AI·Nubia is set to launch the second-generation 'Doubao Phone' at WAIC 2026 as a mass-market flagship with improved AI agent OS, memory, and execution capabilities.
Search
What are you looking for?
12 results for “memory”
AI·XALPHA is a memory-driven AI quant researcher that uses multi-source research memory integrating external financial reports and prior discovery feedback, with Macro Brain for theme planning and archetype selection, Micro Brain for hypothesis-to-code translation and tri-alignment verification, and Cross Brain for feedback consolidation, enabling closed-loop continuous alpha discovery that outperforms baselines on CSI300.
AI·SQuaD-SQL uses LLM-guided synthetic data and LoRA fine-tuning to train 1.5B-parameter SLMs to reach 86.9% execution accuracy on WikiSQL, matching large models while requiring only one consumer GPU and delivering faster, lower-memory inference.
AI·A $100 setup using three NVIDIA P102 cards delivers 20 GB VRAM and 448 GB/s memory bandwidth, sufficient for three concurrent LLM users with high context and better speeds than costlier lower-VRAM cards.
AI·Holographic Neural PCFG induces latent constituency trees from raw text using holographic memory and neural rule scoring for unsupervised parsing.
AI·Structured pruning method for sparsely-activated MoE models removes bad experts to address full expert bank memory bottleneck while preserving inference efficiency.
AI·Baidu's Baidu Dazhi proactive agent sees daily queries surge 20x since launch; personal and enterprise versions upgrade with intelligent routing, multi-device memory, and browser/PPT tools.
AI·Proactive memory agent introduced to combat behavioral state decay in long-horizon agents by actively surfacing scattered decision states.
AI·Dual Latent Memory in Vision-Language-Action models for robotic manipulation interleaves historical experience fluidly in the native latent embedding space, overcoming Markovian limitations in long-horizon tasks.
AI·Sparse Delta Memory scales the hidden state of gated linear RNNs to orders of magnitude higher capacity via sparse addressing, improving long-context recall and in-context learning while keeping compute efficient.
AI·The paper compares softmax attention with recurrent linear-attention architectures including DeltaNet and Gated DeltaNet, analyzing expressivity, memory decay, training throughput, and introducing cross-layer value routing.
Embodied agents are typically built as hand-designed compositions of perception, memory, planning, and action modules. This modularity exposes a large architectural design space, but current systems still rely on researcher intuition to choose where information is stored, how observations are processed, and how model calls are connected. Agent Architecture Search (AAS) automates such design for text-domain agents, but has not been systematically evaluated on perceptual embodied agents through s…