An Experimental Reservoir-Augmented Foundation Model: 6G O-RAN Case Study
arxiv.org·5d
🔧Systems-level optimizations for LLM serving
Audio-Thinker: Guiding Audio Language Model When and How to Think via Reinforcement Learning
arxiv.org·5d
🧠Large Language Models (LLMs)
Efficient Edge LLMs Deployment via HessianAware Quantization and CPU GPU Collaborative
arxiv.org·5d
🔧Systems-level optimizations for LLM serving
How Does a Virtual Agent Decide Where to Look? - Symbolic Cognitive Reasoning for Embodied Head Rotation
arxiv.org·4d
🧠Large Language Models (LLMs)
READER: Retrieval-Assisted Drafter for Efficient LLM Inference
arxiv.org·4d
🧠Large Language Models (LLMs)
Dynamic Uncertainty-aware Multimodal Fusion for Outdoor Health Monitoring
arxiv.org·4d
🧠Large Language Models (LLMs)
Towards Effective MLLM Jailbreaking Through Balanced On-Topicness and OOD-Intensity
arxiv.org·3d
🧠Large Language Models (LLMs)
MedPatch: Confidence-Guided Multi-Stage Fusion for Multimodal Clinical Data
arxiv.org·3d
🔍Retrieval-augmented generation
Binary Decision Process in Pre-Evacuation Behavior
arxiv.org·4d
✨Model optimizations in LLMs
Micro-Health Interventions: Exploring Design Strategies for 1-Minute Interventions as a Gateway to Healthy Habits
arxiv.org·3d
💬Prompt optimizations for LLM serving
LLM Serving Optimization with Variable Prefill and Decode Lengths
arxiv.org·6d
🔧Systems-level optimizations for LLM serving
A Markov Decision Process Framework for Early Maneuver Decisions in Satellite Collision Avoidance
arxiv.org·6d
✨Model optimizations in LLMs
Gradient- and Newton-Based Unit Vector Extremum Seeking Control
arxiv.org·4d
✨Model optimizations in LLMs
Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent
arxiv.org·5d
📊AI Performance Profiling
BiasGym: Fantastic Biases and How to Find (and Remove) Them
arxiv.org·4d
🧠Large Language Models (LLMs)
Integrating Clinical Knowledge Graphs and Gradient-Based Neural Systems for Enhanced Melanoma Diagnosis via the 7-Point Checklist
arxiv.org·3d
⚙️AI Infrastructure Automation
Robust Reinforcement Learning over Wireless Networks with Homomorphic State Representations
arxiv.org·5d
🤖Agents using LLMs
Shape Completion and Real-Time Visualization in Robotic Ultrasound Spine Acquisitions
arxiv.org·4d
🔍Retrieval-augmented generation
Mediator-Guided Multi-Agent Collaboration among Open-Source Models for Medical Decision-Making
arxiv.org·6d
🤖Agents using LLMs
Integrated Communication and Remote Sensing in LEO Satellite Systems: Protocol, Architecture and Prototype
arxiv.org·2d
🔧Systems-level optimizations for LLM serving