AI on 2 Nov 2026
Everything new on the trackers that day: official announcements, model uploads from the big labs, tool releases, papers, AI rules and outages. Each item links to its source.
On 2 Nov 2026 the Machine Notes trackers recorded 5 papers. The most upvoted paper was "Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs". The fastest-rising AI repo was wangzan101/Mika.
Papers people are reading
Research that day| Paper | Upvotes |
|---|---|
| Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMsSince visual tokens make up 89-97% of this input on the benchmarks we study, most of the decoding computation is spent repeatedly processing the same image.Donghyeon Cho, Joowon Kim, Seungho Shin and others | 109 |
| A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-ImprovementWe address these two questions separately: training dynamics determine when to acquire new experience, while the answers to new tasks remain independently checkable.Yu Liu, Youxing Li, Yuedong Tan and others | 75 |
| Proving and Improving the Platonic Representation Hypothesis with JEPAsWe turn the hypothesis into a theorem. First, we prove a Platonic Representation Theorem: Joint-Embedding Predictive Architectures (JEPAs) trained separately on any number of modalities learn the same representation up to one rotation whenever their positive pairs are two…Randall Balestriero, Yann LeCun | 66 |
| L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian MemoryIn this paper, we introduce a Latent 3D Gaussian Memory (L3G) that combines the efficiency of feed-forward reconstruction with a compact, rapidly renderable scene representation.Jinhyeok Choi, JoungBin Lee, Jongmin Lee and others | 44 |
| R^2Orch: Recursive Self-Improvement for Agent Orchestration via Self-Play within a Skill-Internalization LoopTo address these challenges, we propose R^2Orch, a new paradigm of Recursive Self-Play Orchestration: an inner loop of self-play that improves the orchestrator on self-chosen tasks, and an outer loop that improves how the inner loop improves.Mingda Zhang, Yun Huang, Qiang Huang and others | 34 |
Rising AI repos
Repos that day| Repository | Description | Stars gained |
|---|---|---|
| Mikawangzan101 | An on-device AI agent for Android that operates apps and the web to get things done for you. | +1,367 |
| TokenEconomizermicrosoft | Experience-Driven Black-Box Cost Control for Coding Agents | +863 |
| bamadaveebbelaar | BAMA: Build Any Mac App. Agent skills to research, clone, design, build, optimize, and test native macOS apps with Swift and SwiftUI. | +223 |
| awesome-reverse-engineeredalexgaoth | Don't reverse engineer it twice. 17,000+ open-source tools built by reverse engineering closed apps, APIs, devices, protocols, file formats, games and AI tools. Search site + agent skill + MCP server, refreshed nightly. | +90 |
| antirioneliasbiondo | 🕷️ The fastest open-source AI Gateway and LLM Gateway — one binary with built-in console to route, secure, budget and observe every LLM call across OpenAI, Anthropic, Gemini, Bedrock and more. | +78 |