Coconut frees the reasoning process from the traditional language space and allows the model to reason directly in the continuous latent space.

The density law describes that the power density of large language models (LLMs) increases exponentially over time.

Nearest neighbor search is an algorithmic problem of finding the point (or set of points) in a database or data set that is closest to a given query point.

Neighbor search refers to the process of determining the neighboring particles around each particle (usually an atom) in the simulation box.

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 […]

Coconut frees the reasoning process from the traditional language space and allows the model to reason directly in the continuous latent space.

The density law describes that the power density of large language models (LLMs) increases exponentially over time.

Nearest neighbor search is an algorithmic problem of finding the point (or set of points) in a database or data set that is closest to a given query point.

Neighbor search refers to the process of determining the neighboring particles around each particle (usually an atom) in the simulation box.

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 […]