Q3R: Quadratic Reweighted Rank Regularizer for Effective Low-Rank Training
"训练策略" 相关文章
Rethinking the Text-Vision Reasoning Imbalance in MLLMs through the Lens of Training Recipes
MALT: Improving Reasoning with Multi-Agent LLM Training
A Practitioner's Guide to Multi-turn Agentic Reinforcement Learning
Memory Determines Learning Direction: A Theory of Gradient-Based Optimization in State Space Models
Training Vision-Language Process Reward Models for Test-Time Scaling in Multimodal Reasoning: Key Insights and Lessons Learned
SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation
小红书dots.llm1：重新定义MoE效率边界，14B激活参数挑战72B密集模型极限
Does Prior Data Matter? Exploring Joint Training in the Context of Few-Shot Class-Incremental Learning
Dual Information Speech Language Models for Emotional Conversations
TAR-TVG: Enhancing VLMs with Timestamp Anchor-Constrained Reasoning for Temporal Video Grounding
上岸的局长们，小弟考公最近有点问题咨询
EVEv2: Improved Baselines for Encoder-Free Vision-Language Models
In-Depth and In-Breadth: Pre-training Multimodal Language Models Customized for Comprehensive Chart Understanding
Entropy Loss: An Interpretability Amplifier of 3D Object Detection Network for Intelligent Driving
Sub-Scaling Laws: On the Role of Data Density and Training Strategies in LLMs
Learning Diffusion Models with Flexible Representation Guidance
Pre-Training LLMs on a budget: A comparison of three optimizers
M2-Reasoning: Empowering MLLMs with Unified General and Spatial Reasoning
阿里国际Ovis2系列模型开源：多模态大语言模型的新突破
