Phi-3.5
PulseAugur coverage of Phi-3.5 — every cluster mentioning Phi-3.5 across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New LLM unlearning methods tackle robustness and utility preservation · 5 sources tracked
Researchers are developing advanced techniques for Large Language Model (LLM) unlearning, focusing on methods that are robust against relearning attacks and preserve model utility. New approaches like BLADE and Margin C…
-
AI Model Robustness Analysis Reveals Layer Dissociation
A new research paper analyzes the perturbation robustness of language models, revealing that sensitivity, causality, and repair capacity do not align across model layers. The study found two distinct propagation regimes…
-
New research tackles LLM jailbreaks with advanced detection and defense strategies · 7 sources tracked
Researchers are developing advanced methods to detect and prevent jailbreak attacks against large language and vision-language models. New techniques like SALLIE offer generation-free, cross-modal detection by analyzing…
-
New PRISM method detects physical dangers in LLM actions beyond text safety
Researchers have developed a new method called PRISM to detect physical dangers posed by large language models (LLMs) when they are used to control embodied agents. Unlike traditional text-based safety checks, PRISM ana…
-
iOS app GenBench enables on-device GGUF model benchmarking
A new free iOS application called GenBench has been released, allowing users to download, run, and benchmark GGUF models directly on their iPhones and iPads. The app utilizes llama.cpp and Metal for offline operation an…
-
KV cache eviction protection proves more vital than scoring
Researchers have developed a new method for managing KV cache eviction in large language models, finding that structural protection is more critical than scoring algorithms. Their study on transformer models revealed th…