Orbit
PulseAugur coverage of Orbit — every cluster mentioning Orbit across labs, papers, and developer communities, ranked by signal.
5 day(s) with sentiment data
-
New framework ORBIT probes complex interactions in protein fitness landscapes
Researchers have developed ORBIT, a framework designed to analyze the complex interactions within protein fitness landscapes. This method distinguishes between the presence of interactions, how well representations can …
-
New ORBIT++ benchmark challenges Structure-from-Motion methods
Researchers have introduced ORBIT++, a new benchmark designed to evaluate Structure-from-Motion (SfM) methods in challenging real-world conditions. The benchmark leverages 360-degree panoramic videos to create perspecti…
-
New research tackles training and evaluation challenges for time series foundation models
Two new research papers explore challenges in training and evaluating time series foundation models (TSFMs). The first paper introduces ORBIT, a novel training paradigm designed to control distribution properties like d…
-
New ORBIT technique enables multi-attribute control in language models
Researchers have developed ORBIT, a new training-free technique for simultaneously controlling multiple behavioral attributes in language models. Unlike previous methods that struggled with combining attributes, ORBIT u…
-
Orbit launches as an open-source AI platform with unified API
Orbit is a new open-source AI platform designed to unify access to various AI components. It provides a single API for managing files, databases, models, and tools. The platform supports both local and cloud deployments…
-
Anthropic's Claude AI enhanced with Orbit for multi-tool functionality
This article explores how to leverage Anthropic's Claude AI model to function as a comprehensive AI team. It details seven specific techniques, or "hacks," that can be implemented using Claude in conjunction with the Or…
-
Developer uses Git worktrees to enable AI agents across multiple repos
A developer describes their journey to enable AI agents to work across multiple code repositories simultaneously. Initial attempts using copy-pasting code between agent sessions or starting agents at a project root prov…
-
New ORBIT method enables multi-attribute steering in language models
Researchers have developed ORBIT, a novel training-free method for simultaneously steering multiple behavioral attributes in language models. Unlike previous methods that struggle with combining attributes or require re…
-
New LLM routing methods tackle cost, security, and evaluation · 4 sources tracked
Researchers are developing new methods to optimize Large Language Model (LLM) routing, aiming to balance inference costs with user satisfaction and Service Level Agreements (SLAs). SLARouter, an online algorithm, learns…
-
Eight LLMs Reanalyze RNA-Seq Data, Six Replicate Findings
Researchers used eight advanced large language models to reanalyze an RNA-sequencing dataset for Candida auris, aiming to reproduce a prior study. Six of the models successfully replicated the original finding regarding…
-
GitLab's Orbit knowledge graph tackles AI token waste
GitLab has introduced "Orbit," a knowledge graph that structures code repositories to provide agents with precise context, addressing the issue of high token costs associated with large language models. This approach, v…
-
Sphere AI Lab open-sources Orbit for single-node trillion-parameter model training
Sphere AI Lab has released Orbit, an open-source framework designed for the post-training of large language models. This framework allows for the fine-tuning of trillion-parameter models, such as DeepSeek-V4, to be cond…
-
Orbit SDK auto-routes AI queries to optimal models
Orbit has released an NPM SDK designed to streamline AI query routing for developers. This tool automatically directs requests to the most suitable AI model, eliminating the need for manual selection. The SDK aims to si…
-
New ORBIT method optimizes dynamic pricing with theoretical guarantees
Researchers have developed a new method called ORBIT for contextual dynamic pricing within a semiparametric valuation model. This approach leverages the smoothness properties of an "oracle price map" to learn local poly…
-
New ORBIT method prevents LLM catastrophic forgetting during fine-tuning
Researchers have introduced ORBIT, a new method designed to prevent large language models from losing their foundational language capabilities during task-specific fine-tuning. This issue, known as catastrophic forgetti…