| Probing Outcome-Level Resemblance and Mechanism-Level Alignment in LLM Risk Decisions: Evidence from the St. Petersburg Game | Safety & alignment | Chensong Huang +5 | Jun 3, 2026 | 1 |
| Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning | Agents | Yu Xia +6 | Jun 2, 2026 | 1 |
| Measuring the Symmetry--Data Exchange Rate | Safety & alignment | Ahmed M. Adly | May 31, 2026 | 1 |
| Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain | Theory | Yuan Yao +5 | May 30, 2026 | 1 |
| SuperMemory-VQA: An Egocentric Visual Question-Answering Benchmark for Long-Horizon Memory | Speech & audio | Samiul Alam +6 | May 30, 2026 | 1 |
| Geometric Latent Reasoning Induces Shorter Generations in LLMs | Data & benchmarks | Shashi Kumar +4 | Jun 1, 2026 | 1 |
| A Formally Verified Library of Mathematical Finance in Lean 4 | Theory | Raphael Coelho | May 31, 2026 | 1 |
| Model-Based Quality Assessment for Massively Multilingual Parallel Data | Data & benchmarks | Abdelaziz M. A. Ibrahim +3 | May 29, 2026 | 1 |
| FreeForm: Reduced-Order Deformable Simulation from Particle-Based Skinning Eigenmodes | Robotics | Donglai Xiang +7 | May 28, 2026 | 1 |
| The Chain Holds, the Answer Folds: Trace-Answer Dissociation in Reasoning Models Under Adversarial Pressure | Data & benchmarks | Yubo Li +2 | May 27, 2026 | 1 |
| Same Question, Different Source, Different Answer: Auditing Source-Dependence in Medical Multi-Source RAG | Science & bio | Yubo Li +2 | May 27, 2026 | 1 |
| The Hamilton-Jacobi Theory of Deep Learning | Efficiency & systems | Jose Marie Antonio Miñoza +2 | May 27, 2026 | 1 |
| Review Arcade: On the Human Alignment and Gameability of LLM Reviews | Code | Hans Ole Hatzel +2 | May 27, 2026 | 1 |
| AI, Take the Wheel: What Drives Delegation and Trust in Human-Computer Cooperative Question Answering? | Agents | Maharshi Gor +6 | May 27, 2026 | 1 |
| Lost in Translation? Exploring the Shift in Grammatical Gender from Latin to Occitan | Speech & audio | Ahan Chatterjee +4 | May 9, 2026 | 1 |
| Memory-Bound but Not Bandwidth-Limited: The Physical AI Inference Gap in Batch-1 LLM Decode | Robotics | Josef Chen | May 28, 2026 | 1 |
| Beyond Recall: Behavioral Specification as an Interpretive Layer for AI Personalization | Agents | Aarik Gulaya | May 27, 2026 | 1 |
| Benchmarking Composed Image Retrieval for Applied Earth Observation | Vision & multimodal | Bill Psomas +8 | May 23, 2026 | 1 |
| Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly Detection | Vision & multimodal | Xiaona Zhou +4 | May 28, 2026 | 1 |
| Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning | Vision & multimodal | Chun-Hsiao Yeh +5 | May 28, 2026 | 1 |
| Reducing Political Manipulation with Consistency Training | Robotics | Long Phan +5 | May 21, 2026 | 1 |
| ORACLE: Anticipating Scams from Partial Trajectories in Streaming App Usage | Agents | Wenbo Gao +8 | May 9, 2026 | 1 |
| Got a Secret? LLM Agents Can't Keep It: Evaluating Privacy in Multi-Agent Systems | Agents | Aman Priyanshu +2 | May 26, 2026 | 1 |
| BatteryMFormer: Multi-level Learning for Battery Degradation Trajectory Forecasting | Code | Ruifeng Tan +5 | May 26, 2026 | 1 |
| Growing a Neural Network in Breadth, Depth, and Time | Science & bio | Eivinas Butkus +2 | May 24, 2026 | 1 |
| Don't Guess, Just Ask: Resolving Ambiguity in Referring Segmentation via Multi-turn Clarification | Vision & multimodal | Yuting Yang +4 | May 24, 2026 | 1 |