Trending Research
MOSEL: 950,000 Hours of Speech Data for Open-Source Speech Foundation Model Training on EU Languages
hlt-mt/mosel
•
•
The rise of foundation models (FMs), coupled with regulatory efforts addressing their risks and impacts, has sparked significant interest in open-source models.
AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation
MCG-NJU/AWT
•
•
Pre-trained vision-language models (VLMs) have shown impressive results in various visual classification tasks.
Text2SQL is Not Enough: Unifying AI and Databases with TAG
Such systems would allow users to leverage the powerful reasoning and knowledge capabilities of language models (LMs) alongside the scalable computational power of data management systems.
Resolving Multi-Condition Confusion for Finetuning-Free Personalized Image Generation
Personalized text-to-image generation methods can generate customized images based on the reference images, which have garnered wide research interest.
PrefixQuant: Static Quantization Beats Dynamic through Prefixed Outliers in LLMs
Specifically, PrefixQuant identifies high-frequency outlier tokens and prefixes them in the KV cache, preventing the generation of outlier tokens during inference and simplifying quantization.
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.
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.
CAR: Controllable Autoregressive Modeling for Visual Generation
To the best of our knowledge, we are the first to propose a control framework for pre-trained autoregressive visual generation models.
Unraveling Cross-Modality Knowledge Conflict in Large Vision-Language Models
luka-group/vlm-knowledge-conflict
•
•
Specifically, using LLaVA-34B, our proposed dynamic contrastive decoding improves an average accuracy of 2. 24%.
Breaking reCAPTCHAv2
aplesner/Breaking-reCAPTCHAv2
•
•
Our work examines the efficacy of employing advanced machine learning methods to solve captchas from Google's reCAPTCHAv2 system.
