Trending Research
AgentKit: Structured LLM Reasoning with Dynamic Graphs
The chains of nodes can be designed to explicitly enforce a naturally structured "thought process".
IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation
IterComp opens new research avenues in reward feedback learning for diffusion models and compositional generation.
A Multi-Level Superoptimizer for Tensor Programs
We introduce Mirage, the first multi-level superoptimizer for tensor programs.
LightRAG: Simple and Fast Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) systems enhance large language models (LLMs) by integrating external knowledge sources, enabling more accurate and contextually relevant responses tailored to user needs.
SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration
Although quantization has proven to be an effective method for accelerating model inference, existing quantization methods primarily focus on optimizing the linear layer.
Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation
Alongside PhyGenBench, we propose a novel evaluation framework called PhyGenEval.
Diffusion Models are Evolutionary Algorithms
Zhangyanbo/diffusion-evolution
•
•
In a convergence of machine learning and biology, we reveal that diffusion models are evolutionary algorithms.
Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale
microsoft/windowsagentarena
•
•
To demonstrate Windows Agent Arena's capabilities, we also introduce a new multi-modal agent, Navi.
Text2SQL is Not Enough: Unifying AI and Databases with TAG
Such systems would allow users to leverage the powerful reasoning and knowledge capabilities of language models (LMs) alongside the scalable computational power of data management systems.
CursorCore: Assist Programming through Aligning Anything
In this work, we propose a new conversational framework that comprehensively integrates these information sources, collect data to train our models and evaluate their performance.
