LLMs
Latest breakthroughs in Large Language Models
Articles
Large Models for Battery Prognostics and Health Management: A⭐9
A review of large models for battery prognostics and health management, covering key challenges, methods, and a future roadmap.
Standalone LLM vs. Pre-Specified Agentic Pipeline for Explaining⭐9
Agentic pipelines reduce outcome leakage and improve clinical grounding for ICU mortality explanations, though standalone LLMs better align with SHAP attributio...
TreeGraft: Adaptive Multi-Drafter Grafting for Tree-Based⭐10
TreeGraft enables adaptive multi-drafter speculative decoding, boosting LLM inference speed by 15.1% across benchmarks.
EduRiskX: A Neuro-Symbolic Framework with F-Logic Reasoning for⭐9
EduRiskX combines temporal Transformers with F-Logic reasoning to predict academic risk early, boosting detection rates and interpretability in online learning.
VLM-Based Automatic Multi-Granularity Graph Representation of⭐7
VLM-based pipeline automatically converts building floorplans into multi-granularity graph representations, achieving 92% node match accuracy for design retriev...
Taming Visual Neglect: A Variational Information Bottleneck⭐9
New framework reveals when visual context helps or hurts multimodal in-context learning, with adaptive attention boosting accuracy by 4.7%.
RENDER: Controlling Reader-Facing Evidence in LLM Memory Evaluation⭐8
Evaluating LLM memory with RENDER: how reader-facing formats—summaries, typed records, raw text—impact accuracy, showing up to 72.6-point variance across models...
Distinguishing Revision and Delayed Elaboration in Incremental⭐9
Distinguishing revision from delayed elaboration in incremental narrative interpretation, highlighting their structural differences and roles in processing.
KVBoost: Deviation-Guided Chunk-Level KV Cache Reuse for⭐8
KVBoost enables chunk-level KV cache reuse for LLMs, cutting time-to-first-token by 4.49x with 16% gains over prefix caching.
SDAD: Spec-Driven Agentic Development for the AI-Native Software⭐7
This paper formalizes SDAD, a spec-driven model for AI-native software development, examining its four stages, governance metrics, and impact on the SDLC.