Trending Research
Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
Large Language Models (LLMs) have revolutionized artificial intelligence (AI) by enabling human like text generation and natural language understanding.
Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search
hjyao00/mulberry
•
•
Using CoMCTS, we construct Mulberry-260k, a multimodal dataset with a tree of rich, explicit and well-defined reasoning nodes for each question.
Predicting Human Brain States with Transformer
The human brain is a complex and highly dynamic system, and our current knowledge of its functional mechanism is still very limited.
Click-Calib: A Robust Extrinsic Calibration Method for Surround-View Systems
Surround-View System (SVS) is an essential component in Advanced Driver Assistance System (ADAS) and requires precise calibrations.
Lifelong Learning of Large Language Model based Agents: A Roadmap
This survey is the first to systematically summarize the potential techniques for incorporating lifelong learning into LLM-based agents.
Don't Do RAG: When Cache-Augmented Generation is All You Need for Knowledge Tasks
hhhuang/cag
•
•
With the advent of large language models (LLMs) featuring significantly extended context windows, this paper proposes an alternative paradigm, cache-augmented generation (CAG) that bypasses real-time retrieval.
Gated Delta Networks: Improving Mamba2 with Delta Rule
sustcsonglin/flash-linear-attention
•
•
Linear Transformers have gained attention as efficient alternatives to standard Transformers, but their performance in retrieval and long-context tasks has been limited.
StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows
ag2ai/ag2
•
•
In StateFlow, we distinguish between "process grounding" (via state and state transitions) and "sub-task solving" (through actions within a state), enhancing control and interpretability of the task-solving procedure.
The GAN is dead; long live the GAN! A Modern GAN Baseline
brownvc/r3gan
•
•
There is a widely-spread claim that GANs are difficult to train, and GAN architectures in the literature are littered with empirical tricks.
Ranked #3 on
Image Generation
on ImageNet 32x32
3DIS-FLUX: simple and efficient multi-instance generation with DiT rendering
limuloo/3DIS
•
•
In this paper, we present 3DIS-FLUX, an extension of the 3DIS framework that integrates the FLUX model for enhanced rendering capabilities.
