Jayaditya Sethi
1 followers · 4 following · 843 views
on the atlas · 16
- Effective harnesses for long-running agents \ Anthropic5 savers
- Curius / Onboarding2704 savers
- How Core Web Vitals affect application SEO: Understanding Google page experience ranking and Lighthouse scores - Vercel1 savers
- Raising the bar on SWE-bench Verified with Claude 3.5 Sonnet \ Anthropic2 savers
- Building effective agents \ Anthropic9 savers
- Gmail115 savers
- I’m Lovin’ It: Exploiting McDonald’s APIs to hijack deliveries and order food for a penny1 savers
- Unified Checkout: Streamlining Uber’s Payment Ecosystem | Uber Blog1 savers
- Curius / Bookmarks for the extremely curious190 savers
- Engineering Interviews — A Hiring Manager's Guide to Standing Out1 savers
- Search Jobs | Microsoft Careers1 savers
- trench - Google Search1 savers
- The Egg8 savers
- An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion4 savers
- [2401.05335] InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenes1 savers
- InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenes1 savers
highlights · 5
it's crucial for the agents to gain “ground truth” from the environment at each step (such as tool call results or code execution) to assess its progress.
Building effective agents \ AnthropicAgents, on the other hand, are systems where LLMs dynamically direct their own processes and tool usage, maintaining control over how they accomplish tasks.
Building effective agents \ AnthropicIn our work, we find new embeddings that represent specific, user-provided visual concepts. These embeddings are then linked to new pseudo-words, which can be incorporated into new sentences like any other word. In a sense, we are performing inversion into the text-embedding space of the frozen model. We're calling the process 'Textual Inversion'.
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversionsingle-view object reconstruction method
[2401.05335] InseRF: Text-Driven Generative Object Insertion in Neural 3D ScenesThis 2D edit is then warped to a 3D model of the object and placed into the scene.
InseRF: Text-Driven Generative Object Insertion in Neural 3D Scenes