Trending Research
Proactive Agent: Shifting LLM Agents from Reactive Responses to Active Assistance
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.
Qwen2.5-Coder Technical Report
In this report, we introduce the Qwen2. 5-Coder series, a significant upgrade from its predecessor, CodeQwen1. 5.
OminiControl: Minimal and Universal Control for Diffusion Transformer
In this paper, we introduce OminiControl, a highly versatile and parameter-efficient framework that integrates image conditions into pre-trained Diffusion Transformer (DiT) models.
From Individual to Society: A Survey on Social Simulation Driven by Large Language Model-based Agents
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.
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.
Ranked #1 on
Classification
on XImageNet-12
SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory
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.
Ranked #1 on
Visual Object Tracking
on GOT-10k
DEIM: DETR with Improved Matching for Fast Convergence
We introduce DEIM, an innovative and efficient training framework designed to accelerate convergence in real-time object detection with Transformer-based architectures (DETR).
Ranked #7 on
Real-Time Object Detection
on MS COCO
Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback
High-quality preference data leads to improvements of up to 8% in instruction following and truthfulness.
StableAnimator: High-Quality Identity-Preserving Human Image Animation
Francis-Rings/StableAnimator
•
•
During inference, we propose a novel Hamilton-Jacobi-Bellman (HJB) equation-based optimization to further enhance the face quality.
One Diffusion to Generate Them All
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.
