○ where users can indicate their topics of interest for exploration.Persona Nodes 2 ○ represent AI-simulated expert perspectives that can suggest related literature retrieved from online publication database (Literature Nodes 3 ○), and subsequently provide feedback and critiques (Critique Nodes 4 ○) to users' initial research idea.Based on the critiques and identified literature, the system can further help revise users' initial idea into a revised RQ (RQ node 5 ○).Users can perform this process iteratively and combine inputs from multiple expert personas until they discover satisfactory RQs of their interest.

Passive, compact, single-shot 3D sensing is useful in many application areas such as microscopy, medical imaging, surgical navigation, and autonomous driving where form factor, time, and power constraints can exist. Ob-taining RGB-D scene information over a short imaging distance, in an ultra-compact form factor, and in a passive, snapshot manner is challenging. Dual-pixel (DP) sensors are a potential solution to achieve the same. DP sensors collect light rays from two different halves of the lens in two interleaved pixel arrays, thus capturing two slightly different views of the scene, like a stereo camera system. However, imaging with a DP sensor implies that the defocus blur size is directly proportional to the disparity seen between the views. This creates a tradeoff between disparity estimation vs. deblurring accuracy. To improve this tradeoff effect, we propose CADS (Coded Aperture Dual-Pixel Sensing), in which we use a coded aperture in the imaging lens along with a DP sensor. In our approach, we jointly learn an optimal coded pattern and the reconstruction algorithm in an end-to-end optimization setting. Our resulting CADS imaging system demonstrates improvement of> 1.5 dB PSNR in all-in-focus (AIF) estimates and 5-6% in depth estimation quality over naive DP sensing for a wide range of aperture settings. Furthermore, we build the proposed CADS prototypes for DSLR photography settings and in an endoscope and a dermoscope form factor. Our novel coded dual-pixel sensing approach demonstrates accurate RGB-D reconstruction results in simulations and real-world experiments in a passive, snapshot, and compact manner.

Cheating detection in large classes with online, take-home exams is an extremely difficult problem. While some cheating can be identified through statistical analysis of all student responses, this analysis can easily be fooled by "smart cheaters'' actively attempting to hide evidence of their unauthorized collaboration. We demonstrate the effectiveness of watermarks combined with creative question design to provide evidence of cheating. We provide results from an initial deployment of our answer watermarking method and do a case study into how "smart cheaters'' attempt to cover their tracks, demonstrating the need for more advanced methods of catching cheating in online, take-home exams.

With the ever growing scale of neural models, knowledge distillation (KD) attracts more attention as a prominent tool for neural model compression. However, there are counter intuitive observations in the literature showing some challenging limitations of KD. A case in point is that the best performing checkpoint of the teacher might not necessarily be the best teacher for training the student in KD. Therefore, one important question would be how to find the best checkpoint of the teacher for distillation? Searching through the checkpoints of the teacher would be a very tedious and computationally expensive process, which we refer to as the checkpoint-search problem. Moreover, another observation is that larger teachers might not necessarily be better teachers in KD, which is referred to as the capacity-gap problem. To address these challenging problems, in this work, we introduce our progressive knowledge distillation (Pro-KD) technique which defines a smoother training path for the student by following the training footprints of the teacher instead of solely relying on distilling from a single mature fully-trained teacher. We demonstrate that our technique is quite effective in mitigating the capacity-gap problem and the checkpoint search problem. We evaluate our technique using a comprehensive set of experiments on different tasks such as image classification (CIFAR-10 and CIFAR-100), natural language understanding tasks of the GLUE benchmark, and question answering (SQuAD 1.1 and 2.0) using BERT-based models and consistently got superior results over state-of-the-art techniques.

Significant memory and computational requirements of large deep neural networks restrict their application on edge devices.Knowledge distillation (KD) is a prominent model compression technique for deep neural networks in which the knowledge of a trained large teacher model is transferred to a smaller student model.The success of knowledge distillation is mainly attributed to its training objective function, which exploits the softtarget information (also known as "dark knowledge") besides the given regular hard labels in a training set.However, it is shown in the literature that the larger the gap between the teacher and the student networks, the more difficult is their training using knowledge distillation.To address this shortcoming, we propose an improved knowledge distillation method (called Annealing-KD) by feeding the rich information provided by the teacher's softtargets incrementally and more efficiently.Our Annealing-KD technique is based on a gradual transition over annealed soft-targets generated by the teacher at different temperatures in an iterative process, and therefore, the student is trained to follow the annealed teacher output in a step-by-step manner.This paper includes theoretical and empirical evidence as well as practical experiments to support the effectiveness of our Annealing-KD method.We did a comprehensive set of experiments on different tasks such as image classification (CIFAR-10 and 100) and NLP language inference with BERT-based models on the GLUE benchmark and consistently got superior results.