| LLM Unlearning Should Be Form-Independent | Jun 9, 2025 | FormLarge Language Model | —Unverified | 0 |
| JavelinGuard: Low-Cost Transformer Architectures for LLM Security | Jun 9, 2025 | CPULarge Language Model | —Unverified | 0 |
| G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems | Jun 9, 2025 | Large Language Model | CodeCode Available | 3 |
| Event-Priori-Based Vision-Language Model for Efficient Visual Understanding | Jun 9, 2025 | Event-based visionLanguage Modeling | —Unverified | 0 |
| SpatialLM: Training Large Language Models for Structured Indoor Modeling | Jun 9, 2025 | 3D Object DetectionLanguage Modeling | —Unverified | 0 |
| Decoupling the Image Perception and Multimodal Reasoning for Reasoning Segmentation with Digital Twin Representations | Jun 9, 2025 | Large Language ModelMultimodal Reasoning | —Unverified | 0 |
| How Benchmark Prediction from Fewer Data Misses the Mark | Jun 9, 2025 | Large Language ModelPrediction | CodeCode Available | 0 |
| Language-Grounded Hierarchical Planning and Execution with Multi-Robot 3D Scene Graphs | Jun 9, 2025 | Language ModelingLanguage Modelling | —Unverified | 0 |
| DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO | Jun 9, 2025 | Data AugmentationLarge Language Model | —Unverified | 0 |
| Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions | Jun 9, 2025 | Large Language ModelReinforcement Learning (RL) | CodeCode Available | 2 |
