| Serendipitous Recommendation with Multimodal LLM | Jun 9, 2025 | Recommendation SystemsWorld Knowledge | —Unverified | 0 |
| ReCogDrive: A Reinforced Cognitive Framework for End-to-End Autonomous Driving | Jun 9, 2025 | Autonomous DrivingImitation Learning | —Unverified | 0 |
| Vid2Sim: Generalizable, Video-based Reconstruction of Appearance, Geometry and Physics for Mesh-free Simulation | Jun 6, 2025 | Computational EfficiencyWorld Knowledge | —Unverified | 0 |
| Quantifying Cross-Modality Memorization in Vision-Language Models | Jun 5, 2025 | Machine UnlearningMemorization | —Unverified | 0 |
| TIIF-Bench: How Does Your T2I Model Follow Your Instructions? | Jun 2, 2025 | BenchmarkingInstruction Following | —Unverified | 0 |
| From Words to Waves: Analyzing Concept Formation in Speech and Text-Based Foundation Models | Jun 1, 2025 | World Knowledge | —Unverified | 0 |
| Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks | Jun 1, 2025 | In-Context LearningNegation | CodeCode Available | 0 |
| SC-LoRA: Balancing Efficient Fine-tuning and Knowledge Preservation via Subspace-Constrained LoRA | May 29, 2025 | Navigateparameter-efficient fine-tuning | —Unverified | 0 |
| MOVi: Training-free Text-conditioned Multi-Object Video Generation | May 29, 2025 | ObjectVideo Generation | —Unverified | 0 |
| Augment or Not? A Comparative Study of Pure and Augmented Large Language Model Recommenders | May 29, 2025 | Language ModelingLanguage Modelling | CodeCode Available | 0 |
