activity
20242026
collaborators

11 papers

cs.CY2026

Language-Specific Gaps in AI Safety Training Datasets

Chialuka Prisca-Mary Onuoha, Bright Etornam Sunu, Rashidat Sikiru

Large language model providers routinely cite multilingual safety benchmarks spanning a dozen or more languages as evidence that their models are safe for non-English-speaking user…

cs.DC2026

HiSparse: Scaling Sparse-Attention Decoding with Hierarchical KV Cache Management

Zhiqiang Xie, Zhangheng Huang, Tingwei Huang +3

Top-k sparse attention makes long-context LLM decoding cheap to compute: each step reads only a few thousand selected KV entries rather than the full context. Serving systems, howe…

cs.DB2026

Eiger: An Efficient Library for GPU-based Data Analytics

Bowen Wu, Marko Kabić, Sven Hepkema +3

GPUs have become an increasingly attractive platform for accelerating analytical workloads due to their massive parallelism and high memory bandwidth. Recent studies show that in s…

cs.RO2026

ROSA: A Robotics Foundation Model Serving System for Robot Factories

Wenqi Jiang, Jason Clemons, Rowland O'Flaherty +5

Robotics foundation models (RFMs) are making general-purpose robots increasingly practical for factory deployments. While RFM serving systems are central to this vision, existing s…

cs.DC2026

Regulating Branch Parallelism in LLM Serving

Swapnil Gandhi, Siva Hari, William J. Dally +1

Recent methods expose intra-request parallelism in LLM outputs, allowing independent branches to decode concurrently. Existing serving systems execute these branches eagerly or und…

cs.DC2026

Sparse Checkpointing for Fast and Reliable MoE Training

Swapnil Gandhi, Christos Kozyrakis

As large language models scale, training them requires thousands of GPUs over extended durations--making frequent failures an inevitable reality. While checkpointing remains the pr…