Wiki

Single-point PageRank calculation uses a random walk model to determine the importance of a node.

Reinforced fine-tuning combines supervised fine-tuning and reinforcement learning to optimize the model's ability to generate high-quality answers.

NLRL redefines the core concepts of reinforcement learning in the form of natural language.

MILP-StuDio aims to generate high-quality MILP instances by preserving the problem partitioning structure.

MILP is a mathematical optimization technique used to find the maximum or minimum of a linear objective function subject to a set of linear constraints.

Event-based Camera, also known as Dynamic Vision Sensor (DVS) or DAVIS (Dynamic and Active-Pixel Vision Sensor), is a new type of visual sensor. It is different from traditional cameras […]

The core purpose of the UDK-VQA framework is to enhance existing Large Scale Vision-Language Models (LVLMs) to enable them to handle Visual Question Answering (VQA) with state-of-the-art knowledge.

The SearchLVLMs framework can significantly improve the performance of LVLMs in answering questions that require state-of-the-art knowledge.

The LLMxMapReduce framework breaks the memory limitations of large models and theoretically achieves the processing capability of "infinite length" context.

AdaCache is a technology proposed by Meta in 2024 to accelerate AI video generation. Its core is the adaptive caching mechanism. The related paper results are “Adaptive Caching for Faster Video Generation w […]

In 2024, Carnegie Mellon University (CMU) proposed a new black-box optimization strategy that automatically adjusts natural language prompts through a large language model to optimize the performance of visual language models (VLMs) in multiple downstream tasks such as text maps and visual recognition. This method not only does not require touching the model […]

DexMimicGen is able to generate large amounts of robot training data from a small number of human demonstrations.

MIA-DPO (Multi-Image Augmented Direct Preference Optimization) is a multi-image augmented preference alignment method for large visual language models (LVLMs), which was jointly developed by Shanghai Jiao Tong University and Shanghai Renmin University.

Mel-frequency cepstrum is a widely used technique in the field of sound processing, especially in speech recognition and speaker identification.

Dijkstra's algorithm is a classic algorithm for finding the shortest path from a single source in a graph.

WISE technology aims to combat hallucination phenomena in large language models and improve the model's knowledge memory editing capabilities.

DuoAttention optimizes memory and computing resources by applying a full KV cache for retrieval headers and a lightweight, fixed-length KV cache for streaming headers.

Instead of pursuing a one-to-one correspondence with real objects, digital cousins focus on similar geometric and semantic qualities, thereby generating practical training data at a lower cost.

DAPE stands for Data-Adaptive Positional Encoding, a new positional encoding method proposed by Zheng Chuanyang and others from the Chinese University of Hong Kong. The research team also includes researchers from the National University of Singapore, Noah Lab, the University of Hong Kong, and Hong Kong Baptist University. […]

SparseLLM is a new global pruning framework proposed by researchers from Emory University and Argonne National Laboratory in 2024. The related paper is “SparseLLM: Towards Global Pruning of Pre-trai […]

Diff Transformer calculates two independent softmax attention maps and then takes the difference to get the final attention score. This method can effectively eliminate attention noise and prompt the model to pay more attention to the most relevant parts of the input.

UNA stands for Unified Alignment Framework, a new alignment framework proposed by a research team from Salesforce and Xiamen University. The related paper is “UNA: Unifying Alignments of […]

Swarm is an experimental multi-agent framework developed by OpenAI in 2024 that aims to simplify the construction, orchestration, and deployment of multi-agent systems. Swarm focuses on making agent collaboration and execution lightweight, highly controllable, and easy to test. The core of Swarm […]

Michelangelo is a method proposed by DeepMind researchers in 2024 to evaluate the reasoning ability of large language models in long text contexts. It uses a framework called Latent Structure Queries (LSQ) […]