Leveraging the Power of Large Language Models in Entity Linking via Adaptive Routing and Targeted Reasoning
"高效计算" 相关文章
EAGER: Entropy-Aware GEneRation for Adaptive Inference-Time Scaling
Liquid AI 发布 LFM2-8B-A1B：8B 参数仅激活 1.5B
Liquid AI 发布 LFM2-8B-A1B：8B 参数仅激活 1.5B
ERGO: Efficient High-Resolution Visual Understanding for Vision-Language Models
SD3.5-Flash: Distribution-Guided Distillation of Generative Flows
Neural Networks for Learnable and Scalable Influence Estimation of Instruction Fine-Tuning Data
FragmentRetro: A Quadratic Retrosynthetic Method Based on Fragmentation Algorithms
NVFP4 Trains with Precision of 16-Bit and Speed and Efficiency of 4-Bit
CF3: Compact and Fast 3D Feature Fields
Efficient Machine Unlearning via Influence Approximation
AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning
Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention
Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications
Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics
Tokenization不存在了？Meta最新研究，无需Tokenizer的架构来了
Microsoft AI Research Introduces OLA-VLM: A Vision-Centric Approach to Optimizing Multimodal Large Language Models
Nat. Commun. | 晶体结构弛豫不确定性量化的深度生成模型
