Records found: 3
NVIDIA researchers developed Dynamic Memory Sparsification (DMS), a novel method that compresses KV caches by 8× in Transformer-based LLMs, improving inference efficiency while maintaining accuracy.
Microsoft launched the Phi-4-Reasoning family, a set of 14B parameter open-weight models optimized for complex reasoning tasks. These models demonstrate competitive performance on math, planning, and coding challenges with transparent training and open access.
Google DeepMind introduces QuestBench, a benchmark designed to evaluate how well large language models identify missing information in complex reasoning tasks and generate necessary clarifying questions.