| Geometry Conditioning in an Embodied SLM: Training Controls and Robustness Diagnostics in a 0.8B Hybrid ModelarXiv:2609.09213cs.RO | Hao Li, Haofei Sun, Lin He | — | 11 Sept 2026 | — | — | — | — |
| Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research AgentsarXiv:2609.09219cs.MA | Jingjie Ning, Shanshan Zhong, Xiaochuan Li +1 | — | 11 Sept 2026 | — | — | — | — |
| Compute-Bounded Security Assurance - Coverage, Verification, and Response under Resource ConstraintsarXiv:2609.09229cs.CR | Jithin VG, Ditto PS | — | 11 Sept 2026 | — | — | — | — |
| Scaling Post-Training Ternarisation to Qwen3-8B Capability Retention, Reproduction, Lossless Packing, and Packed ExecutionarXiv:2609.09240cs.LG | Anirudh Malik, M Sparsh Mehra, Poojith Devan | — | 11 Sept 2026 | — | — | — | — |
| Distribution-Consistent Inference for Dynamic Sparse Mixture-of-ExpertsarXiv:2609.09241cs.LG | Dohyeon Kim, Bedionita Soro, Sung Ju Hwang | — | 11 Sept 2026 | — | — | — | — |
| Talking to Itself While Coding: What Makes Comments Help Code Generation?arXiv:2609.09242cs.SE | Dangfeng Pan, Zhensu Sun, Cenyuan Zhang +2 | — | 11 Sept 2026 | — | — | — | — |
| In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document PoisoningarXiv:2609.09243cs.CR | Iliano Fasolino | — | 11 Sept 2026 | — | — | — | — |
| Critical initialization destabilizes higher input derivatives in wide scalar-input networksarXiv:2609.09244stat.ML | Prashant Singh, Pranav Singh | — | 11 Sept 2026 | — | — | — | — |
| What Fixed-Rollout pass@k Evaluations Can IdentifyarXiv:2609.09245stat.ML | Pranav Singh, Prashant Singh | — | 11 Sept 2026 | — | — | — | — |
| No Free Checker: A Survey of Verifiers for Robot PoliciesarXiv:2609.09250cs.RO | Yang Wan, Xihang Yue, Zhirui Liu +2 | — | 11 Sept 2026 | — | — | — | — |
| DiffLUT-Net: Differentiable Training of FPGA LUT Networks with Learnable ConnectivityarXiv:2609.09254cs.LG | Jiaqi Ye, Xinrui Gong, Jingcun Wang +2 | — | 11 Sept 2026 | — | — | — | — |
| Voice or Stereotype? Disentangling Acoustic and Content-Based Gender in Speech-to-Speech ModelsarXiv:2609.09263cs.SD | Xiaoqun Liu, Tanu Mitra, Harshit Rajgarhia +1 | — | 11 Sept 2026 | — | — | — | — |
| Support Discovery With Iteratively Reweighted Least Squares for Fixed-Charge Network FlowarXiv:2609.09295math.OC | Sindura Saraswathi, Christian K\"ummerle | — | 11 Sept 2026 | — | — | — | — |
| Improving 5G AI-RAN MCS Selection by Predicting RetransmissionsarXiv:2609.09324cs.NI | Tamerlan Aghayev, Maxime Elkael, Michele Polese +2 | — | 11 Sept 2026 | — | — | — | — |
| Smart Adaptive Computing Across the Continuum: LLMs in IoT-Edge-Cloud Resource ManagementarXiv:2609.09348cs.DC | Antonino Vaccarella, Lanpei Li, Vincenzo Lomonaco +1 | — | 11 Sept 2026 | — | — | — | — |
| Auditable Emergency Triage for Maternal and Newborn Care in IndiaarXiv:2609.09356cs.CL | Shobhit Jagga, Aman Dalmia, Niharika Priyadarshini +2 | — | 11 Sept 2026 | — | — | — | — |
| VANTAGE-Bench: Evaluating the Infrastructure AI Gap in Vision-Language ModelsarXiv:2609.09396cs.CV | Zaid Pervaiz Bhat, Nimra Nayyar, Arihant Jain +2 | — | 11 Sept 2026 | — | — | — | — |
| An Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI FrameworksarXiv:2609.09404cs.CR | Viet K. Nguyen, Mohammad I. Husain | — | 11 Sept 2026 | — | — | — | — |
| Reliable Near-Field Multi-User Positioning Informed by Two-Stage MUSICarXiv:2609.09409eess.SP | Jiaying Li, Haifeng Wen, Changsheng You +2 | — | 11 Sept 2026 | — | — | — | — |
| SCCM : Stream Cruise Control Method for Automated Drift Detection and AdaptationarXiv:2609.09432cs.LG | Mohammad Abu-Shaira, Weishi Shi | — | 11 Sept 2026 | — | — | — | — |
| Efficient Leakage-Free Neural Architecture Search under Leave-One-Subject-Out EvaluationarXiv:2609.09433cs.LG | Heinke Hihn | — | 11 Sept 2026 | — | — | — | — |
| Distributed Physical Layer Authentication and Collaborative RSMA in Non-Terrestrial Networks via Graph Reinforcement LearningarXiv:2609.09475eess.SP | Parsa Rajabi, Mohammad Mirzaee, Mohammad Reza Abedi +2 | — | 11 Sept 2026 | — | — | — | — |
| From Fixed Keys to Readable Schemas: Small Language Models for Vehicle Agent Function CallsarXiv:2609.09476cs.LG | Hamed Jafarzadeh Asl, Yuanhao Yu, Vahid Partovi Nia | — | 11 Sept 2026 | — | — | — | — |
| Adaptive Distributed Physical-Layer Authentication and Attack Detection in 6G Non-Terrestrial Networks via Causal Meta-LearningarXiv:2609.09511eess.SP | Parsa Rajabi, Mohammad Reza Abedi, Nader Mokari +2 | — | 11 Sept 2026 | — | — | — | — |
| A Statistical Approach to Estimating Sample Size of Machine Learning ModelsarXiv:2609.09547cs.LG | Dat Phan-Trong, Sunil Gupta, Svetha Venkatesh | — | 11 Sept 2026 | — | — | — | — |