Trending Research
Transformers without Normalization
jiachenzhu/DyT
•
•
Normalization layers are ubiquitous in modern neural networks and have long been considered essential.
HybridFlow: A Flexible and Efficient RLHF Framework
volcengine/verl
•
•
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.
Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond
The Light-R1 series of work validates training long-COT models from scratch, showcases the art in SFT data and releases SOTA models from RL.
OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scale
Text-to-SQL, the task of translating natural language questions into SQL queries, plays a crucial role in enabling non-experts to interact with databases.
Retrieval-Augmented Generation with Hierarchical Knowledge
Graph-based Retrieval-Augmented Generation (RAG) methods have significantly enhanced the performance of large language models (LLMs) in domain-specific tasks.
Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models
hiyouga/easyr1
•
•
However, direct training with RL struggles to activate complex reasoning capabilities such as questioning and reflection in MLLMs, due to the absence of substantial high-quality multimodal reasoning data.
HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation
To effectively learn the HealthGPT, we devise a comprehensive medical domain-specific comprehension and generation dataset called VL-Health.
GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing
rongyaofang/got
•
•
We present Generation Chain-of-Thought (GoT), a novel paradigm that enables generation and editing through an explicit language reasoning process before outputting images.
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 #1 on
Real-Time Object Detection
on MS COCO
(using extra training data)
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.
