Press ESC to close Press ⌘K or Ctrl+K to open

用行动赢得尊重

Alan Hou

Notes on coding, AI, and technology.

记录编程、人工智能与技术探索。

Recent Posts / 近期文章

View all posts

Policy Optimization With Multiple Verifiers via Pareto Rankings

多重验证器下的策略优化:基于帕累托偏序排名的无标量化强化学习

What to Practice Next? Latent Profile-Guided Task Selection for Skill-Evolving LLM Agents

接下来练什么?基于潜在能力图谱的自演化智能体任务选择

Recovered or Memorized? Investigating Dynamical Consistency and Faithfulness in World Model Latents

真学到了物理规律还是单纯死记硬背?世界模型潜空间的动力学一致性与保真度检验

Logically Consistent Accurate Forecasts: Reconciling Beliefs via Reasoning Chains

逻辑自洽的精准预测:借助推理链调和多智能体信念悖论

See Every Block Once: Variance-Reduced Post-Training for Masked Diffusion Language Models

每个块只看一次:掩码扩散语言模型的低方差强化学习后训练

Classical Energies Learn to Reason 1,000x Faster than Looped Models

经典能量模型推理学习速度超越循环模型千倍:重构 AI 逻辑推理范式

Two Mathematical Models of Knowledge Distillation: Why Teachers Accelerate Optimization Without Changing Generalization

知识蒸馏的双重数学模型:为什么教师模型加速优化却不改变泛化上限

Back to Pixels: Lifting Latent Video Diffusion into Pixel Space

重返像素空间:摆脱 3D VAE 桎梏的原生像素级视频扩散模型 PixVid

Unbundling Multimodal Vision Encoding: Why Pretrained Priors Are Optional but Dedicated In-Fusion Capacity Is Key

解构多模态视觉编码:为什么预训练先验可有可无,而早期融合内专用算力才是关键

Series / 系列文章