Trending Research
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
LeapLabTHU/Absolute-Zero-Reasoner
?
?
6 May 2025
Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning capabilities of large language models by learning directly from outcome-based rewards.
PixelHacker: Image Inpainting with Structural and Semantic Consistency
Specifically, we first construct a large dataset containing 14 million image-mask pairs by annotating foreground and background (potential 116 and 21 categories, respectively).
Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play
maitrix-org/voila
?
?
5 May 2025
A voice AI agent that blends seamlessly into daily life would interact with humans in an autonomous, real-time, and emotionally expressive manner.
Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities
aidc-ai/awesome-unified-multimodal-models
?
?
5 May 2025
Despite their respective successes, these two domains have evolved independently, leading to distinct architectural paradigms: While autoregressive-based architectures have dominated multimodal understanding, diffusion-based models have become the cornerstone of image generation.
LTX-Video: Realtime Video Latent Diffusion
Lightricks/LTX-Video
?
?
30 Dec 2024
To address this, our VAE decoder is tasked with both latent-to-pixel conversion and the final denoising step, producing the clean result directly in pixel space.
WebThinker: Empowering Large Reasoning Models with Deep Research Capability
Large reasoning models (LRMs), such as OpenAI-o1 and DeepSeek-R1, demonstrate impressive long-horizon reasoning capabilities.
FastVLM: Efficient Vision Encoding for Vision Language Models
apple/ml-fastvlm
?
?
17 Dec 2024
At different operational resolutions, the vision encoder of a VLM can be optimized along two axes: reducing encoding latency and minimizing the number of visual tokens passed to the LLM, thereby lowering overall latency.
Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents
simular-ai/agent-s
?
?
1 Apr 2025
Computer use agents automate digital tasks by directly interacting with graphical user interfaces (GUIs) on computers and mobile devices, offering significant potential to enhance human productivity by completing an open-ended space of user queries.
LiftFeat: 3D Geometry-Aware Local Feature Matching
lyp-deeplearning/liftfeat
?
?
6 May 2025
We then design a 3D geometry-aware feature lifting module to fuse surface normal feature with raw 2D descriptor feature.
PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding
facebookresearch/perception_models
?
?
17 Apr 2025
In this paper, we study building a Perception Language Model (PLM) in a fully open and reproducible framework for transparent research in image and video understanding.
Ranked #4 on
Video Question Answering
on NExT-QA
