Zhihao Ren
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhihao Ren has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Nirwan Ansari
New Jersey Institute of Technology, Newark, New Jersey, USA
5 shared publications - Tao Han
New Jersey Institute of Technology, Newark, New Jersey, USA
5 shared publications - Xiaoyu Fang
New Jersey Institute of Technology, Newark, New Jersey, USA
4 shared publications - Sohom Sen
New Jersey Institute of Technology, Newark, New Jersey, USA
3 shared publications - Mingrui Yin
Electrical and Computer Engineering, New Jersey Institute of Technology, Newark, New Jersey, USA
2 shared publications - Haocheng Wang
New Jersey Institute of Technology, Newark, USA
1 shared publication
Latest Publications
- Open Access
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 706-721
ActiveSight: Enabling Continuous Wearable Perception through Algorithm-Hardware Co-Designed Multimodal Semantic Gating
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 706-721
Open AccessActiveSight: Enabling Continuous Wearable Perception through Algorithm-Hardware Co-Designed Multimodal Semantic Gating
- Open Access
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 35-41
ThermWear: Thermal-Aware Backend Scheduling for On-Device Sustained DNN Inference
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 35-41
Open AccessThermWear: Thermal-Aware Backend Scheduling for On-Device Sustained DNN Inference
- Open Access
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 49-55
Toward Codec-Native Interfaces for Wearable Video-Language Systems
Continuous video-language reasoning on wearable devices requires the edge to preserve useful visual evidence before the user query is known. Current pipelines often transmit sampled RGB frames, while standard codecs already organize video into I-frame appearance anchors and P-frame temporal updates. This paper explores whether such codec structure can serve as a lightweight edge-server interface for wearable Video-LM systems. We present EventRetina, a preliminary codec-native split-stream prototype that transmits low-frequency I-frame anchors and saliency-selected P-frame event deltas. The edge selects informative P-frames using codec-side motion and residual statistics under a bandwidth budget, while the server maintains the received anchors and deltas as visual evidence for later question answering. On the Perception Test dataset, EventRetina improves the bandwidth-accuracy tradeoff over I-only streaming and random or uniform P-frame selection. At a 20% P-frame budget, it reaches 46.3% accuracy while transmitting 0.80 Mbps. Under matched temporal evidence, it also reduces server-side visual processing cost compared with repeatedly encoding selected RGB frames. These results suggest that codec-native split-streaming is a promising design point for bandwidth-limited wearable Video-LM reasoning.
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 49-55
Open AccessToward Codec-Native Interfaces for Wearable Video-Language Systems
Continuous video-language reasoning on wearable devices requires the edge to preserve useful visual evidence before the user query is known. Current pipelines often transmit sampled RGB frames, while standard codecs already organize video into I-frame appearance anchors and P-frame temporal updates. This paper explores whether such codec structure can serve as a lightweight edge-server interface for wearable Video-LM systems. We present EventRetina, a preliminary codec-native split-stream prototype that transmits low-frequency I-frame anchors and saliency-selected P-frame event deltas. The edge selects informative P-frames using codec-side motion and residual statistics under a bandwidth budget, while the server maintains the received anchors and deltas as visual evidence for later question answering. On the Perception Test dataset, EventRetina improves the bandwidth-accuracy tradeoff over I-only streaming and random or uniform P-frame selection. At a 20% P-frame budget, it reaches 46.3% accuracy while transmitting 0.80 Mbps. Under matched temporal evidence, it also reduces server-side visual processing cost compared with repeatedly encoding selected RGB frames. These results suggest that codec-native split-streaming is a promising design point for bandwidth-limited wearable Video-LM reasoning.
- Open Access
- 3 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-6
ImmersiveSlicing: An O-RAN Cross-Layer Reinforcement Learning Framework for Low-Latency Immersive Applications
- 3 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-6
Open AccessImmersiveSlicing: An O-RAN Cross-Layer Reinforcement Learning Framework for Low-Latency Immersive Applications