Deep Learning Weekly
Subscribe
Sign in
Home
Archive
About
Latest
Top
Discussions
Deep Learning Weekly: Issue 427
Introducing Claude Haiku 4.5, The State of Open Models, a paper on TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments, and…
Oct 22
•
Miko Planas
16
Deep Learning Weekly: Issue 426
Introducing Gemini Enterprise, A small number of samples can poison LLMs of any size, a paper on Self-Adapting Language Models, and many more!
Oct 15
•
Miko Planas
21
1
Deep Learning Weekly: Issue 425
RTEB: A New Standard for Retrieval Evaluation, Building Multi-Agent Systems with Crew AI and Weaviate, a paper on MCPMark: A Benchmark for…
Oct 9
•
Miko Planas
18
Deep Learning Weekly: Issue 424
OpenAI's Sora 2, Developing an open standard for agentic commerce, a paper on Enter the Mind Palace: Reasoning and Planning for Long-term Active…
Oct 1
•
Miko Planas
25
1
September 2025
Deep Learning Weekly: Issue 423
DeepSeek-V3.1-Terminus, Introduction to LLM-as-a-Judge For Evals, a paper on LIMI: Less is More for Agency, and many more!
Sep 24
•
Miko Planas
16
Deep Learning Weekly: Issue 422
The Ultimate Guide to LLM Evaluation: Metrics, Methods & Best Practices, How to Train an LLM-RecSys Hybrid for Steerable Recs with Semantic IDs, a paper…
Sep 18
•
Miko Planas
15
Deep Learning Weekly: Issue 421
Claude can now create and use files, Measuring Thinking Efficiency in Reasoning Models, a paper on Parallel-R1: Towards Parallel Thinking via…
Sep 10
•
Miko Planas
24
Deep Learning Weekly: Issue 420
Tencent's Hunyuan-MT translation models, Le Chat. Custom MCP connectors. Memories, a paper on USO: Unified Style and Subject-Driven Generation via…
Sep 3
•
Miko Planas
24
August 2025
Deep Learning Weekly: Issue 419
Anthropic launches Claude for Chrome in limited beta, How a 20-Year-Old Algorithm Can Help Us Understand Transformer Embeddings, a paper on: Fine-tuning…
Aug 28
•
Miko Planas
21
Deep Learning Weekly: Issue 418
Gemma 3 270M, Best Practices for Building Agentic AI Systems: What Actually Works in Production, a paper on GEPA: Reflective Prompt Evolution Can…
Aug 20
•
Miko Planas
19
Deep Learning Weekly: Issue 417
How to Build Reliable AI Agent Architecture for Production, How Much Power Will Frontier AI Training Demand in 2030, a paper on TextQuests: How Good are…
Aug 13
•
Miko Planas
32
2
Deep Learning Weekly: Issue 416
OpenAI's gpt-oss, Pretraining: Breaking Down the Modern LLM Training Pipeline, a paper on Routine: A Structural Planning Framework for LLM Agent System…
Aug 6
•
Miko Planas
25
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
