Trending Research
A Diffusion Model and Knowledge Distillation Framework for Robust Coral Detection in Complex Underwater Environments
RDXiaoLu/MambaCoral-DiffDet
•
•
SSRN 2025
From an engineering perspective, MCDD significantly advances automated coral detection in challenging underwater conditions, providing a reliable solution for monitoring marine ecosystems.
Ranked #1 on
2D Object Detection
on SCoralDet Dataset
(using extra training data)
LBM: Latent Bridge Matching for Fast Image-to-Image Translation
gojasper/lbm
•
•
In this paper, we introduce Latent Bridge Matching (LBM), a new, versatile and scalable method that relies on Bridge Matching in a latent space to achieve fast image-to-image translation.
LatentSync: Audio Conditioned Latent Diffusion Models for Lip Sync
Since we did not change the overall training framework of SyncNet, our experience can also be applied to other lip sync and audio-driven portrait animation methods that utilize SyncNet.
Transformers without Normalization
jiachenzhu/DyT
•
•
Normalization layers are ubiquitous in modern neural networks and have long been considered essential.
HourVideo: 1-Hour Video-Language Understanding
We present HourVideo, a benchmark dataset for hour-long video-language understanding.
Next-Scale Autoregressive Models are Zero-Shot Single-Image Object View Synthesizers
We present Next-Scale Autoregression Conditioned by View (ArchonView), a method that significantly exceeds state-of-the-art methods despite being trained from scratch with 3D rendering data only and no 2D pretraining.
SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks
Large language model (LLM) agents need to perform multi-turn interactions in real-world tasks.
YOLOE: Real-Time Seeing Anything
THU-MIG/yoloe
•
•
Object detection and segmentation are widely employed in computer vision applications, yet conventional models like YOLO series, while efficient and accurate, are limited by predefined categories, hindering adaptability in open scenarios.
MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilot
However, the diagnostic accuracy and specificity of existing heuristic-based RAG models used in the medical domain are inadequate, particularly for diseases with similar manifestations.
ZO2: Scalable Zeroth-Order Fine-Tuning for Extremely Large Language Models with Limited GPU Memory
liangyuwang/zo2
•
•
Alternatively, zeroth-order (ZO) techniques can compute gradients using just forward operations, eliminating the need to store activations.
