Anatomy of an Outlier: The Lifecycle of Massive Activations in Llama 3.1 (Sep 4)
Published: | 6:27 am | Posted in: Events
Anatomy of an Outlier: The Lifecycle of Massive Activations in Llama 3.1 Xiuwen Liu · Computer Science Colloquium Series TALK Speaker Xiuwen Liu Date Friday, September 4, 2:15 – 3:05 pm Location 307 Love Abstract Recent experiments highlight the prevalence of massive activations—often referred to as outlier features—in pre-norm, open-weight large language models. In this […]
Analog Bloom Filters for Wireless Control: From Cellular Random Access to Scalable LoRa Acknowledgment (Aug 28)
Published: | 9:40 pm | Posted in: Events
Analog Bloom Filters for Wireless Control: From Cellular Random Access to Scalable LoRa Acknowledgment Zhenghao Zhang · Computer Science Colloquium Series TALK Speaker Zhenghao Zhang Date Friday, August 28, 2:15 – 3:05 pm Location 307 Love Abstract Wireless control often asks a simple but difficult question: which users are active, requesting resources, or acknowledged? Existing […]
Developing Indigenous Language Technology for Choctaw: Results and Lessons (April 22)
Published: | 9:26 am | Posted in: Events
Developing Indigenous Language Technology for Choctaw: Results and Lessons Lina Brixey · Department of Computer Science Seminar TALK Speaker Lina Brixey Date April 22, 10:00 AM Location DIFF 009 (In Person Only) Abstract This talk will discuss useful roles where language technologies can be used to improve and ease the process of language documentation and […]
SHiDM: Skiplist-Based Efficient Disaggregated Memory with Hybrid Delegation (March 31)
Published: | 10:36 am | Posted in: Events
SHiDM: Skiplist-Based Efficient Disaggregated Memory with Hybrid Delegation Joydhriti Choudhury · Department of Computer Science Seminar TALK Speaker Joydhriti Choudhury Date March 31, 11:45 – 12:45 pm Location LOV 353 (In Person Only) Abstract Disaggregated memory (DM) architectures separate compute from memory resources and enable flexible scaling and improving memory utilization. DM indexing techniques have […]
Mobile Computing Demo Showcase (April 9)
Published: | 2:11 pm | Posted in: Events
Mobile Computing Demo Showcase Hosted by the Mobile Computing Group at FSU SHOWCASE Date April 9, 2025 Time 1:00 PM – 4:00 PM Location Innovation Hub Register Registration form → We are excited to invite you to the Mobile Computing Demo Showcase! This event features a series of interactive demos exploring emerging technologies in: AI […]
FSU CS Expo 2026 (April 10)
Published: | 3:23 pm | Posted in: Events
FSU CS Expo 2026 Department of Computer Science EXPO Date Friday, April 10, 2026 Time 8:30 AM – 5:30 PM Location Love 353 Register Full expo page & registration → FSU CS Expo 2026 is a department-wide event that brings together students, faculty, alumni, and guests to celebrate research, share ideas, and build connections across […]
iCR: Intent-Driven Checkpoint/Restart (Mar 10)
Published: | 9:50 am | Posted in: Events
iCR: Intent-Driven Checkpoint/Restart Olga Kogiou · Department of Computer Science Seminar TALK Speaker Olga Kogiou Date March 10, 11:45 – 12:45 pm Location LOV 353 (In Person Only) Abstract High Performance Computing applications have evolved from monolithic simulations to interdependent tasks that form heterogeneous workflows. These workflows rely on Checkpoint/Restart (C/R) mechanisms to enable continuity […]
ATOMIC: Attention Reallocation to Mitigate Irrelevant Context in Small Language Models (Mar 3)
Published: | 12:28 pm | Posted in: Events
Speaker: Bolin Shen Date: March 3, 11:45 – 12:45 pm Abstract: Small language models have recently gained increasing attention due to their strong cost efficiency, computational efficiency, and competitive performance across a wide range of reasoning tasks. However, when reasoning inputs contain irrelevant context, SLMS are substantially more vulnerable to distraction than large language models, […]
Robust Machine Learning on the Edge (Feb 27)
Published: | 9:09 am | Posted in: Events
Speaker: Stratis Ioannidis Date: Feb 27, 11:15 – 12:15 pm Abstract: Adversarial robustness, i.e., the ability of a machine learning (ML) algorithm to maintain its predictive power under input perturbations, is an important property for many safety-critical applications. It is even more important in edge deployments of ML algorithms, where inference is performed in a […]
ReAD: Reinforcement-Guided Capability Distillation (Feb 24)
Published: | 10:58 am | Posted in: Events
Speaker: Xueqi Cheng Date: Feb 24, 11:45 – 12:45 pm Abstract: Knowledge distillation (KD) compresses a large model into a smaller one that preserves the capabilities needed for a downstream task, yet existing methods assume that capabilities can be optimized independently…