Trending Research
Kimi-VL Technical Report
We present Kimi-VL, an efficient open-source Mixture-of-Experts (MoE) vision-language model (VLM) that offers advanced multimodal reasoning, long-context understanding, and strong agent capabilities - all while activating only 2. 8B parameters in its language decoder (Kimi-VL-A3B).
Relative Pose Estimation through Affine Corrections of Monocular Depth Priors
markyu98/madpose
•
•
In this paper, we develop three solvers for relative pose estimation that explicitly account for independent affine (scale and shift) ambiguities, covering both calibrated and uncalibrated conditions.
3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting
nv-tlabs/3dgrut
•
•
3D Gaussian Splatting (3DGS) enables efficient reconstruction and high-fidelity real-time rendering of complex scenes on consumer hardware.
VGGT: Visual Geometry Grounded Transformer
We present VGGT, a feed-forward neural network that directly infers all key 3D attributes of a scene, including camera parameters, point maps, depth maps, and 3D point tracks, from one, a few, or hundreds of its views.
Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning
xufangzhi/genius
•
•
This motivates us to enhance LLM reasoning without the need for external supervision.
Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning
In this work, we introduce an adaptive multi-agent framework designed to enhance collaborative reasoning through both model-level training and system-level coordination.
LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds
aigc3d/LHM
•
•
Animatable 3D human reconstruction from a single image is a challenging problem due to the ambiguity in decoupling geometry, appearance, and deformation.
Zep: A Temporal Knowledge Graph Architecture for Agent Memory
We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark.
SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models
To address this, we co-design an inference engine Nunchaku that fuses the kernels of the low-rank branch into those of the low-bit branch to cut off redundant memory access.
Perception-R1: Pioneering Perception Policy with Reinforcement Learning
linkangheng/pr1
•
•
In this work, we return to the fundamentals and explore the effects of RL on different perception tasks.
