CatalyX
PulseAugur coverage of CatalyX — every cluster mentioning CatalyX across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
Image augmentation techniques tested as generators for deep learning image retrieval systems
This paper introduces a novel approach to testing deep learning-based image retrieval systems by utilizing image augmentation techniques as test generators. The research categorizes 50 augmentation methods and empirical…
-
New SlotNarrative Interface Boosts Video-LLM Token Efficiency
Researchers have introduced SlotNarrative, a novel interface designed to make Video Large Language Models (Video-LLMs) more token-efficient. This system organizes videos into persistent object narratives using compact o…
-
New CDIS framework enhances 3D instance segmentation for robots
Researchers have developed a new framework called CDIS for class-agnostic 3D instance segmentation. This zero-shot method tracks 2D instance masks across frames and links them with 3D superpoints, creating a feedback lo…
-
SuperFlex framework enhances point cloud decomposition with novel deformations
Researchers have introduced SuperFlex, an advanced framework for decomposing point clouds into superquadric representations. This new method significantly enhances reconstruction accuracy by incorporating bending and ta…
-
DivRL framework tackles image generation's identity-diversity paradox
Researchers have developed a new post-training framework called DivRL to address the "Identity-Diversity Paradox" in subject-driven image generation. This paradox occurs when maintaining strong identity consistency resu…
-
New framework enhances robot safety with verifiable foundation models
Researchers have developed FEARL, a framework designed to make foundation models safer for robot control. FEARL separates the robot's policy into a large "Controller" for perception and reasoning, and a smaller "Safety"…