| 1 | SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models | Junchao Huang, Guian Fang, Shengju Qian +15 | cs.CV | 2026-09-02 |
| 2 | Discriminative World Models for Web Agents | Kelvin Li, Dhruv Pendharkar, Anish Pahilajani +6 | cs.AI | 2026-09-02 |
| 3 | ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding | Jitai Hao, Ke Yang, Qiang Huang +1 | cs.CV | 2026-09-02 |
| #4 | HyperStyler: Low-resource Authorship Style Transfer via Context-aware Style Navigation and Hypernetworks | Jongkyung Shin, Minguk Jeon, Chanwoo Park +1 | cs.CL | 2026-09-02 |
| #5 | From Reweighting to Rewriting: Unlocking the Intervention Effects of Influential Samples in Training Data Attribution | Yuzhang Luo, Chenpeng Wang, Jianhui Chen +1 | cs.CL | 2026-09-02 |
| #6 | Measurement-Driven Sub-Network Selection for On-Premise Retrieval-Augmented Factory Agents | Vasileios Rizeakos, Georgios Paisios, Alexandros Machairas +2 | cs.AI | 2026-09-02 |
| #7 | Incremental Pooled LLM Evaluation for Cost-Effective Retrieval Model Selection | Max Nelson, Hanoz Bhathena, Aviral Joshi +1 | cs.IR | 2026-09-02 |
| #8 | RVSD: Retrieval Vision Sparse Decoding for Mitigating Visual Hallucinations in Large Vision-Language Models | Canjie Liu, Jiawen Kang, Jinbo Wen +1 | cs.CV | 2026-09-02 |
| #9 | H3DNAS: Hardware-Aware ONNX-Native 3D Point Cloud Model Compression | Anchit Mulye, Rhythm Baghel, Sujay Kumar Ingle +1 | cs.LG | 2026-09-02 |
| #10 | When Persona Attributes Improve Population Alignment in Large Language Models | Leon Fröhling, Jens Rupprecht, Markus Strohmaier +1 | cs.CL | 2026-09-02 |
| #11 | Training seeds and model-selection stability in recommender-system evaluation | Juan Manuel Rodriguez, Oleg Lesota, Antonela Tommasel | cs.IR | 2026-09-02 |
| #12 | NE-R1: Enhancing Named Entity Recognition Model via Reinforcement Learning | Meixuan Chen, Hehan Li, Ruizhi Zhao +8 | cs.CL | 2026-09-02 |
| #13 | SALA: Semantic-Aware Logical Alignment for Complex Reasoning in In-Context Learning | Zhao Ji, Wenqing Chen, Zhixuan Chu +4 | cs.AI | 2026-09-02 |
| #14 | SEAL: Reinforcing Global Safety in Mixture-of-Experts through Shared Expert ALignment | Qingyu Meng, Yiwei Zha, Jiahuan Pei +3 | cs.LG | 2026-09-02 |
| #15 | SCX Router: Streaming Zero-Shot Model Selection with a Decoder-KV Classifier and a Real-World Task Ontology | Ihor Stepanov, Aleksandr Smechov, Mykhailo Shtopko +2 | cs.AI | 2026-09-02 |
| #16 | RouteGraph-Mona: Confusion-Aware Routing Fine-Tuning for Mineral Image Classification | Jierui Li, Zhiyuan Qi, Hao Zhu +7 | cs.CV | 2026-09-02 |
| #17 | CrashDiffuser: VLM-Guided Collision Intent Reasoning for Fine-Grained Safety-Critical Traffic Scenario Generation | Shucheng Zhang, Yuang Zhang, Bingzhang Wang +3 | cs.RO | 2026-09-02 |
| #18 | Progressive Pseudo-Label Optimization for Point-Supervised Change Detection | Hailong Ning, Hao Wang, Yimeng Wang +3 | cs.CV | 2026-09-02 |
| #19 | GenCAR: Generative Counterfactual Alignment with Risk-Controlled Selection for Out-of-Distribution Recommendation | Qianqian Wang, Yunshan Li, Jiawen Zeng +2 | cs.IR | 2026-09-02 |
| #20 | World-Coherent Decoding: Self-Verifying Test-Time Planning for World Action Models | Chuhan Zhang, Seiji Ito, Kenta Hoshino +2 | cs.CV | 2026-09-02 |
| #21 | SoK: Where Do Flow Labels Come From? Auditing Label Provenance in Encrypted Traffic Benchmarks | Sizhe Huang, Shujie Yang | cs.NI | 2026-09-02 |
| #22 | HyperMC: Multi-Fidelity Hyperparameter Tuning for Stochastic Gradient MCMC | Ming Tan, Xiyun Jiao | stat.ML | 2026-09-02 |
| #23 | XMerge: Cross-Axis Selection and Reconstructive Layer Merging for LLM Depth Compression | Jundong Hu, Shekar Ramachandran | cs.LG | 2026-09-02 |
| #24 | InstEditSeg: Instruction-Driven Image Editing for Polyp and Skin Lesion Segmentation | Ziquan Liu, Zhewei Zhu, Xuyang Shi | cs.CV | 2026-09-02 |
| #25 | NS-Copilot: An LLM-Driven Agent System for Autonomous Neuroscience Analysis | Wuche Liu, Yiran Qiao, Linlin Hou +4 | cs.CL | 2026-09-02 |
| #26 | CRISP: Cliff-awaRe Input-adaptive Sparse Prefilling with Structural-Mass-Motivated Routing | Huu Huy Nguyen, Chien Van Nguyen, Franck Dernoncourt +4 | cs.LG | 2026-09-01 |
| #27 | When Does Information Sharing Improve Decentralized Discovery? Aggregation, Independent Rescue, and Equilibrium Selection | Yohei Nakajima | cs.AI | 2026-09-01 |
| #28 | Designing Versatile Samples for Learned Trajectory Scoring | Yaguang Li, Jiaru Zhang, Chuheng Wei +2 | cs.RO | 2026-09-01 |
| #29 | When Can a Machine Trust a Statute? A Survival Certificate for Machine-Extracted Legal Logic | Surya Saka | cs.AI | 2026-09-01 |
| #30 | Efficient SWE Agent Benchmarking via Trajectory-Aware Evaluation | Kefeng Duan, Dewu Zheng, Yanlin Wang +7 | cs.SE | 2026-09-01 |
| #31 | Can LLMs Discover Scientific Laws in Real and Parallel Worlds? | Yiming Huang, Ziche Liu, Zhuohang Wu +11 | cs.AI | 2026-09-01 |
| #32 | Variable Selection for Feature-Based Newsvendor | Zhaoliang Yuan, Jie Wang | stat.ML | 2026-09-01 |
| #33 | Diffusion as a Training Curriculum for Timestep-Free Iterative Reasoning | Mariia Drozdova, Aidan Sirbu, Pietro Miotti +4 | cs.LG | 2026-09-01 |
| #34 | Scale-based Approach for Active Wildfire Segmentation on Satellite Imagery | Matheus F. Kovaleski, Cristiano Premebida, João Ruivo Paulo | cs.CV | 2026-09-01 |
| #35 | Polish ModernBERT: The Long and Short of Polish Language Understanding | Michał Perełkiewicz, Sławomir Dadas, Rafał Poświata +1 | cs.CL | 2026-09-01 |
| #36 | Diffusion Based Unpaired Data Learning for Inverse Problems | Chenglong Bao, Yiming Dang, Chenguang Duan +2 | cs.CV | 2026-09-01 |
| #37 | Accurate Reconstruction of Gas Turbine Blade Geometry Using 3D/2D Rigid Registration and CT View Optimization | Hristo Valtchanov, Nicolas Piché, Vladimir Brailovski +3 | cs.CV | 2026-09-01 |
| #38 | ExBind: A Controlled Diagnostic Benchmark for Visual-to-Executable Correspondence | Ziqian Wang, Yuxiao Cheng, Tingxiong Xiao +1 | cs.CV | 2026-09-01 |
| #39 | Bandits in Prod: Hyperparameter Optimization at Inference Time | Louis Abraham, Tuan-Anh Nguyen, Nicolas Devatine | cs.LG | 2026-09-01 |
| #40 | EmbodiedSkills: A Unified Framework for Orchestrating, Training, and Deploying VLA Agents | Wei Wang, Wenqiao Zhang, Yutong Lin +14 | cs.RO | 2026-09-01 |
| #41 | Post-Training Science for Supervised Fine-Tuning | Charles O'Neill, Mudith Jayasekara, Harry Partridge | cs.LG | 2026-09-01 |
| #42 | PersuaRL: Reinforcement Learning-Driven Multi-Expert Selection for Persuasive Dialogue Generation in Insurance | Rohan Kirti, Akash Ghosh, Aryan Vats +5 | cs.CL | 2026-09-01 |
| #43 | When Does Online Adaptation Pay on the Edge? A Leakage-Free Evaluation of Warmup, Learning-Rate Selection, and Resource Trade-offs for Time-Series Forecasting | Takumi Fujimoto, Hiroaki Nishi | cs.LG | 2026-09-01 |
| #44 | Hints Help But Do They Teach? Evaluating Skills Transfer in Code Generation | Will Badr | cs.SE | 2026-09-01 |
| #45 | Space Generative AI with Solar Energy Harvesting | Jierui Zhang, Jianhao Huang, Zhanwei Wang +1 | cs.AI | 2026-09-01 |
| #46 | Spawn Freely, Act Sparingly: Progressive Risk Vesting for Recursive LLM-Agent Trees | Molly Wang | cs.AI | 2026-09-01 |
| #47 | PCoMoE: Shifting MoE Inference from Monolithic Expert Selection to Fine-Grained Path Composition | Ziyan Gan, Fangxin Liu, Chenyang Guan +10 | cs.CL | 2026-09-01 |
| #48 | Right Frame, Wrong Rule: Cultural Cues Expose the Financial Knowledge Gap They Were Meant to Close | Rania Elbadry, Ahmed Heakl, Saeed Almheiri +12 | cs.CL | 2026-09-01 |
| #49 | ReFlowSET: Representation-Aligned Latent Flow Matching for SAR-to-EO Image Translation | Jeonghyeok Do, Seungchul Lee, Munchurl Kim | cs.CV | 2026-09-01 |
| #50 | Candidate-Expanding Routing with Permutation-Stabilized Experts for Mixed-Format Medical VQA | Hai-Dang Nguyen, Huy-Hieu Pham | cs.CV | 2026-09-01 |