#PaperADay 12
2019: Learning Latent Dynamics for Planning from Pixels (PlaNet) https://
arxiv.org/pdf/1811.04551 This was the forerunner to the Dreamer 1/2/3/4 series of RL agents / papers, which I am going to read in sequence. Planning is common in tasks with fully specified transition
MACHINE LEARNING
-
PlaNet: Learning Latent Dynamics for Planning from Pixels
By
–
-
Kimi K2.5 tops LM Arena open models, top 7 coding
By
–
Kimi K2.5 captures a top spot on LM Arena among open models and lands in top 7 in coding category. Top 15 overall
-
Data Efficiency Research for RLVR Accepted to MLSys 2026
By
–
Exciting work from our team, studying data efficiency for RLVR. These kinds of insights inform our dataset creation work for foundation model labs. Kudos to @realjustinbauer @pham_derek for this paper's acceptance to #MLSys 2026!
-
3D World Models: The Key to Truly Intelligent Robots
By
–
What's the single biggest roadblock to creating truly intelligent robots? A new survey tackles this. They argue that moving beyond simple point clouds to dense, AI-powered 3D "world models" is key. These neural scene representations, like NeRF and 3D Gaussian Splatting,
-
RAG as a Modular Stack: Building Scalable Enterprise AI Systems
By
–
RAG isn’t a tool.
It’s a stack. LLMs
Frameworks
Vector DBs
Embeddings
Extraction
Evaluation Winning teams design modular RAG systems — not single-vendor pipelines. This is how enterprise AI actually scales. -
Multi-Agent Communication Architecture: Design Decisions for AI Systems
By
–
How should AI agents talk to each other? There's no one-size-fits-all answer. As we deploy multi-agent systems in robotics, autonomous vehicles, and distributed AI, choosing the right communication architecture becomes a first-order design decision. The problem: Multi-agent RL
-
Free MLops Repository with Talks Books and Papers
By
–
This repository on ML operations has free talks, books, papers and more: https://
bit.ly/MLops Developed by @visenger -
SP3F: Improving LLM Reasoning in Lower-Resource Languages
By
–
We introduce SP3F: an algorithm to improve LLM reasoning in lower-resource languages (e.g., Indonesian, Bengali, and Swahili), no manual data collection needed! SP3F produces models that out-perform fully post-trained models across multiple tasks and languages🧵 [1/N]
-
LobeHub: multi-model, direct API, agent marketplace, 70k GitHub stars
By
–
Claude Cowork: $200/month. One model. macOS only.
Manus: VM-based browsing. Slow. Unstable. Expensive. LobeHub:
→ Multi-model support (switch freely)
→ Direct API access (faster, more accurate)
→ Agent marketplace to discover and remix
→ 70k GitHub stars foundation More