| Which Medical Questions Deserve Rationales? Perturbation-Sensitive Selection for Robust QAarXiv:2609.09684cs.CL | Yuexin Wu, Dayou Yu, Vasile Rus | — | 11 Sept 2026 | — | — | — | — |
| Looped GPT-BERT: Trading Parameters for Computation in Small Language ModelingarXiv:2609.09691cs.CL | Tingshuo Fan, Hongtao Mu, Tianyu Zhou +2 | — | 11 Sept 2026 | — | — | — | — |
| CT-SAFR: Safe and Interpretable Chain-of-Thought Reasoning for Autonomous Robots: A Multi-Layered Verification Framework for Trustworthy AI-Driven Robotic Decision MakingarXiv:2609.09692cs.RO | Cagri Temel | — | 11 Sept 2026 | — | — | — | — |
| When Auditors Fabricate: Batch-Size Degradation and Confident Hallucination in LLM Detection of Planted Document ContaminationarXiv:2609.09696cs.CL | Karan Parekh, Sanjana Pendyala Ravinder, Sana Mhapsekar +1 | — | 11 Sept 2026 | — | — | — | — |
| Kernel-Complexity Edge Sanitization for Training-Free Defense against Structural Graph AttacksarXiv:2609.09698cs.LG | Yaning Jia, Shenyang Deng, Yaoqing Yang +2 | — | 11 Sept 2026 | — | — | — | — |
| Distilling Image Prototypes for Guided Test-Time AdaptationarXiv:2609.09737cs.CV | Liwen Wang, Xingbo Dong, Iman Yi Liao +2 | — | 11 Sept 2026 | — | — | — | — |
| HiRAD: A Flexible Large-Scale AGV Routing SystemarXiv:2609.09752cs.RO | Yunjie Huang, Ruizhong Wu, Mengxuan Zhang +2 | — | 11 Sept 2026 | — | — | — | — |
| Fine-Tuning a KV Cache Concatenation-Aware Model or Recomputing KV Caches? Why Not Both?arXiv:2609.09768cs.LG | Fumihiko Tachibana, Daisuke Miyashita, Jun Deguchi | — | 11 Sept 2026 | — | — | — | — |
| BRACE: Anchored Bellman-Residual Correction for Stale Critics in Asynchronous RLarXiv:2609.09783cs.LG | Guanqun Zhao, Zijun Xie, Binbin Zheng +2 | — | 11 Sept 2026 | — | — | — | — |
| Pairit: A Platform for Live Experiments on Human-AI CollaborationarXiv:2609.09789cs.HC | Harang Ju, Sinan Aral | — | 11 Sept 2026 | — | — | — | — |
| LogiScope-VQA: Benchmarking Vision-Language Models for Logistics Hazard Identification in Industrial ScenariosarXiv:2609.09790cs.CV | Hanjing Zhou, Mingze Yin, Ying Lian +2 | — | 11 Sept 2026 | — | — | — | — |
| How Fragile Is Safety Alignment at Frontier Scale? A Single-Direction Attack on a 320B MoEarXiv:2609.09793cs.CR | Yi Shi, Tanyu Chen, Kai Shen | — | 11 Sept 2026 | — | — | — | — |
| CS-Guard: Benchmarking LLM Guardrails for Code Generation SecurityarXiv:2609.09798cs.CR | Jinyang Li, Mingyu Guo, Hung X. Nguyen | — | 11 Sept 2026 | — | — | — | — |
| uFlowCSP: Crystal Structure Prediction using Mean flow generative modelsarXiv:2609.09799cond-mat.mtrl-sci | Sourin Dey, Dipannoy Das Gupta, Lai Wei +2 | — | 11 Sept 2026 | — | — | — | — |
| Subgroup Membership Inference Audits of Differentially Private Synthetic TextarXiv:2609.09848cs.CR | Yidan Sun, Viktor Schlegel, Srinivasan Nandakumar +2 | — | 11 Sept 2026 | — | — | — | — |
| Can AI Agents Detect and Repair Artifact Drift in Network Experiments?arXiv:2609.09849cs.NI | Tianzhu Zhang, Weichen Tao, Changgang Zheng +2 | — | 11 Sept 2026 | — | — | — | — |
| With a Thermomix You Lose the Ability to Cook: A Kitchen Machine Analogy for Applications of Generative AI in EducationarXiv:2609.09856cs.CY | Nikol Rummel, Valentina Nachtigall, Ernesto Panadero | — | 11 Sept 2026 | — | — | — | — |
| Forward-Free LLM Depth Pruning via Weight RedundancyarXiv:2609.09883cs.LG | Vincent-Daniel Yun, Woosang Lim | — | 11 Sept 2026 | — | — | — | — |
| Albedo Estimation via Latent Bridge MatchingarXiv:2609.09884cs.CV | Carme Corbi, David Serrano-Lozano, Javier Vazquez-Corral +1 | — | 11 Sept 2026 | — | — | — | — |
| Strangers to Themselves: What Language Models Say About Themselves Is GenericarXiv:2609.09899cs.LG | Phil Blandfort, Urja Pawar | — | 11 Sept 2026 | — | — | — | — |
| FlowCPO: A Unified Divergence View of Preference Alignment for Flow ModelsarXiv:2609.09905stat.ML | Yansen Han, Shengyi Liao, Peng Sun +2 | — | 11 Sept 2026 | — | — | — | — |
| Improving Cross-Lingual Token Representations by Adding a Pinch of SALTarXiv:2609.09953cs.CL | Guillem Ram\'irez | — | 11 Sept 2026 | — | — | — | — |
| Fidelity-Aware Scheduling of Quantum Circuits on Multi-QPU SystemsarXiv:2609.09980quant-ph | Innocenzo Fulginiti, Antonio Tudisco, Salvatore Zammuto +2 | — | 11 Sept 2026 | — | — | — | — |
| What Makes Adversarial Examples Transfer Across Deepfake Detectors?arXiv:2609.10002cs.CV | Rafael M. Mamede, Pedro C. Neto, Ana F. Sequeira | — | 11 Sept 2026 | — | — | — | — |
| MetroLLM-Bench: Evaluating Language Models as Transit Kiosk RuntimesarXiv:2609.10016cs.LG | Remco Hendriks (Continker) | — | 11 Sept 2026 | — | — | — | — |