A new attention mechanism condenses context directly inside DeepSeek-style latent space, cutting KV cache by 90% and speeding prefill 2.5x at 128K tokens.
New research finds humans regulate bias through structurally distinct memory layers, while Mistral and Llama3 collapse those layers into overlapping associations.
A new multi-agent framework tackles long-horizon story simulation by treating LLM hallucinations as narrative fuel and giving agents a mutable, evolving social memory.
DDTree turns one block diffusion drafter pass into an optimal draft tree, lifting DFlash speedups from around 5x to over 7x across every tested benchmark.
A new benchmark exposes how eight frontier LLMs treat India as culturally uniform, defaulting to Central and North Indian practices when generating cultural answers.
A KU Leuven team audits the field's most-cited semantic change benchmark and finds OCR noise, mislabeled targets, and error bars so wide they swallow rankings.
A YAML-based specification language decouples agent workflows from Python code, adding explicit control flow, sandboxed execution, and a visual editor.
A new self-supervised pipeline combines Segment Anything Model, Depth Anything V2, and topographic priors to segment sinkholes from RGB imagery without manual labels.
A new anomaly detection framework uses low-dimensional subspaces to mimic unseen features, hitting state-of-the-art scores on three industrial defect benchmarks.
A new transformer-based world model ditches VAE codebooks and bird's-eye-view grids, forecasting future 3D driving scenes directly from camera images with 18.7% higher mIoU.