Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance

thunlp/proactiveagent 16 Oct 2024

The labeled data is used to train a reward model that simulates human judgment and serves as an automatic evaluator of the proactiveness of LLM agents.

210
0.39 stars / hour

Qwen2.5-Coder Technical Report

qwenlm/qwen2.5-coder 18 Sep 2024

In this report, we introduce the Qwen2. 5-Coder series, a significant upgrade from its predecessor, CodeQwen1. 5.

Code Generation +2

3,318
0.39 stars / hour

OminiControl: Minimal and Universal Control for Diffusion Transformer

Yuanshi9815/OminiControl 22 Nov 2024

In this paper, we introduce OminiControl, a highly versatile and parameter-efficient framework that integrates image conditions into pre-trained Diffusion Transformer (DiT) models.

828
0.38 stars / hour

From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents

fudandisc/socialagent 4 Dec 2024

We categorize the simulations into three types: (1) Individual Simulation, which mimics specific individuals or demographic groups; (2) Scenario Simulation, where multiple agents collaborate to achieve goals within specific contexts; and (3) Society Simulation, which models interactions within agent societies to reflect the complexity and variety of real-world dynamics.

Language Modelling Large Language Model

39
0.37 stars / hour

Densely Connected Convolutional Networks

RajdeepBiswas/Manufacturing-Quality-Inspection CVPR 2017

Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output.

Breast Tumour Classification Crowd Counting +8

53
0.37 stars / hour

SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory

yangchris11/samurai 18 Nov 2024

The Segment Anything Model 2 (SAM 2) has demonstrated strong performance in object segmentation tasks but faces challenges in visual object tracking, particularly when managing crowded scenes with fast-moving or self-occluding objects.

Visual Object Tracking Visual Tracking

5,776
0.34 stars / hour

DEIM: DETR with Improved Matching for Fast Convergence

shihuahuang95/deim 5 Dec 2024

We introduce DEIM, an innovative and efficient training framework designed to accelerate convergence in real-time object detection with Transformer-based architectures (DETR).

Data Augmentation object-detection +1

45
0.34 stars / hour

Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback

allenai/open-instruct 13 Jun 2024

High-quality preference data leads to improvements of up to 8% in instruction following and truthfulness.

Instruction Following Math

2,064
0.34 stars / hour

StableAnimator: High-Quality Identity-Preserving Human Image Animation

Francis-Rings/StableAnimator 26 Nov 2024

During inference, we propose a novel Hamilton-Jacobi-Bellman (HJB) equation-based optimization to further enhance the face quality.

Denoising Face Reenactment +3

248
0.33 stars / hour

One Diffusion to Generate Them All

lehduong/onediffusion 25 Nov 2024

Experimental results demonstrate competitive performance across tasks in both generation and prediction such as text-to-image, multiview generation, ID preservation, depth estimation and camera pose estimation despite relatively small training dataset.

Camera Pose Estimation Deblurring +4

326
0.33 stars / hour