Trending Research
MM-Eureka: Exploring Visual Aha Moment with Rule-based Large-scale Reinforcement Learning
We present MM-Eureka, a multimodal reasoning model that successfully extends large-scale rule-based reinforcement learning (RL) to multimodal reasoning.
Proximal Policy Optimization Algorithms
hiyouga/easyr1
•
•
We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent.
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.
PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides
Automatically generating presentations from documents is a challenging task that requires balancing content quality, visual design, and structural coherence.
Exploring the Coordination of Frequency and Attention in Masked Image Modeling
guijiejie/amt
•
•
To tackle this issue, we propose the Frequency \& Attention-driven Masking and Throwing Strategy (FAMT), which can extract semantic patches and reduce the number of training patches to boost model performance and training efficiency simultaneously.
A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends
Deep supervised learning algorithms typically require a large volume of labeled data to achieve satisfactory performance.
Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities
Fine-tuning AF2 on LongAudio leads to exceptional performance on our proposed LongAudioBench, an expert annotated benchmark for evaluating ALMs on long audio understanding capabilities.
G-LLaVA: Solving Geometric Problem with Multi-Modal Large Language Model
deep-agent/r1-v
•
•
We first analyze the limitations of current Multimodal Large Language Models (MLLMs) in this area: they struggle to accurately comprehending basic geometric elements and their relationships.
LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization
Recent advances in text-to-image generation have primarily relied on extensive datasets and parameter-heavy architectures.
2 OLMo 2 Furious
Our modified model architecture and training recipe achieve both better training stability and improved per-token efficiency.
