Deep Learning
StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving Chang Gao
It employs four LLM-based agents: strategy generator, executor, optimizer, and evaluator, working together to generate, evaluate, and select promising strategies for a given task. Experimental results demonstrate that StrategyLLM outperforms the competitive baseline CoT -SC that requires human-annotated solutions on 13 datasets across 4 challenging tasks without human involvement, including math reasoning (34.2%
KD-Zero: Evolving Knowledge Distiller for Any Teacher-Student Pairs
Knowledge distillation (KD) has emerged as an effective technique for compressing models that can enhance the lightweight model. Conventional KD methods propose various designs to allow student model to imitate the teacher better.
Convolutions and More as Einsum: AT ensor Network Perspective with Advances for Second-Order Methods
Our TN implementation accelerates a recently-proposed KFAC variant up to 4.5 x while removing the
ANPL: Towards Natural Programming with Interactive Decomposition Di Huang
Though LLMs are capable of generating plausible programs, it's challenging to interact with the LLMs further to revise the program, especially if the user's specific requirements are different from the initial proposal.
Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?
However, current evidence indicates the contrary.
xTrimoGene: An Efficient and Scalable Representation Learner for Single-Cell RNA-Seq Data
Advances in high-throughput sequencing technology have led to significant progress in measuring gene expressions at the single-cell level. The amount of publicly available single-cell RNA-seq (scRNA-seq) data is already surpassing 50M records for humans with each record measuring 20,000 genes.
