Josh Susskind
PulseAugur coverage of Josh Susskind — every cluster mentioning Josh Susskind across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Apple researchers unveil weighted state souping for efficient long-context retrieval
Apple Machine Learning Research has introduced Weighted State Souping, a novel method to enhance the efficiency of long-context retrieval in State Space Models (SSMs). This technique addresses the limitations of existin…
-
Apple research reveals gating mechanism hinders State Space Models' in-context learning
Researchers at Apple Inc. have published a paper exploring the role of the gating mechanism in State Space Models (SSMs). Their findings indicate that this mechanism, while beneficial for generalization to long sequence…
-
Apple unveils Normalizing Trajectory Models for faster AI image generation
Apple Machine Learning Research has introduced Normalizing Trajectory Models (NTM), a novel approach to generative modeling that maintains exact likelihood training even with a few coarse sampling steps. Unlike previous…
-
Apple researchers unveil new task to test visual concept inference in AI models
Apple Machine Learning Research has introduced a new task called Visual Concept Inference from Sets (VICIS) to evaluate the ability of vision-language models to infer shared concepts from image sets. Current state-of-th…
-
Apple to showcase AI research at CVPR 2026
Apple's Machine Learning Research team will present multiple papers and participate in workshops at the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2026. The company is also a sponsor of the ev…
-
Learning Long-Term Motion Embeddings for Efficient Kinematics Generation
Apple researchers have developed a novel method for generating realistic human motion, significantly improving efficiency in kinematics generation. Their approach involves learning a compressed motion embedding from ext…