Trending Research
FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry
The fusion of both visual and LiDAR measurements is based on a single unified voxel map where the LiDAR module constructs the geometric structure for registering new LiDAR scans and the visual module attaches image patches to the LiDAR points.
MatMamba: A Matryoshka State Space Model
scaledfoundations/matmamba
•
•
In this work, we present MatMamba: a state space model which combines Matryoshka-style learning with Mamba2, by modifying the block to contain nested dimensions to enable joint training and adaptive inference.
How to Train Long-Context Language Models (Effectively)
We study continued training and supervised fine-tuning (SFT) of a language model (LM) to make effective use of long-context information.
SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration
Although quantization has proven to be an effective method for accelerating model inference, existing quantization methods primarily focus on optimizing the linear layer.
FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs
This report introduces FunAudioLLM, a model family designed to enhance natural voice interactions between humans and large language models (LLMs).
PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation
We present PhysGen, a novel image-to-video generation method that converts a single image and an input condition (e. g., force and torque applied to an object in the image) to produce a realistic, physically plausible, and temporally consistent video.
PHI-S: Distribution Balancing for Label-Free Multi-Teacher Distillation
nvlabs/radio
•
•
Various visual foundation models have distinct strengths and weaknesses, both of which can be improved through heterogeneous multi-teacher knowledge distillation without labels, termed "agglomerative models."
Q-VLM: Post-training Quantization for Large Vision-Language Models
On the contrary, we mine the cross-layer dependency that significantly influences discretization errors of the entire vision-language model, and embed this dependency into optimal quantization strategy searching with low search cost.
A Multi-Level Superoptimizer for Tensor Programs
We introduce Mirage, the first multi-level superoptimizer for tensor programs.
Grounding Image Matching in 3D with MASt3R
naver/mast3r
•
•
Image Matching is a core component of all best-performing algorithms and pipelines in 3D vision.
