spear
PulseAugur coverage of spear — every cluster mentioning spear across labs, papers, and developer communities, ranked by signal.
- 2026-05-08 research_milestone Publication of a new algorithm for federated LLM fine-tuning. source
2 day(s) with sentiment data
-
New SPEAR framework enhances AI explainability in materials science
Researchers have developed a new framework called SPEAR (Structure Property Explainability with Attention Regularization) to improve the interpretability of machine learning models used in materials science. This framew…
-
SPEAR framework enhances e-commerce search with adaptive rewriting and retrieval
Researchers have developed SPEAR, a novel framework for community search that enhances query reformulation and retrieval effectiveness. SPEAR addresses the misalignment in current systems by integrating three components…
-
Qunhe Technology's Physical AI Research Accepted to ECCV 2026, Partners with NVIDIA on Simulation Platform
Qunhe Technology has had three papers accepted to ECCV 2026, focusing on physical AI. These papers cover spatial perception, reinforcement learning data generation, and high-fidelity physical simulation, addressing key …
-
New simulators and frameworks advance embodied AI research and deployment
Researchers are developing advanced simulators and frameworks to enhance embodied AI research and deployment. SPEAR, a Python library, offers high-speed, photorealistic rendering and extensive programmability for Unreal…
-
New methods boost LLM efficiency with advanced 2-bit and adaptive quantization
Researchers have developed new techniques to improve the efficiency of large language models (LLMs) through advanced quantization methods. One approach, SPEAR, focuses on adaptive recovery after quantization, reducing t…
-
New self-play methods refine LLMs without human data
Two new research papers introduce novel self-play algorithms for fine-tuning large language models without human supervision. The first, TPAW, uses a team-based approach where models compete and collaborate with histori…