Coherent Multimodal Reasoning with Iterative Self-Evaluation for Vision-Language Models
arxiv.org·1d
🧠Large Language Models (LLMs)
Improve Retinal Artery/Vein Classification via Channel Couplin
arxiv.org·7h
🔢Quantization of LLMs
AQUAH: Automatic Quantification and Unified Agent in Hydrology
arxiv.org·1d
⚙️AI Infrastructure Automation
MalFlows: Context-aware Fusion of Heterogeneous Flow Semantics for Android Malware Detection
arxiv.org·1d
📊AI Performance Profiling
Reinforcement Learning for Target Zone Blood Glucose Control
arxiv.org·7h
🤖Agents using LLMs
Kronos: A Foundation Model for the Language of Financial Markets
arxiv.org·1d
🧠Large Language Models (LLMs)
Minimal Convolutional RNNs Accelerate Spatiotemporal Learning
arxiv.org·1d
🧠Large Language Models (LLMs)
Understanding the Embedding Models on Hyper-relational Knowledge Graph
arxiv.org·1d
🧠Large Language Models (LLMs)
Semi-Supervised Anomaly Detection in Brain MRI Using a Domain-Agnostic Deep Reinforcement Learning Approach
arxiv.org·2d
✨Model optimizations in LLMs
Veli: Unsupervised Method and Unified Benchmark for Low-Cost Air Quality Sensor Correction
arxiv.org·1d
🧠Large Language Models (LLMs)
Transferring Expert Cognitive Models to Social Robots via Agentic Concept Bottleneck Models
arxiv.org·7h
🧠Large Language Models (LLMs)
BDFirewall: Towards Effective and Expeditiously Black-Box Backdoor Defense in MLaaS
arxiv.org·1d
⚙️AI Infrastructure Automation
Key-Augmented Neural Triggers for Knowledge Sharing
arxiv.org·1d
🧠Large Language Models (LLMs)
Cognitive Loop via In-Situ Optimization: Self-Adaptive Reasoning for Science
arxiv.org·1d
⚙️AI Infrastructure Automation
Thinking With Videos: Multimodal Tool-Augmented Reinforcement Learning for Long Video Reasoning
arxiv.org·7h
🧠Large Language Models (LLMs)
UrBLiMP: A Benchmark for Evaluating the Linguistic Competence of Large Language Models in Urdu
arxiv.org·2d
🧠Large Language Models (LLMs)
AoI-Aware Resource Allocation with Deep Reinforcement Learning for HAPS-V2X Networks
arxiv.org·3d
⚙️AI Infrastructure Automation
Learning an Efficient Multi-Turn Dialogue Evaluator from Multiple Judges
arxiv.org·3d
🧠Large Language Models (LLMs)
Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools
arxiv.org·2d
🤖Agents using LLMs
LECTOR: LLM-Enhanced Concept-based Test-Oriented Repetition for Adaptive Spaced Learning
arxiv.org·1d
🧠Large Language Models (LLMs)