GTR can guide model reasoning in complex visual environments and prevent "brain breakdown".

Spatial theory refers to the framework of an intelligent agent’s ability to construct, update and utilize spatial beliefs in an environment of incomplete information through active exploration.

A decentralized machine learning approach that keeps training data on a local device and trains a shared global model by aggregating locally computed model updates only.

PRGS significantly enhances the ability of offline reinforcement learning models to stitch together high-reward experiences.

The dense search engine is responsible for quickly finding the paragraphs most relevant to the query semantics from a massive document library, and is the core foundational component of the search enhancement generation system.

Multi-agent architecture is an artificial intelligence system structure in which multiple intelligent agents cooperate to complete complex tasks.

Agentic RAG is an enhanced generation method that uses agents to dynamically retrieve, verify, and integrate information.

Agent memory is a mechanism for storing and retrieving information, enabling agent systems to maintain context and accumulate experience.

A single-agent architecture is an AI system structure in which a single agent uniformly completes task understanding, decision-making, and execution.

MVP achieves single-step action generation with both high expressive power and extremely fast computation by modeling the average velocity field.

WorldGen is capable of creating geometrically unified, visually rich, and highly efficient real-time rendering worlds.

Model Souping can generate a better model by averaging the weights of multiple fine-tunings.

By leveraging GPU parallelism to efficiently expand the decoding tree, fast and scalable optimization of the inference path is achieved.

Skills are reusable capability modules that encapsulate knowledge and processes, enabling AI to transform from general-purpose models into specialized intelligent agents.

SoCE is a model optimization paradigm based on an automatic category-aware expert selection mechanism and combined with multiple benchmark tasks.

DePass is used to interpret the Transformer model by decomposing the forward pass.

A file format for storing medical imaging data

iSeal achieves a 100% fingerprint success rate (FSR) against more than 10 attacks on 12 LLMs.

It effectively solves the key challenges in LVLM secure alignment.

VLM can achieve cross-modal understanding, reasoning, and generation tasks by aligning and fusing image and text information.

VLA can generate robot movements directly based on visual images and verbal commands.

The NSG statistic quantifies the ratio of spatial probability gradient to temporal density change.

Mem-I has achieved significant improvements over existing memory-enhanced agent baselines in multiple benchmark tests.

SSP demonstrates the potential of self-game theory as a scalable and data-efficient training paradigm for agent LLM.

GTR can guide model reasoning in complex visual environments and prevent "brain breakdown".

Spatial theory refers to the framework of an intelligent agent’s ability to construct, update and utilize spatial beliefs in an environment of incomplete information through active exploration.

A decentralized machine learning approach that keeps training data on a local device and trains a shared global model by aggregating locally computed model updates only.

PRGS significantly enhances the ability of offline reinforcement learning models to stitch together high-reward experiences.

The dense search engine is responsible for quickly finding the paragraphs most relevant to the query semantics from a massive document library, and is the core foundational component of the search enhancement generation system.

Multi-agent architecture is an artificial intelligence system structure in which multiple intelligent agents cooperate to complete complex tasks.

Agentic RAG is an enhanced generation method that uses agents to dynamically retrieve, verify, and integrate information.

Agent memory is a mechanism for storing and retrieving information, enabling agent systems to maintain context and accumulate experience.

A single-agent architecture is an AI system structure in which a single agent uniformly completes task understanding, decision-making, and execution.

MVP achieves single-step action generation with both high expressive power and extremely fast computation by modeling the average velocity field.

WorldGen is capable of creating geometrically unified, visually rich, and highly efficient real-time rendering worlds.

Model Souping can generate a better model by averaging the weights of multiple fine-tunings.

By leveraging GPU parallelism to efficiently expand the decoding tree, fast and scalable optimization of the inference path is achieved.

Skills are reusable capability modules that encapsulate knowledge and processes, enabling AI to transform from general-purpose models into specialized intelligent agents.

SoCE is a model optimization paradigm based on an automatic category-aware expert selection mechanism and combined with multiple benchmark tasks.

DePass is used to interpret the Transformer model by decomposing the forward pass.

A file format for storing medical imaging data

iSeal achieves a 100% fingerprint success rate (FSR) against more than 10 attacks on 12 LLMs.

It effectively solves the key challenges in LVLM secure alignment.

VLM can achieve cross-modal understanding, reasoning, and generation tasks by aligning and fusing image and text information.

VLA can generate robot movements directly based on visual images and verbal commands.

The NSG statistic quantifies the ratio of spatial probability gradient to temporal density change.

Mem-I has achieved significant improvements over existing memory-enhanced agent baselines in multiple benchmark tests.

SSP demonstrates the potential of self-game theory as a scalable and data-efficient training paradigm for agent LLM.