newsIEEE Spectrum AITrust 88 · LabPublished 14d agoLive · 5d ago
IEEE Rolls Out Large Language Models Virtual Training Course
Large language models have moved out of the research lab and into engineers’ daily workflow. LLMs serve as reasoning engines that can orchestrate complex tasks including identifying vulnerabilities
Covers
Covers (incoming)
paperLMs as Task-Specific Knowledge Bases: An Interpretability Analysisrepopisanuw/ltmspaperSingle and Multi Truth Data Fusion using Large Language ModelspaperMechanism-Driven Monitors for Preemptive Detection of LLM Training InstabilitypaperFrom Tokens to States: LLMs as a Special Case of World Models and the Continuous Path BeyondpaperHierarchical Experimentalist AgentspaperDynamo: Dynamic Skill-Tool Evolution for Vision-Language AgentspaperLinguistic Firewall: Geometry as Defense in Multi-Agent Systems RoutingpaperWords Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability DetectionpaperCalibration, Not Compilation: Detecting and Repairing Misspecified Probabilistic Programs Written by Language ModelspaperLearning from Failure: Inference-Time Self-Improvement for Computer-Use AgentspaperWhen the Database Fails: Prompting LLM Dialogue Agents for Safe Recovery in Task-Oriented DialoguepaperTeam MKC at CLPsych 2026: Capturing and Characterizing Mental Health Changes through Social Media Timeline DynamicspaperAutoTrainess: Teaching Language Models to Improve Language Models AutonomouslypaperAutomating Cause-Effect Specification with Knowledge Graphs and Large Language ModelspaperA Tutorial on Autonomous Fault-Tolerant Control Using Knowledge-Grounded LLM AgentspaperA Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open ProblemspaperSurrogate Fidelity: When Can Open LLMs Explain Closed Ones?paperSelf-Study Reconsidered: The Hidden Fragility of Learning from Self-Generated QApaperWhen LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing ErrorspaperGenerative Skill Composition for LLM AgentspaperThe Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training MethodologypaperMessage Passing Enables Efficient ReasoningpaperAgentic generation of verifiable rules for deterministic, self-expanding reaction classificationpaperUnderstanding Large Language ModelspaperConversable Complexity: Agentic LLM Collectives as Interpretable SubstratespaperAutoMem: Automated Learning of Memory as a Cognitive SkillpaperSkills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply Chainsrepoedefbo1/a-hirepoolonok69/LLM_Notebooksrepoaallan/verarepovllm-project/vllmrepovitali87/code-graph-ragrepoiree-org/ireerepoAI-Hypercomputer/maxtextrepochrisliu298/awesome-llm-unlearningrepojordanhubbard/nanolangrepohuhusmang/Awesome-LLMs-for-Vulnerability-DetectionpaperChallenges and Recommendations for LLMs-as-a-Judge in Multilingual Settings and Low-Resource LanguagespaperGrounded autonomous research: a fault-tolerant LLM pipeline from corpus to manuscript in frontier computational physicspaperDecompRL: Solving Harder Problems by Learning Modular Code GenerationpaperFast Multi-dimensional Refusal Subspaces via RFM-AGOPpaperNeuron-Aware Data Selection for Annotation-Free LLM Self-DistillationpaperDemoPSD: Disagreement-Modulated Policy Self-DistillationpaperOnline Safety Monitoring for LLMsrepoyegor256/promptrepolabring/FastGPTrepoKerberosClaw/kc_ai_skillsrepoModelTC/LightLLMrepozjunlp/EasyEditrepo11divyansh/OxyJen
Related across the graph
repochrisliu298/awesome-llm-unlearningpaperTeam MKC at CLPsych 2026: Capturing and Characterizing Mental Health Changes through Social Media Timeline DynamicspaperDynamo: Dynamic Skill-Tool Evolution for Vision-Language Agentsrepo11divyansh/OxyJenpaperWords Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability DetectionpaperLMs as Task-Specific Knowledge Bases: An Interpretability AnalysispaperDemoPSD: Disagreement-Modulated Policy Self-DistillationpaperFast Multi-dimensional Refusal Subspaces via RFM-AGOPpaperSelf-Study Reconsidered: The Hidden Fragility of Learning from Self-Generated QApaperA Tutorial on Autonomous Fault-Tolerant Control Using Knowledge-Grounded LLM Agentsrepovllm-project/vllmpaperDecompRL: Solving Harder Problems by Learning Modular Code Generationrepoolonok69/LLM_Notebooksrepoiree-org/ireerepoengineering87/llm-atlaspaperSingle and Multi Truth Data Fusion using Large Language ModelspaperLinguistic Firewall: Geometry as Defense in Multi-Agent Systems RoutingpaperGenerative Skill Composition for LLM AgentspaperMessage Passing Enables Efficient Reasoningrepovitali87/code-graph-ragpaperMechanism-Driven Monitors for Preemptive Detection of LLM Training InstabilitypaperAutoMem: Automated Learning of Memory as a Cognitive Skillrepoedefbo1/a-hipaperChallenges and Recommendations for LLMs-as-a-Judge in Multilingual Settings and Low-Resource Languagesrepopisanuw/ltmspaperOnline Safety Monitoring for LLMsrepozjunlp/EasyEditpaperLearning from Failure: Inference-Time Self-Improvement for Computer-Use AgentspaperSurrogate Fidelity: When Can Open LLMs Explain Closed Ones?companyLattice Labsrepohuhusmang/Awesome-LLMs-for-Vulnerability-DetectionpaperUnderstanding Large Language ModelspaperGrounded autonomous research: a fault-tolerant LLM pipeline from corpus to manuscript in frontier computational physicspaperConversable Complexity: Agentic LLM Collectives as Interpretable SubstratesrepoModelTC/LightLLMrepoyegor256/promptpaperHierarchical Experimentalist AgentspaperAutoTrainess: Teaching Language Models to Improve Language Models AutonomouslypaperNeuron-Aware Data Selection for Annotation-Free LLM Self-DistillationpaperSkills Are Not Islands: Measuring Dependency and Risk in Agent Skill Supply ChainspaperThe Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training MethodologypaperAutomating Cause-Effect Specification with Knowledge Graphs and Large Language ModelspaperNuclearQAv2: A Structured Benchmark for Evaluating Domain-Science Competence in Large Language Modelsrepojordanhubbard/nanolangpaperCalibration, Not Compilation: Detecting and Repairing Misspecified Probabilistic Programs Written by Language ModelspaperWhen LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing ErrorspaperA Lifecycle and Application-Stack Survey of Large Language Model Vulnerabilities: Attacks, Risks, Defenses, and Open ProblemsrepoAI-Hypercomputer/maxtextpaperFrom Tokens to States: LLMs as a Special Case of World Models and the Continuous Path BeyondpaperWhen the Database Fails: Prompting LLM Dialogue Agents for Safe Recovery in Task-Oriented Dialoguerepolabring/FastGPTrepoagent-toolspaperAgentic generation of verifiable rules for deterministic, self-expanding reaction classificationrepoKerberosClaw/kc_ai_skillsrepovlm-starterrepoaallan/vera