PaperScope
LIVE · 2026-09-03 05:40 UTC

transformer 31 papers this week · -6% WoW

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

Latestcs.CLcs.LGcs.AIcs.CV

Mentions per Day (30d)

Latest Papers

#TitleAuthorsCatDate
1Graph Machine: Towards Better Pretraining via EdgesLintai Houcs.LG2026-09-02
2Towards Trustworthy Autonomous Robots: An Explainable AI-Based Decision FrameworkCagri Temelcs.RO2026-09-02
3UE5M3 FP4 Block Scaling for Stable Language Model PretrainingRobert Hu, Carlo Luschi, Paul Balancacs.LG2026-09-02
#4Efficient All-in-One Weather Restoration using Spectral HarmonizationPaula Garrido-Mellado, Daniel Feijoo, Yuning Cui +2cs.CV2026-09-02
#5Trace as State: Reasoning Traces as Conditional States for Long-Context TransformersXu Zou, Jie Tangcs.CL2026-09-02
#6GaLe: memory-efficient Global Approximate and Local Exact featuresAlberto Ancilotto, Elisabetta Farellacs.CV2026-09-02
#7oHC: Orthogonal Hyper-Connections on SO(4) via QuaternionsHaoqiang Guo, Xuyi Chen, Bo Ke +5cs.CL2026-09-02
#8UnCapsTSR: An Unsupervised Transformer-based Image Super-Resolution Approach for Capsule Endoscopy ImagesAnjali Sarvaiya, Shubh Kawa, Lalit Agrawal +3cs.CV2026-09-02
#9When Decodability Is Not Enough: Logical Validity Representations, Behavioral Dissociation, and Causal Tests in Language ModelsSmitha Muthya Sudheendra, Jaideep Srivastavacs.CL2026-09-02
#10Uncertainty-Guided Adverse Weather Restoration via Gated Transformer NetworkZheke Jin, Yuning Cui, Tianle Jin +2cs.CV2026-09-02
#11MultiGhostBench: A Multilingual Benchmark for Long-Form LLM-Generated Text Attribution under Distribution ShiftsMatteo Greco, Anudeex Shetty, Andrea Tagarelli +1cs.CL2026-09-02
#12GlyphAnchor: Enhancing Visual Text Rendering via Position-Anchored Glyph PriorsQiang Xiang, Shuang Sun, Binglei Li +4cs.CV2026-09-02
#13AGI Maze Prediction Datasets: A Compact Benchmark for Learning World Dynamics with TransformersAlexey Potapovcs.LG2026-09-02
#14If It Moves, Radar Knows: A Physics-Aware Radar Transformer for Class-Agnostic Moving-Object DetectionYinghao Sun, Shuguang Li, Jinliang Shao +1cs.CV2026-09-02
#15SMart: A Multi-source Multi-phase Time Series Representation Transfer FrameworkFang He, Wang-chien Leecs.LG2026-09-02
#16Lightweight Adaptation of General-Purpose VLMs for Multispectral and SAR Image UnderstandingShanji Liu, Kelu Yao, Junxiao Xue +5cs.CV2026-09-02
#17C$^{3}$T: Counterfactual Causal Reasoning for Sentiment Shifts in Social-Media Conversation TreesS M Rafiuddin, Atriya Sencs.CL2026-09-02
#18XMerge: Cross-Axis Selection and Reconstructive Layer Merging for LLM Depth CompressionJundong Hu, Shekar Ramachandrancs.LG2026-09-02
#19The Dynamics of Continuous Mixture Collapse in Language ModelsAli Backourcs.LG2026-09-02
#20Aggregating Neighbor Embedding Projection and Rank-Based Manifold Learning for Image RetrievalVinicius Atsushi Sato Kawai, Gustavo Rosseto Leticio, Lucas Pascotti Valem +1cs.CV2026-09-02
#21OR-Transformer: Scaling Real-Time Decision-Making to 1,000 ItemsShuze Daniel Liu, David Simchi-Levi, Claire Chen +2cs.LG2026-09-01
#22Looped Transformers under the Jacobian Lens: Does the Global Workspace Survive Recurrence?Wenlong Wang, Fergal Reidcs.AI2026-09-01
#23Latent unified smooth Hamiltonians for excited state chemistryDavid Juergens, Martin Stöhr, Andreas E. Hillers-Bendtsen +2physics.chem-ph2026-09-01
#24Improved Automatic Target Recognition in Synthetic Aperture Sonar Imagery Using Large Deep Neural NetworksC. J. Moore, Alex Hurt, Jordan Malofcs.CV2026-09-01
#25Designing Versatile Samples for Learned Trajectory ScoringYaguang Li, Jiaru Zhang, Chuheng Wei +2cs.RO2026-09-01
#26CoViT: Instance-Correspondence Contrastive Learning for Vision TransformerYisen Wang, Zhirong Wu, Limin Wangcs.CV2026-09-01
#27Ten Architectures, One Error: Shared Failure Modes in Hyperspectral Classification under Spatially Disjoint EvaluationEhsan Faghih, Fatemeh Ashrafi, Marguerite Moore +1cs.CV2026-09-01
#28Emergence of Fibrations, Compression, and Symmetry Breaking in Artificial Neural NetworksOsvaldo M Velarde, Lucas C Parra, Alireza Hashemi +1cs.LG2026-09-01
#29Swin Meets EfficientNet: Lightweight Architectures for GAN-Based Face ForensicsSejuti Basu, Ashima Sood, Vijay Kumar +1cs.CV2026-09-01
#30ZipTok3D: High-Fidelity 3D Tokenization with Compact Token PrefixesMingda Lin, Weijie Wang, Zeyu Zhang +7cs.CV2026-09-01
#31What, Where, and How: Probing Spatiotemporal Representations in Video Foundation ModelsSharon S. Musa, Fereshteh Forghani, Harrish Thasarathan +3cs.CV2026-09-01
#32Benchmarking Spatial, Spectral, and Self-Supervised Cues for Face Forgery Detection under Realistic DegradationLucas Cunha, Lucas Sotomaior, Lucas Gasperin +3cs.CV2026-09-01
#33Does Imitation Learning Preserve Temporal Robustness in Dexterous Manipulation? An Expert-Learner Comparison Across Task Execution SpeedsClinton Enwerem, John S. Baras, Calin Beltacs.RO2026-09-01
#34Learning Sparse Decision Trees via Transformer Variational Auto-EncodersGiacomo Fidone, Alessio Cascione, Riccardo Guidottics.LG2026-09-01
#35Semantic-Guided Multimodal Preprocessing for Vision Transformer-Based Clear Cell Renal Cell Carcinoma GradingFatemeh Javadian, Zhu Chen, Zahra Aminparast +1cs.CV2026-09-01
#36Measuring consistency via ensemble margin and local prediction variability: Auditing decision systems in the presence of predictive multiplicitySinjini Banerjee, Tim Marrinan, Anand D. Sarwatestat.ML2026-09-01
#37Multimodal RGB-Infrared Combination for UAV-Based Wildfire Segmentation: A Comparative Study on FLAME3Matheus F. Kovaleski, Luís Garrote, Cristiano Premebida +2cs.CV2026-09-01
#38Polish ModernBERT: The Long and Short of Polish Language UnderstandingMichał Perełkiewicz, Sławomir Dadas, Rafał Poświata +1cs.CL2026-09-01
#39SMELT: Scaling Laws for Compute-Matched MoE Looped TransformersShaowen Wang, Ge Zhang, Kairong Luo +6cs.LG2026-09-01
#40One-Layer Transformer Provably Learns Multiclass One-Nearest Neighbor in ContextSkanda Athreya, Yutong Wangcs.LG2026-09-01
#41HiLRP: Toward One Trustworthy Explanation for Vision Transformer: Conservation-Valid Attribution via Attention PrimitivesSathiyamohan Nishankar, Pubudu Sanjeewani, Asanka Perera +1cs.CV2026-09-01
#42Solving In-Table Prediction Problems by Deep Neural Networks with Performance Evaluation Using Synthetic DataXiao Zhao, Daniela Oelkecs.LG2026-09-01
#43From Language to Behavior: Scaling Sequence Transformers for Industrial Recommendation Ranking with Rec-Native DesignsJie Chen, Xiangqian Yu, Yanchao Lian +9cs.IR2026-09-01
#44Position Matters: Feature Inversion Attacks in ViT Split Inference with Token Reduction and ShufflingStefano Leggio, Giulio Rossolini, Alessandro Biondics.CR2026-09-01
#45Multi-Head Self Attention is a Parameter Identification MechanismW. Ross Morrowcs.LG2026-09-01
#46Recent Developments in Transformer Inference Deployment on FPGA Platforms: A SurveyArjan Blankestijn, Uraz Odyurt, Amirreza Yousefzadehcs.LG2026-09-01
#47Births are difficult to predict even with rich survey and full-population register dataElizaveta Sivak, Emily M. Cantrell, Thomas Emery +109cs.LG2026-09-01
#48Scaled Idempotence in Transformer Attention: Paired OV Geometry and Shared-Value AlgebrasJiming Feng, Junliang Lics.LG2026-09-01
#49ViTAMINS: An Empirical Study of Training Self-Supervised Vision Transformers with Synthetic Hard NegativesNikos Giakoumoglou, Andreas Floros, Kleanthis-Marios Papadopoulos +1cs.CV2026-09-01
#50Low-Quality Face Recognition using Center Aligned Representations and Local Margin ConstraintsVedat Can Dilaver, Benjamin S. Riggancs.CV2026-09-01

all trends · matching is case-insensitive substring after tokenization