Country
Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite Programming
IoT devices, where limitations in memory, processing power and energy are critical [Sze et al., 2017]. To address these issues, Muller and Indiveri [2015] and Courbariaux et al. [2015b] noted that
LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition (Supplementary Material)
In Figure 1, we compare our LMC framework with the baseline Softmax, and present qualitative results on the TinyImageNet dataset. Below, we discuss them in more detail. AUROC is a widely-used threshold-independent evaluation metric. Both authors contributed equally to the work. Before entering the inference process, similar to our framework, Softmax also pre-stores certain CLIP and DINO features to make the inference process more efficient.
Supplemental: A Benchmark for Compositional Text-to-image Retrieval
GQA GQA has annotations of objects and attributes in images. We use this to construct queries like "square white plate". We train on the GQA train split (with the test unseen queries and corresponding images removed). Hence, we have around 67K training images and 27K queries. CLEVR On CLEVR, we test on 96 classes on 22,500 images.
T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models Yibo Miao
The recent development of Sora leads to a new era in text-to-video (T2V) generation. Along with this comes the rising concern about its safety risks.
Provable Partially Observable Reinforcement Learning with Privileged Information Yang Cai
Partial observability of the underlying states generally presents significant challenges for reinforcement learning (RL).