Aug 14, 2026
vToken: Token-Level Virtualization for Reclaimable KV Caches
vToken: Token-Level Virtualization for Reclaimable KV Caches introduces a virtualization layer designed to solve the memory fragmentation bottleneck in large...
Explore Franklin AI
AI Research Papers
Understand new AI research with readable explanations and links to the original papers.
Aug 14, 2026
Rules or Character? Scaling Laws for AI Safety Design
Rules or Character? Scaling Laws for AI Safety Design explores how AI developers should balance two primary safety strategies: "character shaping" (training-...
Aug 14, 2026
Who Speaks Matters: Authority-Aware Multi-View RAG over Italian Parliamentary Proceedings
Who Speaks Matters: Authority-Aware Multi-View RAG over Italian Parliamentary Proceedings introduces ParliamentRAG, a system designed to improve how users ac...
Aug 14, 2026
Robust Dempster-Shafer Evidence Fusion with Chaos-Conflict Measurement and Historical-Experience Weighting
This paper introduces a unified evidence reasoning framework designed to improve how multi-source information is combined under Dempster-Shafer theory (DST)....
Aug 14, 2026
Rethinking Normalization Placement for LLMs: Post-Norm under Curriculum Depth Growing
Rethinking Normalization Placement for LLMs: Post-Norm under Curriculum Depth Growing investigates whether the standard preference for "pre-norm" in Transfor...
Aug 14, 2026
Jointly Predicting Courses and Grades Using a Transformer-Based Model
Jointly Predicting Courses and Grades Using a Transformer-Based Model introduces TRACE (TRansformer for Academic Course-grade Estimation), a model designed t...
Aug 14, 2026
Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development
Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development investigates the performance of autonomous AI agents in c...
Aug 14, 2026
QuoteBench: How Matched Scores Can Hide Command-Path Failures
QuoteBench: How Matched Scores Can Hide Command-Path Failures investigates why current benchmarks for LLM coding agents often fail to distinguish between a m...
Aug 14, 2026
SPADE: Speculative Decoding for Precise and Low Cost Distributed Edge Cloud Inference
SPADE is a distributed inference framework designed to reduce the computational costs and latency of running Large Language Models (LLMs) by splitting the wo...
Aug 14, 2026
SkillShapley: Boundary-Adaptive Shapley Valuation for Skill Step Attribution in LLM Agents
SkillShapley is a framework designed to quantify the contribution of individual steps within an LLM agent’s procedural skill.
Good to know
How do I use these AI research explainers?
Start with the overview to understand the paper’s main idea, then follow its original paper link for the methods, results and limitations.
Can I suggest a research paper?
Use Submit Research to send the original paper URL and explain why it is useful. An editor reviews the suggestion before publication.