| 1 | Reasoning Topology Matters: A Controlled Study of LLM-Based Cybersecurity Analysis | Jiling Zhou, Aisvarya Adeseye, Antti Hakkala +2 | cs.CR | 2026-09-21 |
| 2 | Morpho-VITS: Variational Inference with Morphological Modeling for End-to-End Speech Synthesis of a Tonal Bantu Language | Antoine Nzeyimana | eess.AS | 2026-09-21 |
| 3 | The Visual Target Matters: Learning across the Visual Hierarchy for Brain-to-Image Retrieval | Ye Wang, HaoKun Ren, Hong Yu +4 | cs.CV | 2026-09-21 |
| #4 | Positive Pair Geometry Matters: Optimal Transport for Contrastive Learning of Visual Representations | Akshit Nanda, Shahzad Ahmad, Ram Prasad Padhy | cs.CV | 2026-09-21 |
| #5 | Representation-guided in-context learning for medical image interpretation with multimodal large language models | Minda Zhao, Fangyu Hu, Yan Luo +8 | cs.AI | 2026-09-21 |
| #6 | Rethinking Diffusion Segmentation: When Does It Rely on Its Noisy State, and Does Diffusion Matter? | Hengzhuo Yang, Yuming Zeng, Yuling Yang | cs.CV | 2026-09-21 |
| #7 | From Tables to Quantified Statements: Evaluating LLM Inference Generation through Executable Verification | Mai Mohamed Eida, Gunjan Anand, Ayush Singh +1 | cs.CL | 2026-09-21 |
| #8 | Which Terrain Is Better? Preference Learning with VLM Prototypes for Off-Road Traversability Ranking | Ji-Hoon Hwang, Jisung Bae, E-In Son +3 | cs.CV | 2026-09-20 |
| #9 | Reassessing Global Gradient-Norm Imbalance in BLIP Fine-Tuning Across Physical Domains | Kiran Naseer, Samreen Azhar, Dwarikanath Mahapatra | cs.CV | 2026-09-20 |
| #10 | Robot World Models Are Not Invariant to How the Actions Are Written | Ahmed Karim, Leon Chlon | cs.RO | 2026-09-19 |
| #11 | Auditing Political Alignment in LLM Assistants: Engagement, Stance, and User Identity | Joan C. Timoneda | cs.CL | 2026-09-19 |
| #12 | Intervention Granularity Matters: Coherent Treatment Bundles in Counterfactual Simulation with Clinical World Models | Fangzhou Wang, Yixuan Yang, Camilla Balzarotti +1 | cs.LG | 2026-09-18 |
| #13 | Beyond Gaussian Worlds: Latent Geometry Matters for JEPAs | Léo Nicollier, Enric Meinhardt-Llopis, Marc Pic +2 | cs.LG | 2026-09-18 |
| #14 | TetrisCNN for interpretable detection of phases of matter from experimental quantum simulator data | Kacper Cybiński, Björn van Zwol, James Enouen +5 | quant-ph | 2026-09-17 |
| #15 | How Do Agent Harnesses Create Value? Planning Information and Release Control in Stateful LLM Agents | Yukun Zhang, Kemu Xu, Yishen Chen | cs.AI | 2026-09-17 |
| #16 | Generating Heterogeneous 3D Geological Microstructures from 2D Images via a Stable Diffusion-Adversarial Model | Ali Aouf, Eric Laloy, Bart Rogiers +1 | cs.AI | 2026-09-17 |
| #17 | AdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair | Z. C. Luo, J. C. Guo, W. J. He +10 | cs.SE | 2026-09-17 |
| #18 | Physical knowledge on historical data matters more than enforcing physical constraints on the forecast | Etienne Lehembre, Pascal Audigane, Vincent Nguyen +2 | cs.AI | 2026-09-17 |
| #19 | Steering Equilibrium Selection in Regularized Self-Play via the Reference Policy | Luis Leal | cs.AI | 2026-09-17 |
| #20 | DeliveryGym: An RL Environment for Long-Horizon Embodied Agent Planning with Adaptive Curriculum | Haoqiang Kang, Yiming Zhang, Yiyang Guo +5 | cs.LG | 2026-09-17 |
| #21 | Flag Game: A Toy Model for Mechanistic Swarm Interpretability | Elizabeth Pavlova, Hidenori Tanaka | cs.AI | 2026-09-16 |
| #22 | Reporting Practice Matters: The Impact of Reference Choice on Chest X-ray Report Evaluation | Daniel P. Jeong, Charles Q. Li, Hossein Hosseiny +5 | cs.CL | 2026-09-16 |
| #23 | Long-Lived Characters, Local Inference: Incremental Memory Maintenance for Game NPCs | Zimu Xu | cs.CL | 2026-09-16 |
| #24 | The evolution of sex for artificial intelligence: a population-genetic framework for multigenerational model populations | Giorgio F. Gilestro | cs.LG | 2026-09-16 |
| #25 | Size Matters: Foundation Model for Czech HTML documents | Martin Dvořák, Vít Tlustoš, Artyom Voronin +4 | cs.CL | 2026-09-16 |
| #26 | First Token Matters: Understanding Safety Collapse in Large Reasoning Models | Yizheng Yang, Haining Yu, Yuechen Wang +4 | cs.AI | 2026-09-16 |
| #27 | Reaching Every Position Without Searching: Rotating Sparse Wiring on the Hypercube as a Substitute for Attention | Yoshiaki Takashita | cs.LG | 2026-09-16 |
| #28 | Anchoring What Matters: A Dual-Level Learning Framework for Visually-Grounded Multimodal Reasoning | Xinxin Song, Siyuan Li, Tingxiong Xiao +1 | cs.AI | 2026-09-16 |
| #29 | IRIS: Implicit Rendering Matters for Pose-Free Novel View Synthesis | Wenyu Li, Sidun Liu, Peng Qiao +2 | cs.CV | 2026-09-16 |
| #30 | A Calibrated Instrument for Measuring How Inference Optimizations Affect Output Quality | Jerry Kaplan | cs.CL | 2026-09-16 |
| #31 | When to Call an LLM: A Confidence-Gated Hybrid for Cost-Effective Emotion Recognition in Conversational AI | Sai Babu Udayagiri, Arjun Chouhan, Ravisekhar Kanagala +1 | cs.AI | 2026-09-16 |
| #32 | Who Judges Matters: Measuring Family-Conditioned Preference in LLM-as-Judge Panels | David Ababio Awuni, Luke E. K. Achenie, Benjamin Tei Partey +2 | cs.CL | 2026-09-15 |
| #33 | Beyond Performance Metrics: Uncertainty Mapping of Label Ambiguity in Fazekas Score Prediction | Susanne Schmid, Johanna Ospel, Richard Frayne +1 | cs.CV | 2026-09-15 |
| #34 | Exploring 2D backbone effects for indoor semantic occupancy prediction | Shizhang Fanga, Wanling Yea, Qi Zheng | cs.CV | 2026-09-15 |
| #35 | Easy to Catch a Liar, Hard to Clear an Honest One: Language Models Diagnosing a Corrupted Reward Channel from a Verified Record | Arman Nik Khah | cs.LG | 2026-09-15 |
| #36 | Nameless Tokenization: A Lossless Tokenizer-Level Defense Against Control-Token Forgery in Open-Weight LLMs | Kisu Yang, Yoonna Jang, Heuiseok Lim | cs.CL | 2026-09-15 |
| #37 | When Confidence Signals Disagree: Local and Global Confidence in Autoregressive Language Models | Julio C. Amador Diaz Lopez | cs.LG | 2026-09-15 |
| #38 | MAETrack: Unleashing the Potential of Pretrained Geometric Priors for 3D Single Object Tracking | Sifan Zhou, Qiwei Wang, Linyue Tan +3 | cs.CV | 2026-09-15 |
| #39 | Decoder Design Matters for ECG Delineation | Joseph Scharpf, William Han, Chaojing Duan +3 | cs.LG | 2026-09-15 |
| #40 | Mini-batch Sampling Strategies for Long-Tailed Image Classification: An Empirical Study on CIFAR-100-LT | Siyu Yuan | stat.ML | 2026-09-14 |
| #41 | Racing in Volume with Flow Ensembles | Saswat Subhajyoti Mallick, Riu Cherdchusakulchai, Marc Ruiz Olle +4 | cs.CV | 2026-09-14 |
| #42 | Calibrate, Then Route: A Measured Study of Learned Request Routing for Disaggregated LLM Serving | Srikanta Datta Tumkur, Jay Iyer, Mehar Simhadri +3 | cs.AI | 2026-09-14 |
| #43 | Sharp Rates and a One-Line Correction for Spectral Representation Learning | Dier Tang, Jing Yee Tan, Guangyue Han | cs.LG | 2026-09-14 |
| #44 | Reason What Matters: Retrieval-Grounded Reasoning for Universal Multimodal Embeddings | Mingzhou Jiang, Peixi Wu, Hang Cheng +7 | cs.AI | 2026-09-14 |
| #45 | Is INT8 Portable? A Cross-Platform Measurement Study of Quantized Inference on Embedded and Automotive Accelerators | Yuyeong Shin | cs.AR | 2026-09-14 |
| #46 | Can We Triage LLM Translation Errors in Classical Texts Without Human References? Source Novelty, GEMBA Scoring, and Budgeted Review through Pali-to-English Translation | Máté Metzger | cs.CL | 2026-09-14 |
| #47 | Decision-Oriented Uncertainty Quantification for Risk Control in Earth System Spatiotemporal Foundation Models | Ji Lu, Huiran Duan, Bo Zhao +5 | cs.LG | 2026-09-13 |
| #48 | Toward a Layer-2 Trigger for AI/ML Lifecycle Management in 6G | Dharmendra Kumar | cs.NI | 2026-09-13 |
| #49 | Question's Gambit: The First Move Matters in Agentic Deep Search | Radin Hamidi Rad, Amin Bigdeli, Negar Arabzadeh +4 | cs.AI | 2026-09-13 |
| #50 | Physically Typed and Geometry-Aware Representations for Earth Foundation Models | Rajiv Ranjan | cs.CV | 2026-09-12 |