Doc2X

https://arxiv.org/pdf/2410.11163 Model Swarms: Collaborative Search to Adapt LLM EXPERTS VIA SWARM翻译

https://arxiv.org/pdf/2405.14768 WISE: Rethinking the Knowledge Memory for Lifelong Model Editing 翻译

https://arxiv.org/pdf/2410.11792 OKAMI: Teaching Humanoid Robots Manipulation Skills through Single

https://arxiv.org/pdf/2410.10819 DuoAttention: EFFICIENT LONG-CONTEXT LLM INFERENCE WITH RETRIEVAL

https://arxiv.org/pdf/2410.08593 VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grain

https://arxiv.org/pdf/2410.19456 Computational Bottlenecks of Training Small-scale Large Language M

https://arxiv.org/pdf/2410.10394 PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic M

https://arxiv.org/pdf/2410.19750 THE GEOMETRY OF CONCEPTS: Sparse Autoencoder Feature Structure

https://arxiv.org/pdf/2405.09999 Reward Centering 奖励中心化