Thought Branches: Interpreting LLM Reasoning Requires Resampling
arxiv.org·1d
🧠Large Language Models (LLMs)
Flag this post
Single-agent Reinforcement Learning Model for Regional Adaptive Traffic Signal Control
arxiv.org·23h
⚡Real-time AI Systems
Flag this post
A generative adversarial network optimization method for damage detection and digital twinning by deep AI fault learning: Z24 Bridge structural health monitorin...
arxiv.org·23h
⚙️AI Infrastructure Automation
Flag this post
What a diff makes: automating code migration with large language models
arxiv.org·23h
🧠Large Language Models (LLMs)
Flag this post
Incremental Selection of Most-Filtering Conjectures and Proofs of the Selected Conjectures
arxiv.org·23h
💬Prompt optimizations for LLM serving
Flag this post
Urban-MAS: Human-Centered Urban Prediction with LLM-Based Multi-Agent System
arxiv.org·23h
🧠Large Language Models (LLMs)
Flag this post
Region-Aware Reconstruction Strategy for Pre-training fMRI Foundation Model
arxiv.org·23h
🔍Retrieval-augmented generation
Flag this post
Hydra: Dual Exponentiated Memory for Multivariate Time Series Analysis
arxiv.org·23h
📊AI Performance Profiling
Flag this post
Hybrid Retrieval-Augmented Generation Agent for Trustworthy Legal Question Answering in Judicial Forensics
arxiv.org·23h
🔍Retrieval-augmented generation
Flag this post
Robust Single-Agent Reinforcement Learning for Regional Traffic Signal Control Under Demand Fluctuations
arxiv.org·23h
⚙️AI Infrastructure Automation
Flag this post
Variational Data-Consistent Assimilation
arxiv.org·23h
🔢Quantization of LLMs
Flag this post
OpenSIR: Open-Ended Self-Improving Reasoner
arxiv.org·23h
💬Prompt optimizations for LLM serving
Flag this post
Confounding Factors in Relating Model Performance to Morphology
arxiv.org·23h
🧠Large Language Models (LLMs)
Flag this post
ShadowLogic: Backdoors in Any Whitebox LLM
arxiv.org·23h
🔧Systems-level optimizations for LLM serving
Flag this post
Sherlock: Reliable and Efficient Agentic Workflow Execution
arxiv.org·23h
⚙️AI Infrastructure Automation
Flag this post
ParlaSpeech 3.0: Richly Annotated Spoken Parliamentary Corpora of Croatian, Czech, Polish, and Serbian
arxiv.org·23h
🧠Large Language Models (LLMs)
Flag this post
DocPrism: Local Categorization and External Filtering to Identify Relevant Code-Documentation Inconsistencies
arxiv.org·23h
💬Prompt optimizations for LLM serving
Flag this post
DCcluster-Opt: Benchmarking Dynamic Multi-Objective Optimization for Geo-Distributed Data Center Workloads
arxiv.org·23h
🔧Systems-level optimizations for LLM serving
Flag this post
Application of predictive machine learning in pen & paper RPG game design
arxiv.org·23h
📊AI Performance Profiling
Flag this post
Tackling the Kidnapped Robot Problem via Sparse Feasible Hypothesis Sampling and Reliable Batched Multi-Stage Inference
arxiv.org·23h
⚡Real-time AI Systems
Flag this post