| 1 | A Chosen Future Can Still Be Rewritten: Causal Writability in Video Models | Xingyun Wang, Haomin Zheng, Man Yuan +2 | cs.LG | 2026-09-14 |
| 2 | SURE-Map: Self-Correcting Streaming Geometric Foundation Model | Mingkai Liu, Hao Zhao, Xingxing Zuo | cs.CV | 2026-09-14 |
| 3 | A Language-Guided Multimodal Foundation Model for Zero-Shot and Multi-Task Brain Signal Analysis | Mingzhi Chen, Yiyu Gui, Guibo Luo +1 | cs.LG | 2026-09-14 |
| #4 | VideoScout: Learning Agentic Active Exploration with Adaptive Reasoning Pacing for Long Video Understanding | Weixin Xu, Zhenyu Yang, Bing Wang +2 | cs.CV | 2026-09-14 |
| #5 | Planning in the Backbone: DiffAdapterVLA for Native Continuous Trajectory Generation with Driving VLMs | Changxin Lu, Xiaoliang Meng, Yu Wu +5 | cs.RO | 2026-09-14 |
| #6 | T-LoopFormer: Token-Level Elastic-Depth Looped Transformers for Latent Reasoning With Dynamic Routing | Mingqian Yu, Wenpeng Zhang, Peilin Zhao | cs.AI | 2026-09-14 |
| #7 | DepthBenchCAD: When Does Deeper Auditing Yield More Reliable Conclusions? | Hongye Yang, Zhihao Xie, Shengjun Xiong +1 | cs.SE | 2026-09-14 |
| #8 | LG-VLN: A Zero-Shot Vision-and-Language Navigation Framework with LangGraph State Orchestration | Jianhe Zhao, Yanhua Qiu, Zhiyu Zhang +2 | cs.CV | 2026-09-14 |
| #9 | $\mathbb{SL}(n)$ Representation Learning: An Intrinsic Mixed-Curvature Space with Higher Curvature Capacities and Deeper Order-Aware Composition | Xingrun Li, Yusuke Mukuta, Xin Yang +2 | cs.LG | 2026-09-14 |
| #10 | Beyond Depth and Width: The Information-Slack Dilemma in Streaming Test-Time Compute | Xiaotian Zhang | cs.CL | 2026-09-14 |
| #11 | LiftGCN: Efficient Energy-Preserving Graph Learning via Joukowski Spectral Lifting for Finite Element Stress Prediction | Chen Zeng, Qiao Wang | cs.LG | 2026-09-14 |
| #12 | PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models | DeepCybo Team, Yu Bin, Haipeng Cao +51 | cs.CV | 2026-09-14 |
| #13 | CAL-MOS: Bridging Layers with Adapters for Robust MOS Prediction Across Speech Foundation Models | Alef Iury Siqueira Ferreira, Pedro Lustosa Rege Botelho, Fernanda Silva +5 | cs.SD | 2026-09-14 |
| #14 | GGUF-Metadata Prediction of Single-Sequence llama.cpp Throughput Across Three Systems | Xinyu Qiu, Chuhong Xu, Bo Su +3 | cs.AI | 2026-09-14 |
| #15 | Func-R1: Incentivizing Mathematical Function Reasoning in Multimodal Large Language Models | Mingze Yin, Xiaohan Wang, Dian Li +8 | cs.CL | 2026-09-13 |
| #16 | Calibrating Interpretability Instruments Before Trusting Their Verdicts | Orion Reblitz-Richardson | cs.LG | 2026-09-13 |
| #17 | Depth and Scale in the Sub-150M Regime: JugnuLM-53M vs JugnuLM-110M | Dushyant Rajput, Nirdesh Chauhan, Siddharth Kosaraju | cs.AI | 2026-09-13 |
| #18 | Disentangling Topology and Diversity in Multi-Agent LLMs for Multilingual Low-Resource Emotion Detection | Ulugbek Shernazarov, Charitha Ruwansiri Weerakon Basnayake, Abdelkhaleq El Jarjini +2 | cs.CL | 2026-09-13 |
| #19 | Parameter-Efficient Quantum NLP for Paraphrase Detection: Performance, Robustness, and Entanglement | Farha Nausheen, Khandakar Ahmed, Farina Riaz | quant-ph | 2026-09-13 |
| #20 | CGGT: Curve-Grounded Geometry Transformer for 3D Parametric Curve Reconstruction | Zhirui Gao, Renjiao Yi, Yunfan Ye +4 | cs.CV | 2026-09-13 |
| #21 | PRI-Net: A Lightweight Multimodal Framework for 3D UAV Localization | Zhixuan Chen, Jialiang Lu, Zhong Ye +2 | cs.CV | 2026-09-13 |
| #22 | DynEoMT: Learning Object Dynamicity from Online Segmentation Queries | Calvin Galagain, Martyna Poreba, François Goulette | cs.CV | 2026-09-13 |
| #23 | NeuroActiSep: Detecting Factual Hallucinations from Feed-Forward Neurons in a Single Pass | Ali Derogar Odolou, Reza Nazari, Mostafa Salehi | cs.CL | 2026-09-13 |
| #24 | Has Scientific Talent Shifted from Depth to Breadth?Evidence across Papers, Knowledge Inputs, Careers, and Teams | Xiaoshn Nee, Haobo Zhong, Xiaomin Ni | cs.DL | 2026-09-13 |
| #25 | Formal Properties of Language as Constraints on Neural Dynamics | Elliot Murphy | cs.CL | 2026-09-13 |
| #26 | One Size Does Not Fit All: Setting Inference Depth from the Questions a Deployment Actually Asks | Jerry Kaplan | cs.CL | 2026-09-12 |
| #27 | GraMRAG: Orchestrating Multi-Agent Multi-Step Reasoning via Graph Memory with Reinforcement Learning | Zhongyu Wang | cs.CL | 2026-09-12 |
| #28 | Finite-Time Node Separation in Recurrent Graph Neural Networks with Persistent Gaussian Perturbations | Mostafa Haghir Chehreghani | cs.LG | 2026-09-12 |
| #29 | ViperQ: Order Flow Pattern Recognition via Auction Market Theory for Reinforcement Learning Trading | Asser Moustafa, Rares-Mihail Neagu, Jugal Kalita | cs.AI | 2026-09-12 |
| #30 | Bypass Observation: A Conceptual Design of a Non-Intrusive Layer-Wise Semantic Extraction Architecture | Haibin Tong, Jiang Yu | cs.AI | 2026-09-12 |
| #31 | When Do Learned Priors Help Visual Inertial Estimation? A Controlled Study of Prior Integration, Calibration, Initialization, and Backend Consistency | Jinchang Zhang, Guoyu Lu | cs.RO | 2026-09-12 |
| #32 | Does Reasoning Improve Psychological Depth in Large Language Models? It Depends on Who's Judging | Ruichen Zheng, Yihe Wang, Fabrice Y Harel-Canada +4 | cs.LG | 2026-09-12 |
| #33 | Inside VLM Chart Reading: Tracing Value Reading from Vertical Bar Charts Across Space and Depth | Tianhao Niu, Qingfu Zhu, Wanxiang Che | cs.CL | 2026-09-12 |
| #34 | Trustworthy Agentic AI: A Comprehensive Cybersecurity and Systems Survey on Threat Landscapes, Defense Architectures, and Open Challenges | Seyedakbar Mostafavi | cs.AI | 2026-09-12 |
| #35 | Degraded but Not Entirely Ineffective: PE-Based Deformable Graph Neural Networks | Jinhua Wu, Xinliang Zhang | cs.AI | 2026-09-12 |
| #36 | Prefix Sharing Is a Sorting Problem | Rong He | cs.DS | 2026-09-12 |
| #37 | FlowTSFM: Turning Encoder Depth into Quantile Transport | Bahaeddine Abdessalem, Shifeng Xie, Zehao Xiao +6 | cs.LG | 2026-09-12 |
| #38 | EI-DDLGN: Efficient Encrypted Inference with Deep Differentiable Logic Gate Networks under TFHE | Mahmoud Y. M. Yassin, Mahmoud AbdelHafeez Sayed, Mostafa Taha | cs.CR | 2026-09-12 |
| #39 | GPU-CFR: 80x Faster Counterfactual Regret Minimization by Compiling the Game to Static Dataflow and CUDA Graph Replay | Boning Li, Longbo Huang | cs.DC | 2026-09-10 |
| #40 | Near-Optimal Reinforcement Learning with Multi-Step Transition Lookahead | Corentin Pla, Hugo Richard, Marc Abeille +1 | stat.ML | 2026-09-10 |
| #41 | Why Does Post-Training Quantization Work? | Yuxiang Chen, Michael Beyer, Jun Zhu +1 | cs.LG | 2026-09-10 |
| #42 | MMGait: Benchmarking and Unifying Gait Recognition across Heterogeneous Modalities | Saihui Hou, Chenye Wang, Qingyuan Cai +2 | cs.CV | 2026-09-10 |
| #43 | LoopVAE: Recurrent Depth Across Scales for Visual Tokenization | Zhiying Lu | cs.CV | 2026-09-10 |
| #44 | ActMap: Single-Pass Uncertainty Quantification from Generation-Time Activation Maps | Jacopo Dardini, Roberta Calegari | cs.AI | 2026-09-10 |
| #45 | X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation | Haojun Zhang, Yi Zou, Min Chen +7 | cs.SD | 2026-09-10 |
| #46 | From Queries to Narratives: Cultural Heritage Data Stories for Knowledge Graph Exploration and Quality Assessment | Tabea Tietz, Torsten Schrade, Etienne Posthumus +4 | cs.AI | 2026-09-10 |
| #47 | Portable Semantics, Private Dialects: Reuse and Negative Transfer in Latent Communication Between Language-Model Cells | Narcis Marincat | cs.AI | 2026-09-10 |
| #48 | Predictive Multi-Landmark OCT Tracking for Increased Motion Robustness | Konrad Reuter, Suresh Guttikonda, Chaitali Uday Karekar +2 | cs.CV | 2026-09-10 |
| #49 | Mr.LHDR: A Benchmark for Multimodal Real-World Long-Horizon Deep Research Agents | Minghao Guo, Meng Cao, Sui Zhao +10 | cs.AI | 2026-09-10 |
| #50 | 2AM: Grounding Agent-Side Memory as Guidance for Steerable Action Models in Long-Horizon Manipulation | Yutong Hu, Fengjiao Chen, Xuezhi Cao +1 | cs.RO | 2026-09-10 |