Researchers introduced LinearKV, a training-free framework enabling position-independent caching (PIC) for hybrid large language models (LLMs) that combine linear recurrences with full attention. The …
Moonshot released Kimi K3, a 2-trillion-parameter model with a 1-million-token context window, in July 2026, using its linear-attention variant Kimi Delta Attention (KDA). The model trails only Claude…
A new benchmark suite called JAXBench, comprising 50 JAX workloads for AI-generated kernel optimization on Google Cloud TPUs, shows that target-specific documentation context matters more than model s…
NVIDIA released Nemotron 3 Super, a 120-billion-parameter hybrid model that scores 60.47% on SWE-Bench Verified, beating GPT-OSS-120B by nearly 20 points while delivering 2.2 times the inference throu…
NVIDIA released Nemotron-Labs-TwoTower, an open-weight diffusion language model that separates token representation and denoising into two towers, achieving 2.42× higher generation throughput while re…
Researchers introduced NarrativeWorldBench, a benchmark for long-horizon co-creative audio drama, and N-VSSM, a latent world model that outperforms frontier LLMs like Claude Opus 4.5 on long-arc consi…
Researchers introduced Gated DeltaNet-2, a linear attention model that decouples the erase and write operations in recurrent state updates using separate channel-wise gates. The model outperforms Mamb…