| 1 | Predictable Failure in Multi-Hop Retrieval: Score-Distributional Confidence Scoring and Abstention | Andre Bacellar | cs.IR | 2026-09-18 |
| 2 | LLMs as Feature Engineers for Text-and-Tabular Prediction | Merwan Barlier, Blaz Skrlj | cs.LG | 2026-09-18 |
| 3 | Catena: A Comprehensive Software Suite for Large-Scale Connectomics | Samia Mohinta, Pedro Gómez-Gálvez, Shi Yan Lee +5 | cs.CV | 2026-09-18 |
| #4 | Object Detection Benchmarks are Incomplete: The Role of Label Errors and Annotation Uncertainty | Sarina Penquitt, Jonathan Klees, Antonia van Betteray +4 | cs.CV | 2026-09-18 |
| #5 | XCalib Depth-Guided Geometric Optimization for Dense Thermal-Visible Video Registration | Aurelien Godet, Gabriel Jobert, Mauro Dalla Mura | cs.CV | 2026-09-18 |
| #6 | SFVO: Decoupled Confidence-Guided Stereo-Flow Visual Odometry with Bidirectional PnP | Kai Zhang, Guoyang Zhao, Jun Ma | cs.CV | 2026-09-18 |
| #7 | Balanced Prompt Adaptation against Entropy-Induced Collapse for Test-Time Binary Segmentation | Zhengshan Wang, Joshua Charles Webster-Ford, Yifei Tian +3 | cs.CV | 2026-09-18 |
| #8 | DRT: Dense Reasoning Trace for Efficient and Grounded Multimodal Reasoning | Wan Xu, Yuanfan Guo, Kevin Han +2 | cs.CV | 2026-09-18 |
| #9 | Accelerating Dense LLMs via L0-regularized Mixture-of-Experts | Zhenyu Zhang, Jiudong Yang, Zhaowen Tao +1 | cs.AI | 2026-09-18 |
| #10 | Extending Decoupled Attention to Dense Prediction and Masked Training for Multi-Channel Images | Umar Marikkar, Sameed Husain, Muhammad Awais +1 | cs.CV | 2026-09-18 |
| #11 | Beyond Accuracy: Centroid-Guided Contrastive Loss for Structured Fraudulent Job Posting Detection | Syed Ali Ahmed, Malaika Raza, Muhammad Shoaib Siddiqui +1 | cs.AI | 2026-09-18 |
| #12 | Evaluating In-Context Learning and Retrieval Strategies for Devanagari Post-OCR Correction | Abhishek Bhandari, Gaurav Harit | cs.CL | 2026-09-18 |
| #13 | On Repulsive and Attractive Teachers: Separating Correctness from Behavior in Self-Distillation | Anton Baumann, Akmal Ashirmatov, Leo Schmidt-Traub +4 | cs.LG | 2026-09-18 |
| #14 | From Retrieval to Recognition:How Vision--Language Models Become OCR Specialists | Yuanxiang Huangfu, Hanmeng Zhong, Linqing Chen +1 | cs.CV | 2026-09-18 |
| #15 | VidOmni-Bench: A Benchmark for Fine-Grained Video Understanding via Spatio-Temporal Event Verification across Complexity and Duration | Changbeen Kim, Junwon Chang, Kipyo Kim +3 | cs.CV | 2026-09-18 |
| #16 | Adaptive World Memory 3D Foundation Model for Scalable 3D Mapping, Localization, and Rendering | Tianchen Deng, Guole Shen, Yilin Shen +7 | cs.CV | 2026-09-18 |
| #17 | VoxelTTO: Voxel-Aligned Feed-Forward 3D Gaussian Splatting with Test-Time Optimization | Yibin Zhao, Yihan Pan, Yangwen Li +2 | cs.CV | 2026-09-18 |
| #18 | Driving on Registers, Reasoning on Risk: Risk-Aware Occupancy for Register-Based End-to-End Autonomous Driving | Jiaxing Chen, Hengduo Zou, YuKai Qin +3 | cs.AI | 2026-09-18 |
| #19 | Risk-Aware Occupancy for Safety-Oriented End-to-End Autonomous Driving | Jiaxing Chen, Hengduo Zou, Yiren Zhao +1 | cs.AI | 2026-09-18 |
| #20 | DENSE: Distilling Agent Trajectories into Evidence-Grounded Shortcut Trees for Self-Refinement | Siyuan Liu, Fan Yu, Dongyu Ru +5 | cs.AI | 2026-09-18 |
| #21 | Cube-Splat: High-Fidelity 360° Gaussian Splatting SLAM via Cubemap Factorization and Adjoint-Consistent Optimization | Xiangfei Guo, Hao Shi, Yufan Zhang +4 | cs.CV | 2026-09-18 |
| #22 | IntBMoE: Integrating Block-Level Conditioning into Expert Composition for Full-Participation Mixture-of-Experts | Ran Cheng, Longfei Xu, Zheng Liu +2 | cs.LG | 2026-09-18 |
| #23 | Combining Object Detection with Geometry-Aware Clustering to Distinguish Overlapping Plants in UAV Imagery | Ik Jae Lee, Hieu D. Nguyen, Mahbubur Meenar +2 | cs.CV | 2026-09-18 |
| #24 | 4DGS-Fixer: Generative Sparse-View 4D Gaussian Splatting with Iterative Refinement Guided by Video Diffusion Priors | Haitao Huang, Shenghao Zhao, Boyuan Tian +7 | cs.CV | 2026-09-18 |
| #25 | RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning | Yan Yu, Zhengxi Lu, Yizhou Liu +8 | cs.CL | 2026-09-17 |
| #26 | Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation | Haocheng Xi, Yiming Xie, Hexu Zhao +8 | cs.LG | 2026-09-17 |
| #27 | FunArt: Decoding Functional Structure and Articulation from Generative 3D Latents | Dennis Rotondi, Abdelrhman Werby, Kai O. Arras | cs.CV | 2026-09-17 |
| #28 | Learning Foresight without Explicit Trajectories for 3D Diffusion Policies | Zhongbo Zhang, Zaibin Zhang, Yifan Wang +3 | cs.RO | 2026-09-17 |
| #29 | DexTouch-WM: Learning Action-Conditioned Tactile World Models from Human Touch for Dexterous Robot Manipulation | Yan Qin, Yue Chen, Wenwei Lin +8 | cs.RO | 2026-09-17 |
| #30 | RawSLAM: Online HDR Gaussian SLAM from Linear Radiance | Marina Orozco González, Luis Merino | cs.CV | 2026-09-17 |
| #31 | NS3Learn: Transferring 5G NR Mode-2 Reception Realism from ns-3 to the Veins/SUMO Stack for Connected-Vehicle Safety Assessment | Rasheed Bello, Arthur Mukwaya, Gurcan Comert +5 | cs.NI | 2026-09-17 |
| #32 | A Dual-Stream Regulated Reconstruction and Segmentation Network with Hierarchical Artifact-Prior Modeling for Ultra-Low-Field Pediatric Neuroimaging | Bahram Jafrasteh, Leo Milecki, Qingyu Zhao | cs.CV | 2026-09-17 |
| #33 | Relational Attention for Data-Efficient Language Modeling | Adrian Brasoveanu, Ece Takmaz, Jakub Dotlačil | cs.CL | 2026-09-17 |
| #34 | Training Neural Networks to Approach the Optimum Bayes Estimator in Dense Multi-Emitter Localization | Yi Sun, Mona Sharifi, Muzna Yumman | cs.LG | 2026-09-17 |
| #35 | Online Supervised Dimension Reduction with Random Features: Diagnostics and Computational Trade-offs | Zhenlin Yao, Wei Xiong | stat.ML | 2026-09-17 |
| #36 | Seismic Site Response Prediction from Sparse Observations Using Finite-Element-Pretrained Latent Dynamics | Yi Zhu, Su Chen, Xiaojun Li | cs.LG | 2026-09-17 |
| #37 | TouchSight: Bare-Handed Tactile Prediction from Egocentric Video via Generative Visual Augmentation | Danyan Zhou, Jinxuan Lu, Jiawei Lin +3 | cs.CV | 2026-09-17 |
| #38 | FreqDINO++: A Frequency-Guided Multi-Task Routing Vision Foundation Model for Universal Ultrasound Analysis | Qing Xu, Yixuan Zhang, Yue Li +7 | cs.CV | 2026-09-17 |
| #39 | AgriScope: Pixel-Grounded Multimodal Understanding for Agricultural Images | Abderrahmene Boudiaf, Mohamad Alanssari, Irfan Hussain +1 | cs.CV | 2026-09-17 |
| #40 | PointEvent: Rethinking Event-based Tiny Object Detection via Serialized Motion Evidence Accumulation | Zongze Wu, Baofeng Jia, Weiqi Yan +4 | cs.CV | 2026-09-17 |
| #41 | EPIG-Tree: Compute-Optimal Branching for Gradient-Efficient Reinforcement Learning | Nikita Khomich, Leopold Hermansson, Ido Hakimi | cs.LG | 2026-09-17 |
| #42 | Beyond Depth Truncation: Controlled Evaluation of Depth Utilization in Recursive Language Models | Ha Van Dau, Thanh Tung Khuat, Nguyen Thanh Dung | cs.AI | 2026-09-17 |
| #43 | TRACE: Accountable Agentic Retrieval for Source Discovery in Digital Archives | Donghan Bian, Marie Puren, Florian Cafiero | cs.AI | 2026-09-17 |
| #44 | BinoGen: Scaling egocentric binocular data for embodied visual perception and learning | Chunpeng Li, Ya-tang Li | cs.CV | 2026-09-17 |
| #45 | Benchmarking MLLMs via Cognitive Expected Scene Graph for Safety-Critical Visual Negation Understanding | Zhiyun Jiang, Hanyong Wang, Binbin Liang +3 | cs.CV | 2026-09-17 |
| #46 | The segmentation ceiling: why explicit left-ventricular masks do not improve learned ejection-fraction regression | Farshid Farhadi Khouzani, Paul La Plante, Bryar Mustafa Shareef +1 | eess.IV | 2026-09-17 |
| #47 | Understanding and Exploiting Diagonal Attention Sparsity in Autoregressive Image Generation | Daeun Kim, Junwha Hong, Changhun Oh +3 | cs.CV | 2026-09-17 |
| #48 | FCx: An algorithm for finding Feasible Counterfactual Explanations | Kleopatra Markou, Vana Kalogeraki, Dimitrios Gunopulos | cs.LG | 2026-09-16 |
| #49 | PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection | Sara Pieri, Evangelos Kazakos, Shizhe Chen +2 | cs.CV | 2026-09-16 |
| #50 | Track, Articulate, Act: Generating Articulation from Casual Human Videos | Jiaming Zhang, Homanga Bharadhwaj | cs.CV | 2026-09-16 |