14 papers
Coordination-Free Workload Regularization for Variable-Cost Distributed Training
Tao Huang, Chen Zhu, Antonio Alonso +4
Synchronous data-parallel training usually assigns every rank the same number of records, even when record costs vary by orders of magnitude. For variable-length models, this conve…
The Ingestion Tax: Adopting File-Backed Weights in Tensor Frameworks
Yuan Si, Yufeng Lin, Daming Li +1
Open-weight models can occupy a middle capacity regime: active weights fit in DRAM as cached file pages, but a second framework-owned copy does not fit or must be refilled as layer…
Who Should Own the Expert Cache? Kernel-Managed Tiering for Trillion-Parameter MoE Inference
Yuan Si, Yufeng Lin, Daming Li +1
Mixture-of-experts models whose expert pools exceed DRAM capacity require a weight-residency tier. Existing systems manage it in user space with expert-granular placement, frequenc…
RENDER: Controlling Reader-Facing Evidence in LLM Memory Evaluation
Yuan Si, Simeng Han, Daming Li +1
Memory and RAG evaluations often treat the answering model's input as an implementation detail, even though systems may render the same history as a memory entry, summary, typed re…
Do Recommendation Algorithms Work When Users Are LLM Agents? A Case Study on Moltbook
Daming Li, Simeng Han, Jialu Zhang
Large language model (LLM) agents are increasingly populating web platforms, raising a fundamental question for recommender systems: do algorithms designed for human users still wo…
Content Hidden Behind Execution: Analyzing Public Scratch Projects at Runtime
Yuan Si, Yufeng Lin, Daming Li +3
Public Scratch projects are reused in computing education as classroom examples, remix sources, open-exploration materials, and research data. Curation often begins with titles, th…
Attraction, Not Adaptation: How AI Agent Communities Develop Distinct Linguistic Identities
Daming Li, Simeng Han, Can Meng +2
When tens of thousands of autonomous AI agents interact in topical online forums, do they develop distinct community-specific linguistic identities? We study this question on Moltb…
Raven: Rethinking Automated Assessment for Scratch Programs via Video-Grounded Evaluation
Donglin Li, Daming Li, Hanyuan Shi +1
Block-based programming environments such as Scratch are widely used in introductory computing education, yet scalable and reliable automated assessment remains elusive. Scratch pr…
EcoScratch: Cost-Effective Multimodal Repair for Scratch Using Execution Feedback
Yuan Si, Ming Wang, Daming Li +2
Scratch is the most popular programming environment for novices, with over 1.15 billion projects created worldwide. Unlike traditional languages, correctness in Scratch is defined…
An Industrial-Scale Sequential Recommender for LinkedIn Feed Ranking
Lars Hertel, Gaurav Srivastava, Syed Ali Naqvi +21
LinkedIn Feed enables professionals worldwide to discover relevant content, build connections, and share knowledge at scale. We present Feed Sequential Recommender (Feed SR), a tra…
ScratchEval : A Multimodal Evaluation Framework for LLMs in Block-Based Programming
Yuan Si, Simeng Han, Daming Li +2
LLMs have achieved strong performance on text-based programming tasks, yet they remain unreliable for block-based languages such as Scratch. Scratch programs exhibit deeply nested,…
Stitch: Step-by-step LLM Guided Tutoring for Scratch
Yuan Si, Kyle Qi, Daming Li +2
Block-based environments such as Scratch are increasingly popular in programming education. While block syntax reduces surface errors, semantic bugs remain common and challenging f…
A Systematic Study of Time Limit Exceeded Errors in Online Programming Assignments
Jialu Zhang, Jialiang Gu, Wangmeiyu Zhang +5
Online programming platforms such as Codeforces and LeetCode attract millions of users seeking to learn to program or refine their skills for industry interviews. A major challenge…
ViScratch: Using Large Language Models and Gameplay Videos for Automated Feedback in Scratch
Yuan Si, Daming Li, Hanyuan Shi +1
Block-based programming environments such as Scratch are increasingly popular in programming education, in particular for young learners. While the use of blocks helps prevent synt…