Bibliographic record
Abstract
Nowadays, Virtual reality(VR) and Aug- mented reality(AR) have become one of the most popular format in many fields, for example video gaming, medical training and even aviation. VR and AR technique simulates images in an edge device, it gives an immersive experience to the users. AR/VR requires high resolution and high FPS for good experience. However, most of the AR/VR devices are made of embedded device due to the limitation of the size and weight of the headset. It is hard to render high quality frames in headset. Many popular VR/AR applications utilize the desktop and server to render the frames and transmit the frames to VR/AR for display. Data transmission from a more powerful device to the VR/AR device requires high transmission speed (1.6GB/s for Oculus quest 2), it is hard to provide the bandwidth with wireless protocol (WIFI/5G). HDMI or DP cable can be applied, but they limit the use case of the VR/AR devices. In this paper, we proposed a latency sensitive super sampling hardware accelerator for VR/AR devices based on machine learning which can significantly reduce the bandwidth requires to transmit frames to VR/AR. In our experiment, the super sampling can deliver high-resolution frames with 25% bandwidth which enable the wireless protocal for VR/AR devices. We implemented the accelerators in RTL and synthesis it with 130 nm skywater pkd. The power consumption of our accelerator at normal data rate for VR/AR devices is 20.97 w and the area is 299.602 mm2.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.021 | 0.004 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".