27 citations · 47 across the 9 of their papers we have counts for
10 papers
TokenGate: Adapting LLMs for Fast and Memory-Efficient Prefill with Learned Token Pruning
Liana Patel, Rishabh Ranjan, Ion Stoica +2
Expert human readers process large inputs (e.g., code repositories and long documents) by skimming to closely read only what matters. On the other hand, language models process all…
What Happens When the Model Eats the Stack? Rethinking the Research Agenda for Data Agents to Withstand the Bitter Lesson
Liana Patel, Siddharth Jha, Negar Arabzadeh +3
The bitter lesson poses an existential question for the data systems community, whereby large language models (LLMs) trained end-to-end are rapidly internalizing new capabilities t…
Establishing Best Practices for Building Rigorous Agentic Benchmarks
Yuxuan Zhu, Tengjun Jin, Yada Pruksachatkun +22
Benchmarks are essential for quantitatively tracking progress in AI. As AI agents become increasingly capable, researchers and practitioners have introduced agentic benchmarks to e…
DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis
Liana Patel, Negar Arabzadeh, Harshit Gupta +4
The ability to research and synthesize knowledge is central to human expertise and progress. A new class of AI systems--designed for generative research synthesis--aims to automate…
Revisiting Cache Freshness for Emerging Real-Time Applications
Ziming Mao, Rishabh Iyer, Scott Shenker +1
Caching is widely used in industry to improve application performance by reducing data-access latency and taking the load off the backend infrastructure. TTLs have become the de-fa…
Trustless Audits without Revealing Data or Models
Suppakit Waiwitlikhit, Ion Stoica, Yi Sun +2
There is an increasing conflict between business incentives to hide models and data as trade secrets, and the societal need for algorithmic transparency. For example, a rightsholde…
Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks
Daniel Kang, Xuechen Li, Ion Stoica +3
Recent advances in instruction-following large language models (LLMs) have led to dramatic improvements in a range of NLP tasks. Unfortunately, we find that the same improved capab…
ZK-IMG: Attested Images via Zero-Knowledge Proofs to Fight Disinformation
Daniel Kang, Tatsunori Hashimoto, Ion Stoica +1
Over the past few years, AI methods of generating images have been increasing in capabilities, with recent breakthroughs enabling high-resolution, photorealistic "deepfakes" (artif…
Scaling up Trustless DNN Inference with Zero-Knowledge Proofs
Daniel Kang, Tatsunori Hashimoto, Ion Stoica +1
As ML models have increased in capabilities and accuracy, so has the complexity of their deployments. Increasingly, ML model consumers are turning to service providers to serve the…
Exoshuffle: An Extensible Shuffle Architecture
Frank Sifei Luan, Stephanie Wang, Samyukta Yagati +7
Shuffle is one of the most expensive communication primitives in distributed data processing and is difficult to scale. Prior work addresses the scalability challenges of shuffle b…