026-09-18
#4Joint Remaining Useful Life Prediction and Capacity Estimation of Lithium-Ion Batteries Using Partial-Charging DataKhoa Tran, Ho-Si-Hung Nguyen, Phone Wai Yan Moe +2cs.LG2026-09-18
#5Detecting Pretraining Data in Large Language Models from a Free-Energy PerspectiveChenye Ke, Zirui Liu, Qi Liu +4cs.LG2026-09-18
#6From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human InterventionSichang Su, Benjamin Yang, Zhiyun Deng +4cs.RO2026-09-18
#7Beyond Benchmark Scores: Auditing Medical Vision-Language Models for Chest X-Ray Tuberculosis ScreeningMushir Akhtar, M. Tanveer, Mohd. Arshadcs.CV2026-09-18
#8MT-WAM: Reorienting the One-Pass Predictive Representation Toward Action GenerationYiguang Yang, Jiankun Peng, Xiaoming Wang +2cs.CV2026-09-18
#9AtomEgo: Exploring Ego-Robot Integration for Embodied Foundation Model PretrainingDi Wu, Dongchen Zheng, Junhe Sheng +8cs.RO2026-09-18
#10Tracing the Evidence Behind Zero-Shot Time-Series Forecasting: A Source-First Taxonomy and Audit FrameworkDelun Kong, Wanyun Ling, Chenxi Liu +1cs.LG2026-09-18
#11Beyond Atomic Tokens: Factorizing Syllables for Language Model PretrainingNghia Hieu Nguyen, Thai Bao Huynh, Binh-An Dinh-Le +4cs.CL2026-09-18
#12Multi-Subject Pretraining Enables Short-Calibration Personalization for Closed-Corpus Surface EMG Speech DecodingChenqian Le, Beatrice Fumagalli, Yasamin Esmaeili +5cs.LG2026-09-18
#13Not All Irregularity Is Equal: Causally Isolating a Rare Failure Mode in Japanese Morphological InflectionWen Zhangcs.CL2026-09-18
#14How Does Distribution Shift Shape Pretraining Gains in Neural PDE Surrogates?Pochinapeddi Sai Bhargav, Nithin Somasekharan, Rohit Sunil Kanchi +2physics.comp-ph2026-09-17
#15FreqCondNorm: Towards Cross-domain Predictive Maintenance through a Frequency-Conditioned Transformer Foundation ModelZaynab Raounak, Camille LHermine, Zhiguo Zengcs.AI2026-09-17
#16Automated Goldsmith's Mark Retrieval in SilverwareAtmik Tiwari, Vincent Christlein, Mark Fichtner +5cs.CV2026-09-17
#17Stress-testing Alignment MidtrainingSid Baines, Jonathan Bostock, Maria Angelica Martinez +3cs.CL2026-09-17
#18Compact Vision Models for Iris Presentation Attack Detection under Presentation Attack Instrument Shift and Environmental DegradationAthanasios Angelakis, Marta Gomez-Barrerocs.CV2026-09-17
#19A Free Lunch? Adapting PP-OCRv6 for Historical Text RecognitionBenjamin Kiesslingcs.CV2026-09-17
#20Improving Cross-embodiment Transfer in Latent Action Models with Action-Similarity SupervisionMaxime Alvarez, Renzo Caballero, Tatsuya Matsushima +2cs.RO2026-09-17
#21Form Over Content In Gradient-Based Data Attribution MethodsSunwoo Kim, Seokwon Jung, Sohyung Kim +2cs.CL2026-09-17
#22Why Pretraining Fails to Share Cross-Lingual KnowledgeAdam Gaber, Uriel Dolev, Elisabeth Fittschen +3cs.CL2026-09-16
#23Infinite-Parameter LLMs: Generating and Adapting Weights from Live DataJinli Hu, Ross M. Clarke, Yichuan Zhang +1cs.AI2026-09-16
#24Open ultrasound foundation model for robust segmentation and clinical measurement across heterogeneous settingsChao Qin, Fahad Shahbaz Khan, Salman Khan +4cs.CV2026-09-16
#25CSWAM: Better Causal Semantic Representations for Out-of-Distribution Generalization in World Action ModelsTianbin Liu, Jian Zhu, Taiyi Su +4cs.CV2026-09-16
#26Knowledge-Graph Based Augmentation versus Retrieval Augmented Generation for Cultural-Related Question AnsweringPablo Poulenard, Yannis Karmim, Valentin Barrièrecs.CL2026-09-16
#27Lumen: Parameter-Efficient Alignment of Pretrained Vision and Language Encoders for Zero-Shot Computational PathologyKiarash Tajbakhsh, Abdelrahman Faqieh, Michael Jopiti +9cs.CV2026-09-15
#28Procedural Pretraining for Molecular Property PredictionMoritz Friedemann, Zachary Shinnick, Philip Torr +1cs.LG2026-09-15
#29FreqSpaNet: Frequency and Spatial Learning of SFPF for Physical Layer Hardware Integrity DetectionXiaoxuan Huang, Jinlong Xu, YiZhe Wang +3cs.LG2026-09-15
#30LimiX-2: A Contextual Mechanism Network Towards General Structured-Data IntelligenceXingxuan Zhang, Gang Ren, Hao Yuan +57cs.AI2026-09-15
#31OPEN-1B: A Fully Auditable Training RunJohn Donaghy, Brian Wilcox, Oğuzhan Ersoy +6cs.LG2026-09-15
#32Robust and Efficient AI Frameworks for Scalable Material Design and Property PredictionKishalay Dascond-mat.mtrl-sci2026-09-15
#33DecoGS: Adaptive Static-Dynamic Decoupling of 3D Gaussians for Free-Viewpoint Video StreamingIdil Sulo, Alexey Supikov, Ilke Demir +1cs.CV2026-09-15
#34GeoLAM: Learning Geometry-Grounded Latent Actions from Unlabeled Human VideosYifan Xie, Hekun Tian, Jinkun Liu +3cs.CV2026-09-15
#35Beyond In-Distribution Metrics: A Systematic Out-of-Distribution Evaluation of Congenital Heart Disease SegmentationAniketh Vijesh, Shrisharanyan Vasu, Abhijit Ramesh +5cs.CV2026-09-15
#36HyCoSeq: Contextual Hyperbolic Representation Learning for Genomic SequencesChenhao Zeng, Zhibin Pu, Shufei Gecs.LG2026-09-15
#37Measuring Annotation Efficiency for Handwritten Devanagari Recognition: Sample-Complexity Curves for Four Pretraining RegimesManglesh Kumar Pandey, Sumit Kumar Banshalcs.CV2026-09-15
#38Hyper-RED: Scalable Event Pre-training via Semantic Hypergraph DistillationMeisen Wang, Zhiqiang Tian, Wei Bao +3cs.CV2026-09-15
#39Bridging the Perceptual Gap: Residual-Enhanced Downscaling and Manifold-Aware Perception Alignment Adaptation for NR-IQAYu Li, Zhengran Shen, Yachun Mi +2cs.CV2026-09-15
#40GrowMTP: Can RL Grow Its Own Draft Head?Minghua He, Lingzhe Zhang, Yuan Liu +2cs.LG2026-09-15
#41Which Pretext Task Transfers? Self-Supervised Pretraining Objectives for Lung UltrasoundMoein Heidari, Junbo Rao, Jai Choraria +3cs.CV2026-09-15
#42Style-Debiased DPO: Updating LLM Knowledge with Factuality-Aware Synthetic Preference DataTakayuki Yamamoto, Daisuke Kawaharacs.CL2026-09-15
#43Drift Field Net: Learning Ocean Lagrangian advection fields from in-situ and satellite observationsThéo Archambault, Pierre Garcia, Mattia Romero +2cs.LG2026-09-14
#44Compute-Optimal Pretrain--Fine-tune in Ridge Gradient DescentAlex Buna, Fanghui Liu, Patrick Rebeschinistat.ML2026-09-14
#45Disentangling Representation Evolution in Transformers through Directional DecompositionShwai He, Haichao Zhang, Shen Yancs.CL2026-09-14
#46Multi-View Molecular Representation Learning with Hierarchical Graphs and Contextualized FingerprintsGwang-Hyeon Yun, Jong-Hoon Park, Bing Hu +3cs.LG2026-09-14
#47A Unified Vision-Language Model for PSMA PET/CT Report Generation, Visual Question Answering, and Lesion SegmentationYang Xing, Jiong Wu, Savas Ozdemir +11cs.CV2026-09-14
#48To Each Language Its Tokenizer: Modular Tokenizers for Efficient Multilingual LLMsFranck Signe, Hippolyte Pilchen, François Yvon +1cs.CL2026-09-14
#49MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-TrainingTianyi Xu, Daniel Pimentel-Alarcón, Zuzana Buřivalová +1cs.SD2026-09-14
#50MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse LookupMuchen Li, Leonid Sigal, Renjie Liaocs.CL2026-09-14

all trends · matching is case-insensitive substring after tokenization