0
Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers
Hugging Face published a technical guide on training and fine-tuning multimodal embedding and reranker models using the Sentence Transformers library.
Top stories in Research
0
Codex is becoming a productivity tool for everyone
A new report from OpenAI examines how Codex is enhancing knowledge work productivity through automated research, data analysis, and content generation.
0
QIMMA قِمّة ⛰: A Quality-First Arabic LLM Leaderboard
Hugging Face introduced QIMMA, a new evaluation leaderboard focused on assessing the quality of Arabic large language models.
0
Uncovering repurposed medicines to fight liver fibrosis
A Stanford geneticist is leveraging Google DeepMind's Co-Scientist tool to identify existing medications that could be repurposed to treat chronic liver disease and fibrosis.
0
Multimodal Embedding & Reranker Models with Sentence Transformers
Hugging Face detailed the integration of multimodal embedding and reranker models within the Sentence Transformers library.
0
Modeling an AI jobs transition
OpenAI has developed a framework analyzing over 900 occupations to assess how artificial intelligence will impact, automate, or reorganize U.S. jobs.
0
An OpenAI model has disproved a central conjecture in discrete geometry
An OpenAI model has disproved a long-standing 80-year-old conjecture in discrete geometry related to the unit distance problem.
0
How frontier firms are pulling ahead
OpenAI has published research detailing how enterprise customers are adopting AI and scaling agentic workflows powered by Codex.
0
GPT-5.5 Instant System Card
OpenAI has published the safety and technical evaluation documentation for its newly released GPT-5.5 Instant model.
0
Waypoint-1.5: Higher-Fidelity Interactive Worlds for Everyday GPUs
Hugging Face introduced Waypoint-1.5, a framework designed to generate high-fidelity interactive virtual environments on consumer-grade GPUs.
0
Inside VAKRA: Reasoning, Tool Use, and Failure Modes of Agents
Hugging Face has published an analysis of VAKRA, examining how AI agents handle reasoning, tool integration, and common failure modes.
0
Ecom-RLVE: Adaptive Verifiable Environments for E-Commerce Conversational Agents
Researchers introduced Ecom-RLVE, a framework designed to provide adaptive and verifiable environments for training e-commerce conversational agents.
0
Adding Benchmaxxer Repellant to the Open ASR Leaderboard
Hugging Face has introduced a mechanism called Benchmaxxer Repellant to its Open ASR Leaderboard to improve evaluation integrity.
0
vLLM V0 to V1: Correctness Before Corrections in RL
The Hugging Face blog details the transition of the vLLM engine from version 0 to 1, emphasizing reinforcement learning correctness.
0
Unlocking asynchronicity in continuous batching
A new technical post on Hugging Face explores methods for enabling asynchronous operations within continuous batching systems to optimize LLM inference.
0
Where the goblins came from
OpenAI has published an analysis explaining the root causes and fixes for unusual personality quirks observed in GPT-5 outputs.
0
Shipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRL
Hugging Face has introduced a delta weight synchronization method in its TRL library to optimize the transfer of extremely large models.
0
Accelerating discovery of liver disease mechanisms
Scientist Filippo Menolascina is using Google DeepMind's Co-Scientist platform to discover novel treatments for liver disease and analyze patient-specific drug efficacy.
0
GPT-5.5 System Card
OpenAI has published the system card for GPT-5.5, detailing the safety evaluations, risks, and mitigation strategies for the new model.
← NewerPage 18