| 1 | MS-GLA: Multi-Scale Gated Linear Attention for Addressing Representational Bottlenecks via Multi-Temporal Resolution | Prasoon Dev, Anirudh Sankar, Vasudeva Varma | cs.CL | 2026-09-28 |
| 2 | Not All Thinking is Created Equal: Latent Reasoning Discovers a Recurrent Search Algorithm for Depth Generalization | Huzi Cheng, Zhewei Zhang | cs.AI | 2026-09-28 |
| 3 | Verifiable Visual Rewards Transfer from Synthetic Scenes to Natural Prompts | Shuyue Stella Li, Xiaochuang Han, Yulia Tsvetkov +1 | cs.AI | 2026-09-28 |
| #4 | Learning the Robustness Mechanism with Bilevel Optimization | Yiyang Shen, Qihang Lin, Weiran Wang | cs.LG | 2026-09-28 |
| #5 | MechBench: Can AI Scientific Agents Discover Mechanisms Beyond Phenomenal Laws? | Zihan Yu, Jiadong Zhang, Jialin Cheng +2 | cs.AI | 2026-09-28 |
| #6 | SRHarness: A Harness for Agentic Symbolic Regression | Zihan Yu, Shixuan Zhou, Hao Huang +2 | cs.AI | 2026-09-28 |
| #7 | Building Transformation Layers for Riemannian Neural Networks | Ziheng Chen | cs.AI | 2026-09-28 |
| #8 | Automated Species Identification in Camera Trap Images for Wildlife Conservation | Nowshin Amin, Nafisa Tabassum Oyshi, Tahmid Abrar Zidan +2 | cs.CV | 2026-09-28 |
| #9 | GLAD: Global-Local Adaptive Detector for Robust Speech Deepfake Detection | Zelin Zhao, Guanjie Huang, Danny Hin Kwok Tsang +1 | cs.SD | 2026-09-28 |
| #10 | First Learn, Then Memorize: The Spectral Bias of Diffusion Models | Raphaël Urfin, Tony Bonnaire, Giulio Biroli +1 | cs.LG | 2026-09-28 |
| #11 | Ego-Forge: Text and Geometric-Attention Free Exo-to-Egocentric Video Generation | Mohammad Mahdi, Luc Van Gool, Danda Pani Paudel | cs.CV | 2026-09-28 |
| #12 | Hyper Algorithm Design Agent: Evolving Learnable Optimizer from Zero | Zipei Yu, Yue-Jiao Gong, Zeyuan Ma +2 | cs.AI | 2026-09-28 |
| #13 | EP-Mem: Elastic Privacy Memory for Social Relationship-Aware LLM Agents | Fengzhou Sun, Yuan Zhang, Xintong Yu +1 | cs.AI | 2026-09-28 |
| #14 | Small transformers track Bayesian evidence for latent common causes via a context-invariant mechanism | Amir Mohammadpour, Michael Franke | cs.LG | 2026-09-28 |
| #15 | Coordinated Lane-Level Variable Speed Limits and Ramp Metering for Successive Weaving Segments Considering Merging/Diverging Risks: A Hybrid Model Predictive Control and Multi-Agent Reinforcement Learning Approach | Guodong Ma, Baofeng Sun, Wenyu Yang +1 | math.OC | 2026-09-28 |
| #16 | Universality and Generalization of Causal Transformers Across Context Lengths | Takashi Furuya, Maarten V. de Hoop, Gabriel Peyré | cs.LG | 2026-09-28 |
| #17 | BA-DPO: Bias-Adjusted Direct Preference Optimization for Language Model Alignment | Antonio Ferrara, Alberto Rumi, Francesco Bonchi | cs.LG | 2026-09-28 |
| #18 | ActionUNet: Improving Robustness of VLA Models with Efficient Multi-scale Fine-tuning | Di Zhu, Ziheng Yan, Fang Wan | cs.CV | 2026-09-28 |
| #19 | What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling | Renping Zhou, Zanlin Ni, Zihao Fan +8 | cs.CV | 2026-09-28 |
| #20 | Drug-Target Interaction Prediction via Hierarchical Sequential Cross-Attention over Chemical and Protein Language Models | Khadidja Henni, Hamza Abdelali, Abdelkrim Aries +4 | cs.LG | 2026-09-28 |
| #21 | ESTHER: Egocentric Stereo Hand Estimation and Reconstruction in the Wild | Hongyu Ma, Hairong Qu, Shiqi Zhao +2 | cs.CV | 2026-09-28 |
| #22 | Instance-Adaptive Prompts as Context for Time-Series Foundation Models | Zehao Xiao, Shifeng Xie, Lei Zan +5 | cs.LG | 2026-09-28 |
| #23 | Information-Theoretic Analysis of Next-Token Prediction under Markovian Data | Masoud Kavian, Abdellatif Zaidi, Milad Sefidgaran | stat.ML | 2026-09-28 |
| #24 | DBCF: Dual-Branch Complementary Fusion of Foundation Models for Generalized Deepfake Detection | Fengming Gu, Mingjie He, Zonghui Guo +2 | cs.CV | 2026-09-28 |
| #25 | From Pixel Generation to Topological Inference: Structural Dual Super-Resolution for Trustworthy Cross-Physical-Domain Trabecular Morphology Learning | Fan Zhang, Yi Zhang, Ling Wang | cs.CV | 2026-09-28 |
| #26 | Unified Trajectory Matching Policy Optimization: Diverse T2I Generation and VLA Generalization | Zhiyuan Ma, Jiaming Li, Lingzhen Li +7 | cs.CV | 2026-09-28 |
| #27 | Backdoor as Probe: Test-Time Adversarial Defense for CLIP | Zhongqi Wang, Jie Zhang, Nie Sen +3 | cs.CV | 2026-09-28 |
| #28 | Beyond Site Agreement: Re-estimation for Brain Network Generalization | Yingxu Wang, Kunyu Zhang, Yanwu Yang3 +4 | cs.LG | 2026-09-28 |
| #29 | Deep Weighted Bellman Residual Minimization for $Q^*$ Estimation | Lican Kang, Jerry Zhijian Yang, Cheng Yuan +1 | cs.LG | 2026-09-28 |
| #30 | Recent Advances in Agentic Agri-Robotic Phenotyping: A Perspective Review from Fragmented Multimodal Sensing to Unified PhenoAgent Intelligence | Muhammad Owais, Ehtesham Iqbal, Samee Ullah Khan +3 | cs.CV | 2026-09-28 |
| #31 | Preference-Guided Adaptation for Open-Vocabulary Semantic Segmentation via Prompt Disagreement | Hyun-Kurl Jang, Jihun Kim, Kuk-Jin Yoon | cs.CV | 2026-09-28 |
| #32 | SentZero: An Enhanced Sentence-Centric Vision-Language Pretraining for Multi-Task Zero-Shot Chest X-Ray Analysis | Hangyul Yoon, Hyungyung Lee, Edward Choi +1 | cs.CV | 2026-09-28 |
| #33 | Alignment-Guided Flow Transformer for Efficient Vision-Language-Action Policy Learning | Shengchao Hu, Peng Wang, Qiyang Zhou +5 | cs.LG | 2026-09-28 |
| #34 | When Does Structured Knowledge Help Neural Theorem Proving? | Sareh Nabi, Roland Vogl, Marzieh Nabi | cs.AI | 2026-09-28 |
| #35 | Understanding Generalization Requires Universal Induction | Aram Ebtekar, Marcus Hutter, Danica J. Sutherland | stat.ML | 2026-09-28 |
| #36 | VastMAT: A Large-Scale Multi-Category Benchmark for Multi-Animal Tracking | Zhizhen Li, Zan Wang, Huidong Peng +4 | cs.CV | 2026-09-28 |
| #37 | Learning to Optimize through Solver-Grounded Self-Play | Xia Jiang, Yaoxin Wu, Chenyu Zhou +3 | cs.LG | 2026-09-28 |
| #38 | Same Tasks, Different Apps: Why Mobile GUI Agents Fail to Generalize? | Tien Tran, Namho Koh, Daiki E. Matsunaga +2 | cs.AI | 2026-09-28 |
| #39 | The Devil is in the Spectrum Bias: Spectrum-Balanced Feature Matching for Robust Representation Distillation | Kuniaki Saito, Yoshitaka Ushiku | cs.CV | 2026-09-28 |
| #40 | Beyond One Epoch: Uncertainty-Weighted Sensitivity Regularization for Recommendation Models | Richard Lettich, Shagun Gupta | cs.LG | 2026-09-28 |
| #41 | GenoMorph: Pathway-Grounded Genomic Disease Reasoning via Adaptive Latent Computation | Tanmoy Kanti Halder, Akash Ghosh, Arijit Roy +1 | cs.AI | 2026-09-28 |
| #42 | PhysFieldBench: Can Multimodal Models Understand Physical Fields? | Yuezhou Ma, Huikun Weng, Jialong Wu +5 | cs.AI | 2026-09-28 |
| #43 | Do World Models Learn Global Understanding? | Alexander Detkov, Matt Thomson | cs.LG | 2026-09-28 |
| #44 | Singularities of Non-negative Matrix Factorization and their application to Bayesian inference | Naoki Hayashi, Yota Maeda, Yasushi Esaki | stat.ML | 2026-09-28 |
| #45 | A Multi-Dataset Benchmark of YOLO-Based Weed Detection in Precision Agriculture | Hristina Zdraveska, Vlatko Spasev, Ivica Dimitrovski +2 | cs.CV | 2026-09-27 |
| #46 | On the Two Faces of Adam in Separable Linear Classification | Chen Fan, Csaba Szepesvári | cs.LG | 2026-09-27 |
| #47 | An Active-Bottleneck Mechanism for Weak-to-Strong Generalization | Mohammad Zeinalpour, Amir Najafi | stat.ML | 2026-09-27 |
| #48 | Selecting Diverse SFT Traces Improves Post-RL Generalization | Dylan Zhang, Mingyuan Wu, Jinning Li | cs.LG | 2026-09-27 |
| #49 | Does Adversarial Training Improve Generalization in Multi-View VLAs? Revealing and Mitigating View Collapse | Futa Waseda, Shuhei Kurita, Isao Echizen | cs.AI | 2026-09-27 |
| #50 | Prompt-Anchored Residual Adaptation for Biomedical Vision-Language Models | Jingxuan Kang, Qianying Yue, Che Liu +1 | cs.CV | 2026-09-27 |