Trending Research
olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models
PDF documents have the potential to provide trillions of novel, high-quality tokens for training language models.
Lanpaint: Training-Free Diffusion Inpainting with Exact and Fast Conditional Inference
Diffusion models generate high-quality images but often lack efficient and universally applicable inpainting capabilities, particularly in community-trained models.
Executable Code Actions Elicit Better LLM Agents
LLM agents are typically prompted to produce actions by generating JSON or text in a pre-defined format, which is usually limited by constrained action space (e. g., the scope of pre-defined tools) and restricted flexibility (e. g., inability to compose multiple tools).
A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models
Large language models (LLMs) have demonstrated remarkable capabilities in a wide range of tasks, yet their application to specialized domains remains challenging due to the need for deep expertise.
Chain of Draft: Thinking Faster by Writing Less
Large Language Models (LLMs) have demonstrated remarkable performance in solving complex reasoning tasks through mechanisms like Chain-of-Thought (CoT) prompting, which emphasizes verbose, step-by-step reasoning.
Interpreting and Improving Diffusion Models from an Optimization Perspective
yuanchenyang/smalldiffusion
•
•
Denoising is intuitively related to projection.
HybridFlow: A Flexible and Efficient RLHF Framework
hiyouga/easyr1
•
•
Traditional RL can be modeled as a dataflow, where each node represents computation of a neural network (NN) and each edge denotes data dependencies between the NNs.
Residual Kolmogorov-Arnold Network for Enhanced Deep Learning
Despite the strong performance in many computer vision tasks, Convolutional Neural Networks (CNNs) can sometimes struggle to efficiently capture long-range, complex non-linear dependencies in deeper layers of the network.
Learning Efficient Online 3D Bin Packing on Packing Configuration Trees
alexfrom0815/Online-3D-BPP-PCT
•
•
ICLR 2022
PCT is a full-fledged description of the state and action space of bin packing which can support packing policy learning based on deep reinforcement learning (DRL).
Self-rewarding correction for mathematical reasoning
volcengine/verl
•
•
We study self-rewarding reasoning large language models (LLMs), which can simultaneously generate step-by-step reasoning and evaluate the correctness of their outputs during the inference time-without external feedback.
