A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Christoph D. Mathys
Introduces a hierarchical Bayesian framework for individual learning under uncertainty, deriving efficient trial-by-trial update equations that bridge reinforcement learning and Bayesian inference.
Zheng Lin, Guanqiao Qu, Qiyuan Chen, et al.
This article explores deploying large language models at the 6G edge through end-edge cooperation, discussing architecture, training, inference, and open challenges.
Mingjin Zhang, Xiaoming Shen, Jiannong Cao, et al.
EdgeShard partitions LLMs into shards across collaborative edge devices and cloud, using dynamic programming to optimize latency and throughput without accuracy loss.
Vijay Badrinarayanan, Alex Kendall, Roberto Cipolla
SegNet introduces a deep encoder-decoder architecture for semantic segmentation that uses max-pooling indices for efficient non-linear upsampling, achieving competitive accuracy with low memory and inference time.
Unknown
Lazydit introduces a lazy learning approach to accelerate Diffusion Transformers by selectively skipping redundant computations during inference.
Unknown
A privacy-preserving FCNN framework using TFHE-based inference for secure medical image analysis on MedMNIST.
Unknown
KeepKV introduces Electoral Votes for periodic lossless KV cache compression, analyzing compression's impact on attention to enable efficient LLM inference.
Unknown
RocketKV is a training-free two-stage KV cache compression method that accelerates long-context LLM inference by combining coarse-grain permanent eviction with fine-grain dynamic sparsity.
Unknown
Introduces a KV cache compression method that estimates attention from the distribution of future queries to reduce memory usage in large language model inference.
柴田 淳司
Introduces generative adversarial nets, a minimax framework training a generator and discriminator to estimate generative models without Markov chains or approximate inference.
Masahiro Kato, Daiki Honma, Taka Kato
GMMM is a causal inference framework that estimates the business impact of Generative Engine Optimization (GEO) and Generative Engine Marketing (GEM) by combining generated answers, question counts, system shares, and notice probabilities.
Canbin Huang, Tianyuan Shi, Yuhua Zhu, et al.
Lookahead routing predicts latent representations of potential model outputs to guide LLM selection, improving routing decisions without full inference.