A Survey on Memory-Efficient Large-Scale Model Training in AI for Science

Scientific research faces high costs and inefficiencies with traditional methods, but the rise of deep learning and large language models (LLMs) offers innovative solutions. This survey reviews LLM applications across scientific fields such as biology, medicine, chemistry, and meteorology, underscoring their role in advancing research. However, the continuous expansion of model size has led to significant memory demands, hindering further development and application of LLMs for science. To address this, we review memory-efficient training techniques for LLMs based on the transformer architecture, including distributed training, mixed precision training, and gradient checkpointing. Using AlphaFold 2 as an example, we demonstrate how tailored memory optimization methods can reduce storage needs while preserving prediction accuracy. We also discuss the challenges of memory optimization in practice and potential future directions, hoping to provide valuable insights for researchers and engineers.

Scattering Environment Aware Joint Multi-user Channel Estimation and Localization with Spatially Reused Pilots

The increasing number of users leads to an increase in pilot overhead, and the limited pilot resources make it challenging to support all users using orthogonal pilots. By fully capturing the inherent physical characteristics of the multi-user (MU) environment, it is possible to reduce pilot costs and improve the channel estimation performance. In reality, users nearby may share the same scatterer, while users further apart tend to have orthogonal channels. This paper proposes a two-timescale approach for joint MU uplink channel estimation and localization in MIMO-OFDM systems, which fully captures the spatial characteristics of MUs. To accurately represent the structure of the MU channel, the channel is modeled in the 3-D location domain. In the long-timescale phase, the time-space-time multiple signal classification (TST-MUSIC) algorithm initially offers a rough approximation of scatterer positions for each user, which is subsequently refined through the scatterer association algorithm based on density-based spatial clustering of applications with noise (DBSCAN) algorithm. The BS then utilizes this prior information to apply a graph-coloring-based user grouping algorithm, enabling spatial division multiplexing of pilots and reducing pilot overhead. In the short timescale phase, a low-complexity scattering environment aware location-domain turbo channel estimation (SEA-LD-TurboCE) algorithm is introduced to merge the overlapping scatterer information from MUs, facilitating high-precision joint MU channel estimation and localization under spatially reused pilots. Simulation results verify the superior channel estimation and localization performance of our proposed scheme over the baselines.

Hybrid Offline-Online Design for Reconfigurable Intelligent Surface Aided UAV Communication

This letter considers the reconfigurable intelligent surface (RIS)-aided unmanned aerial vehicle (UAV) communication systems in urban areas under the general Rician fading channel. A hybrid offline-online design is proposed to improve the system performance by leveraging both the statistical channel state information (S-CSI) and instantaneous channel state information (I-CSI). For the offline phase, we aim to maximize the expected average achievable rate based on the S-CSI by jointly optimizing the RIS's phase-shift and UAV trajectory. The formulated stochastic optimization problem is difficult to solve due to its non-convexity. To tackle this problem, we propose an efficient algorithm by leveraging the stochastic successive convex approximation (SSCA) techniques. For the online phase, the UAV adaptively adjusts the transmit beamforming and user scheduling according to the effective I-CSI. Numerical results verify that the proposed hybrid design performs better than various bechmark schemes, and also demonstrate a favorable trade-off between system performance and CSI overhead.