The last known location of Rishab Iyer’s Jeep has just come to light
The last known location of Rishab Iyer’s Jeep has just come to light.
With all communication with Rishab Iyer and his family cut off, the route taken by their vehicle has become a crucial lead to follow.
GPS data obtained by the family suggests the Jeep may have headed toward the highway.
Now, the route is being cross-referenced with other data to determine where the Iyer family might have gone.
Read more 👇
*************
The last known location of the Jeep carrying Australian medical student Rishab Iyer and his family has become a central focus for those searching for them after catastrophic flooding near the Nepal-Tibet border.
Rishab Iyer, 23, a final-year medical student, vanished along with his parents Sreedharan and Lakshmi Iyer and his younger brother Rudhra on 26 August 2026. The family was part of a pilgrimage group travelling toward the sacred site of Mount Kailash when a glacier collapse triggered devastating floods and landslides that killed more than 1,200 people and left thousands missing, including dozens of Australians.
With all direct communication cut off for more than a week, GPS data recovered by Rishab’s partner, Sarada Viswanathan, has provided one of the few concrete leads. According to location information from the Life360 app and Apple’s Find My service, the family’s vehicle was near their hotel close to the border around 8:45am local time. Minutes later, data points show movement farther up the highway. Viswanathan has said the trail of the Jeep goes cold approximately 30 minutes before the floods struck the area.
“This is the last known location of Rishab’s that I have on Life360. This is the hotel that they were staying at,” Viswanathan explained while reviewing maps from her home in Sydney. “And then here we have his brother’s location about five minutes later. Down here is the hotel. So we can see that they’ve gone up on the highway.”
She and other relatives have been cross-referencing that route with satellite imagery, phone records and information obtained by other members of the same tour group. Relatives of one group member who used a local Nepali phone number were able to obtain later signal data through authorities in Nepal showing activity farther north later on the day of the disaster. Similar data for Australian phone numbers has proved harder to access.
A Family on Pilgrimage
The Iyer family, from the Sydney suburb of Cherrybrook, had joined a group of about 15 Australian friends and other travellers on a Hindu pilgrimage to Mount Kailash. Rishab was in his final year of the Joint Medical Program and was due to begin work as an intern doctor at Gosford Hospital. His younger brother Rudhra was also studying medicine. Their mother Lakshmi ran an early learning centre, and their father Sreedharan worked as a mortgage broker. Both brothers played cricket for a local club.
They were staying at a hotel near a river in the disaster zone. Viswanathan last spoke to Rishab on the morning of 26 August. He mentioned that roads had been closed the previous day because of landslides and that connectivity was already poor. Roughly 20 to 30 minutes after their last contact, the catastrophic flooding began.
None of the vehicles in the tour group, nor any of the travellers, have been accounted for. Access to the worst-affected areas remains extremely difficult because of destroyed roads, ongoing hazards and the remote mountainous terrain.
The Struggle for Data
From her living room in north-western Sydney, Viswanathan has coordinated an unofficial search effort involving family, friends, maps and every digital trail available. She has repeatedly requested more detailed location and call-record data from technology companies and telecommunications providers, arguing that privacy rules should not prevent life-saving information from being shared in a mass-casualty disaster.
“Their phones are most likely dead. They have no way of contacting us. We’re really just begging for help,” she said. “It’s not just some random situation where I’m just trying to see where my partner is. I’m trying to save his life.”
Companies including Apple, Optus and Life360 have cited privacy and security policies in declining to release further individual customer data. Australian Foreign Minister Penny Wong later announced that Australia would share certain telecommunications data with Nepali authorities to assist the search for missing nationals.
Viswanathan has described the past week as “hell.” She and other relatives continue to hope that the family managed to reach higher ground or a remote area that remains cut off from communication. At the same time, they acknowledge the scale of the destruction and the length of time that has passed without contact.
Broader Context of the Disaster
The floods, triggered by a glacier collapse, devastated communities on both sides of the Nepal-Tibet border. Official figures have put the death toll above 1,200, with more than 4,200 people still missing. Among the missing are hundreds of foreign nationals, including 38 Australians at the time of recent reports. Rescue operations have been hampered by the difficult terrain, damaged infrastructure and the sheer number of people unaccounted for.
Relatives of the Iyer family have travelled to Nepal to assist on the ground and to pass information back to those coordinating efforts from Australia. Viswanathan has also supported calls for greater official Australian involvement, including the possible deployment of additional search resources.
A Narrowing Focus on the Highway Route
The GPS trail showing the Jeep moving from the hotel area onto the highway remains one of the most specific pieces of information available to the family. Searchers and relatives are now trying to determine how far the vehicle may have travelled, what roads or tracks were still open at that time, and whether any survivors or debris have been found along that corridor.
Every new data point is being checked against satellite images taken before and after the disaster, witness accounts from the wider region, and information shared by other affected families. The process is painstaking and emotionally exhausting, but Viswanathan has said she will not stop until there is confirmed news.
“My search will never end,” she has stated. “I will keep looking for him until anything is confirmed.”
For the moment, the last known movements of Rishab Iyer’s Jeep stand as both a source of fragile hope and a stark reminder of how quickly a pilgrimage became a race against time in one of the most remote and unforgiving landscapes on earth. Authorities in Nepal, Australian consular officials, and the families of the missing continue to work through the limited leads available while the search for answers goes on.
Rishabh Iyer: Comprehensive Overview of Academic Excellence, Artificial Intelligence Research, and Recent Updates
Introduction and Professional Background
Dr. Rishabh Iyer stands out as a prominent figure in modern computer science, celebrated for his pioneering contributions to machine learning, optimization theory, and data subset selection. Operating at the intersection of rigorous mathematical theory and practical, scalable artificial intelligence, Dr. Iyer has carved a unique niche in the global research community. He currently serves as an Assistant Professor in the Department of Computer Science at the University of Texas at Dallas (UTD), where he directs the CARAML Lab, while also maintaining a strong collaborative research footprint as a Research Scientist at Microsoft. His academic journey reflects deep roots in elite institutions, beginning with his Bachelor’s degree from the Indian Institute of Technology (IIT) Bombay, followed by his Master’s and Ph.D. degrees in Electrical Engineering from the University of Washington, Seattle, where he worked closely with Professor Jeff Bilmes. Furthermore, a parallel academic profile exists for Dr. Rishabh Iyer at the University of California, Berkeley (UC Berkeley), focusing on computer systems, operating systems, and networking architectures, showcasing the multi-disciplinary depth associated with researchers bearing this name in the contemporary technological ecosystem.
Core Research Focus: Submodular Optimization and Data Subset Selection
The primary thrust of Dr. Rishabh Iyer’s research laboratory centers on making machine learning systems remarkably efficient, interpretable, and sustainable through advanced optimization techniques. Modern artificial intelligence is constrained by a fundamental bottleneck: the astronomical cost of compute and the sheer volume of data required to train massive models. Dr. Iyer addresses this by leveraging submodular optimization—a mathematical framework that mirrors properties like diminishing returns, making it exceptionally well-suited for combinatorial problem-solving.
Through his work, he designs algorithmic frameworks that allow deep neural networks to select concise, highly informative subsets of data rather than blindly consuming entire data lakes. This philosophy has given rise to robust toolkits such as submodlib, an open-source Python library designed to democratize submodular optimization for developers and researchers worldwide. By extracting representative, diverse, and informative data coresets, his methodologies drastically lower training times, reduce carbon footprints associated with massive server clusters, and mitigate issues related to class imbalance and out-of-distribution data.
Recent Breakthroughs and Conference Contributions
Dr. Iyer’s research group maintains an active publishing schedule at top-tier artificial intelligence and machine learning venues, including NeurIPS, ICML, EMNLP, CVPR, and AAAI. Recent cycles highlight his group’s expansion into combinatorial representation learning and efficient large language model (LLM) pre-training:
Combinatorial Representation Learning (SCoRe and SSmile): Recent works out of his lab have introduced novel families of combinatorially inspired loss functions designed to enhance self-supervised learning, few-shot learning, and real-world class-imbalanced scenarios. Projects like SCoRe (Submodular Combinatorial Representation Learning) push the boundaries of how models extract meaningful representations without succumbing to majority-class dominance.
Compute-Efficient LLM Pre-training (INGENIOUS): Recognizing the intense computational demands of generative AI and large language models, Dr. Iyer co-authored pivotal research such as INGENIOUS, which explores the utilization of informative data subsets to streamline and optimize the pre-training phases of massive language models.
Active Learning and Computer Vision Applications: His contributions extend heavily into autonomous systems and computer vision. Frameworks like STONE (for active 3D object detection) and TALISMAN (targeted active learning for detecting rare scenarios in autonomous driving, such as motorcycles at night or pedestrians in heavy fog) demonstrate how data subset selection directly enhances safety and reliability in critical real-world deployments.
Medical Imaging and Fairness in AI: Addressing societal and domain-specific challenges, his research incorporates targeted active learning strategies (such as DIAGNOSE) to handle class imbalances in medical imaging, ensuring that diagnostic models perform equitably across all clinical categories. Concurrently, his work on fair speech recognition, supported by accolades like the Amazon Research Award, tackles accent adaptation and bias mitigation in automatic speech recognition (ASR) systems.
Academic Leadership, Editorial Roles, and Honors
Dr. Iyer’s standing in the scientific community is further underscored by his active service as an Area Chair and Senior Program Committee member for premier conferences like NeurIPS, ICLR, and AAAI. He has also taken on editorial responsibilities, serving as an Action Editor for the prestigious IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI).
Over his career, he has accumulated numerous accolades, including multiple Best Paper Awards (such as at NeurIPS and ICML), Microsoft and Facebook Ph.D. Fellowships, NSF Medium and Collaborative Grants, and multiple Adobe Data Science Research Awards. These honors reflect not only his individual brilliance but also the high practical impact of his lab’s open-source tools and theoretical models.
Broader Context and Ongoing Evolution
As artificial intelligence transitions from an era of unbridled data accumulation to an era of refined, efficient, and sustainable scaling, the foundational principles championed by Dr. Rishabh Iyer—namely smart data selection, submodular design, and mathematical optimization—are becoming industry standards. Whether he is optimizing edge devices for autonomous vehicles, accelerating the training cycles of foundational language models, or ensuring algorithmic fairness across demographic lines, Dr. Iyer’s ongoing work continues to shape the structural blueprint of next-generation machine learning systems.
