每天自动聚合 AI 领域最新动态
Autoregressive video diffusion supports streaming generation and interactive control, but its KV cache grows continuo...
Distribution Matching Distillation (DMD) trains a few-step student from the difference between separately estimated t...
Reliable progress in offline policy learning depends on careful reporting, well-tuned baselines, and evaluation acros...
Site-specific fertilizer recommendation systems adapt nutrient advice to location, soil properties, crop type, and pr...
Low-precision execution can substantially accelerate reinforcement learning (RL) for large language models, but discr...
Long-horizon LLM agents are frequently implemented using sparse mixture-of-experts (MoE) models, yet the co-design of...
We present TimeBraid, a series of unified time-series and language models that align pretrained language models and p...
Agentic systems use large language models (LLMs) to carry out concrete tasks. Prior work often borrows abstractions s...
Full-duplex speech models are trained to converse with a person, but they are increasingly made to converse with each...
Large language model agents are accelerating scientific automation, yet verified executions rarely become persistent ...
Assistants from 2011 answered and waited, and agents from 2023 did a task and stopped. In September 2026 Meta's Muse ...
LLM-based agents are increasingly advancing scientific and engineering problem solving, with physics simulation emerg...