| 1 | A richness-sensitive Acoustic Biodiversity Index from species-level detections: classifier benchmarking, false-positive control and validation against standard soundscape indices in an African savanna and an urban zoo | Muhammad Saeed, Dmitry Mikhaylov, Mohamed H. Alhosani +4 | cs.LG | 2026-10-30 |
| 2 | Aligning MLLMs with the Latent Structure of Human Cognition via Behavior-Derived Semantic Dimensions | Ning E, Changde Du, Yizhuo Lu +1 | cs.CL | 2026-10-30 |
| 3 | Automated Keyword Generation Using LLMs in a High-Volume Data Virtualization Service | Saiful Khan, Yiwen Xing, Joyraj Chakraborty +4 | cs.AI | 2026-10-30 |
| #4 | Text as an Index for Zero-Shot Cross-Domain Knowledge Tracing | Yin Yi, Haiping Ma, Siyu Song +2 | cs.CL | 2026-10-30 |
| #5 | Iterated Integrals as Lexical Fingerprints: Path Signature Embeddings for Lexical Similarity | Raj Shekhar Singh, Pratham Agarwal | cs.CL | 2026-10-30 |
| #6 | What Standard Evaluations Hide About Detectors of Hijacked LLM Agents: Rare Attacks, Unseen Tools and Benchmark Transfer | Mahmoud Abbasi, Juan M. Núñez V., Amin Shahraki | cs.CR | 2026-10-30 |
| #7 | Hard Sample-Conditioned Decorrelated Attention for Robust Face Recognition | Tahar Chettaoui, Guray Ozgur, Eduarda Caldeira +2 | cs.CV | 2026-10-30 |
| #8 | Peeling the Matryoshka: Extracting Ontological Structure from Retrieval Embeddings | Eunchan Kim, Inwhee Joe | cs.CL | 2026-10-30 |
| #9 | Latent-Lens: Visual Perception in Small Language Models Through Latent Communication | Mo Shahdloo, Faegheh Sardari, Mathew Salvaris | cs.LG | 2026-10-30 |
| #10 | Task Vectors Can Be Linearly Decomposed into Interpretable and Controllable Components | Yukiya Horiba, Hakaze Cho, Takahiro Yakoh | cs.LG | 2026-10-30 |
| #11 | Advancing Clinical Trial Outcome Prediction with Domain-Specific Large Language Models | Burak Bakkar, Hana Moalla, Mohamed Salem Jedidi +2 | cs.AI | 2026-10-30 |
| #12 | Connectivity-Aware Client Selection in Decentralized Federated Learning | Usevalad Milasheuski, Monica Nicoli, Stefano Savazzi | cs.AI | 2026-10-30 |
| #13 | Infinite ResNets are Gaussian Mean ODEs | Louis-Pierre Chaintron, Lénaïc Chizat, Javier Maass | cs.LG | 2026-10-30 |
| #14 | From the Zoo to the BULLPEN: Sample-Efficient LLM Profiling via Multi-Channel Model Embeddings | Russell Ro, Qiming Cui, Reza Abbasi-Asl | cs.AI | 2026-10-30 |
| #15 | SciGraphSelect: Auditable Scientific Data Selection through Knowledge--Reasoning Graphs | MiHyeon Kim, Ji-Eun Han, Eunkyeong Lee +2 | cs.AI | 2026-10-30 |
| #16 | Differential rank preservation manifold learning | Henry Han, Luyu Niu, Diane Li +1 | cs.AI | 2026-10-30 |
| #17 | A Low-Rank Space Captures Linear Alignment Between LLM and Human Neural Activity During Naturalistic Language Listening | Zach Paris, Emily Finn | cs.CL | 2026-10-29 |
| #18 | Retrieving from Your Own Mistakes: On-Policy Training of Embedding Models for Multi-Hop Retrieval-Augmented Generation | Chenjie Qiu, Zixuan Zeng, Shaobin Shi +3 | cs.AI | 2026-10-29 |
| #19 | How to Loop Your Transformer: Loop Scaling, Specialization, and Parallel Inference | Chanakya Ekbote, Artidoro Pagnoni, Devendra Singh Sachan +5 | cs.LG | 2026-10-29 |
| #20 | Textual Response-Aware Guidance for Zero-Shot Adversarial Robustness of Vision-Language Models | Yubo Cui, Xianchao Guan, Zheng Zhang | cs.CV | 2026-10-29 |
| #21 | Latent Prediction Yields Cross-Subject Alignable Representations in Sensory-Evoked fMRI | Serwan Jassim, Victoria Bosch, Daniel Anthes +2 | cs.LG | 2026-10-29 |
| #22 | TaskFrame: Connecting Task-Level Planning with Frame-Level Control for Game Agents | Guangzhi Wang, Junfu Pu, Yiran Wang +10 | cs.CV | 2026-10-29 |
| #23 | Bridging Semantics and Structure: A Theoretically Grounded Framework for Link Prediction on TAGs | Chen Shao, Ruirui Wang, Tobias Kafer +1 | cs.AI | 2026-10-29 |
| #24 | Fisher Contrastive Learning to Mitigate Feature Suppression: A Case Study in Acute Promyelocytic Leukemia Diagnosis | Shushan Wu, Yongkai Chen, Xilin Gong +3 | stat.ML | 2026-10-29 |
| #25 | NeurEO: dissecting Earth observation embeddings with computational neuroscience | Thijs L van der Plas, Jacob JW Bakermans, Ioannis N Athanasiadis | cs.CV | 2026-10-29 |
| #26 | SynthFaces: Balanced Large Scale Human Dataset | Sergey Karpukhin, Denis Bobkov, Kirill Morozov +1 | cs.CV | 2026-10-29 |
| #27 | M-PFT: Angular Margin for Calibrated Prompt-Tuning of Fine-Tuned Vision-Language Models | Shihab Aaqil Ahamed, Mohamed Ansaff, Nang Khin Myat Lay Phyu +4 | cs.CV | 2026-10-29 |
| #28 | Event-SAMA: Language-Grounded Video Object Segmentation on Neuromorphic Event Streams | Sergei Fedorchenko, Max Zehnder, Nikola Zubić +2 | cs.LG | 2026-10-29 |
| #29 | Emergence of the transformer architecture as the score of entropic laws of random measures | Giacomo Greco | cs.AI | 2026-10-29 |
| #30 | DOSE: Dominance-Guided Ordinal Severity Estimation from Sparse Relative Annotations | Tushir Sahu, Hideaki Hayashi, Hajime Nagahara | cs.CV | 2026-10-29 |
| #31 | Trajeform: Embedding Crowd Data | Marilena Lemonari, Panayiotis Charalambous, Yiorgos Chrysanthou | cs.GR | 2026-10-29 |
| #32 | Non-Zero Radius: The Missing Component of Neural Networks | Tiansi Dong, Mateja Jamnik, Pietro Liò | cs.AI | 2026-10-29 |
| #33 | Lost in the Latent Space: How Code Embeddings Represent Functional Intent and Implementation Fidelity | Lu Sun, Yuheng Huang, Lei Ma +1 | cs.SE | 2026-10-29 |
| #34 | Integrated Feature Selection for classification and Representation Learning with Group-Lasso Siamese Networks | Nisargo Ranjan Pal, Pradeep Singh | cs.AI | 2026-10-29 |
| #35 | FDSML: Formula-Driven Supervised Metric Learning with Parameter-Aware Triplet Loss | Hina Otake, Shinei Arakawa, Keitaro Tanaka +3 | cs.CV | 2026-10-29 |
| #36 | Robustness of Chatbot LLM Judgments of Presidential Actions and Hypothetical Reforms | Oleg Vasilyev | cs.CL | 2026-10-29 |
| #37 | Proving and Improving the Platonic Representation Hypothesis with JEPAs | Randall Balestriero, Yann LeCun | cs.AI | 2026-10-29 |
| #38 | Unlocking Any-Order Generation in Pretrained Autoregressive Image Models | Rishav Pramanik, Marco Pedersoli, Zhaozheng Yin | cs.CV | 2026-10-29 |
| #39 | Where Position Matters: Profiling-Guided Layer-Wise RoPE Allocation in Transformers | Zhiwei Liu, Boao Kong, Bing Liu | cs.LG | 2026-10-29 |
| #40 | PRISM: Personalized Item Representations in User History | Renzhi Wu, Zikun Cui, Junjie Yang +6 | cs.IR | 2026-10-29 |
| #41 | From Local Recovery to Unified Generation: Discovering Triple Set in Knowledge Graphs via Observation-Anchored Latent Diffusion | Jiaqi Wang, Yisen Gao, Huayang Shi +7 | cs.LG | 2026-10-29 |
| #42 | PALATE: Pretrained Autoregressive LATent Embeddings | Sizhang Zhao, Praveen Gondhi, Bin Li +1 | cs.IR | 2026-10-29 |
| #43 | HEARSAYBENCH: Can AI Navigate from Abstract Human Rights to Lived Lives? | Ava Iranmanesh, Sobhan Lotfi, Ali Iranmanesh +1 | cs.CL | 2026-10-28 |
| #44 | FairSplit: Decomposing the Embedding Space for Fair Classification | Andrii Shkabrii, Anna Beer, Ylli Sadikaj +1 | cs.LG | 2026-10-28 |
| #45 | Optimization-based lane-changing trajectory planning in mixed traffic with embedded input convex neural networks | Yuanxiang Yang, Yu Liu, Fabricio Oliveira +2 | math.OC | 2026-10-28 |
| #46 | Contextual Embeddings Beyond the Gold Chunk | Sedigheh Eslami, Markus Krimmel, William Barber +7 | cs.LG | 2026-10-28 |
| #47 | What to randomize matters: a controlled study of volume, axis and representation in low-data molecular generation | Neerav Kaushal, Alisa Teige, Ajay MNV Penmatsa | cs.LG | 2026-10-28 |
| #48 | Learning Scientific Trajectories to Predict Future Biomedical Discoveries | Chia-Hsuan Chang, Brian Ondov, Jiang Lv +7 | cs.CL | 2026-10-28 |
| #49 | Geometry Matters in Packed 3D Attention | Amil Khan, Anantajit Subrahmanya, B. S. Manjunath | cs.CV | 2026-10-28 |
| #50 | Detecting Fine-Grained Differences between Image Datasets | Leander Girrbach, Alexander von Recum, Kirill Bykov +1 | cs.CV | 2026-10-28 |