Computer Science > Computation and Language
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Chinese AI lets everyday users command quantum computing with natural language
Chinese AI lets everyday users command quantum computing with natural language Shanghai-based start-up and researchers unveil platform to turn complex emergent field of computer science into mass-accessible technology On May 15, Shanghai-based Youshu Quantum Technology unveiled what it described as the world’s first agent-driven quantum computing platform. UnitaryLab 2.0 is designed to allow users to operate quantum computing systems using natural language alone. Users no longer need to...
A Comparative Study of Student Perspectives on Technical Writing Feedback Quality: Evaluating LLMs, SLMs, and Humans in Computer Science Topics
arXiv:2601.11541v2 Announce Type: replace Abstract: To address the scalability of feedback in computer science while mitigating the privacy and cost limitations of commercial Large Language Models (LLMs), this study evaluates a locally hosted Small Language Model (SLM). We deployed a quantized Llama-3.1, GPT-4, and human instructors across introductory programming (N=176), operating systems (N=80), and a writing seminar (N=7). Mixed-methods analysis of student perceptions reveals that while...
State commitment learning: training language models to distinguish computation from memory
arXiv:2606.05201v1 Announce Type: new Abstract: Reasoning language models do not distinguish tokens used for computation from tokens that constitute persistent state: once generated, all hidden thoughts remain in context and influence future predictions. As a result, downstream reasoning may depend on failed attempts, dead ends, and private scratch work that should not be safely relied on later. We recast this phenomenon as a new training objective, state commitment learning: training models...
If LLMs Have Human-Like Attributes, Then So Does Age of Empires II
Computer Science > Computation and Language [Submitted on 29 May 2026 (v1), last revised 1 Jun 2026 (this version, v2)] Title:If LLMs Have Human-Like Attributes, Then So Does Age of Empires II View PDFAbstract:Much research has been carried out on large language models (LLMs) and LLM-powered agentic workflows. However, many works within the field state emergence of, ascribe to, or assume, generalised anthropomorphic attributes to them (e.g., morality or understanding of natural language).
Are Large Language Models Suitable for Graph Computation? Progress and Prospects
Announce Type: new Abstract: Large language models (LLMs) have been increasingly explored for graph computation, where tasks require reasoning over structured relationships and algorithmic operations. Yet, it remains unclear when LLMs can reliably support such computation and how they should be incorporated into graph-solving pipelines. Existing surveys at the intersection of LLMs and graphs primarily focus on graph learning, text-attributed graphs, or graph-language modeling.
T1: Tool-integrated Verification for Test-time Compute Scaling in Small Language Models
arXiv:2504.04718v2 Announce Type: replace Abstract: Recent studies have demonstrated that test-time compute scaling effectively improves the performance of small language models (sLMs). However, prior research has mainly examined test-time compute scaling with an additional larger model as a verifier, leaving verification by sLMs underexplored. In this work, we investigate whether sLMs can reliably verify the output candidates under test-time scaling.
Diversity Matters: Revisiting Test-Time Compute in Vision-Language Models
Announce Type: new Abstract: Test-time compute (TTC) strategies have emerged as a lightweight approach to boost reasoning in large language models (LLMs). However, their application and benefits for vision-language models (VLMs) remain underexplored. We present a systematic study of TTC across seven VLMs and six benchmarks, specifically analyzing feature-based scoring and majority voting methods.
From Genes to Tokens: a GWAS-inspired Approach for Interpretable Stylometric Analysis
Computer Science > Computation and Language [Submitted on 8 Jun 2026] Title:From Genes to Tokens: a GWAS-inspired Approach for Interpretable Stylometric Analysis View PDFAbstract:This short paper introduces a stylometric interpretation method inspired by genome-wide association studies (GWAS). Each "gene" token's association with "phenotype" authorship is tested using logistic regression with multiple-comparison correction.
Unified Controllable and Faithful Text-to-CAD Generation with LLMs
Computer Science > Computation and Language [Submitted on 27 Mar 2026] Title:PR-CAD: Progressive Refinement for Unified Controllable and Faithful Text-to-CAD Generation with Large Language Models View PDF HTML (experimental)Abstract:The construction of CAD models has traditionally relied on labor-intensive manual operations and specialized expertise. Recent advances in large language models (LLMs) have inspired research into text-to-CAD generation.
Is Grep All You Need? How Agent Harnesses Reshape Agentic Search
Computer Science > Computation and Language [Submitted on 14 May 2026] Title:Is Grep All You Need? How Agent Harnesses Reshape Agentic Search View PDF HTML (experimental)Abstract:Recent advances in Large Language Model (LLM) agents have enabled complex agentic workflows where models autonomously retrieve information, call tools, and reason over large corpora to complete tasks on behalf of users.