A Multimodal Framework for Understanding Collaborative Design Processes
arxiv.org·4h
🔍Retrieval-augmented generation
Uncertainty-quantified Rollout Policy Adaptation for Unlabelled Cross-domain Temporal Grounding
arxiv.org·4h
🔧Systems-level optimizations for LLM serving
NVSpeech: An Integrated and Scalable Pipeline for Human-Like Speech Modeling with Paralinguistic Vocalizations
arxiv.org·4d
🔍Retrieval-augmented generation
Prediction of Survival Outcomes under Clinical Presence Shift: A Joint Neural Network Architecture
arxiv.org·3d
📊AI Performance Profiling
MAP: Mitigating Hallucinations in Large Vision-Language Models with Map-Level Attention Processing
arxiv.org·6d
🔢Quantization of LLMs
VS-LLM: Visual-Semantic Depression Assessment based on LLM for Drawing Projection Test
arxiv.org·3d
🔍Retrieval-augmented generation
SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs
arxiv.org·4h
💬Prompt optimizations for LLM serving
ActivityDiff: A diffusion model with Positive and Negative Activity Guidance for De Novo Drug Design
arxiv.org·4h
🔍Retrieval-augmented generation
Kronos: A Foundation Model for the Language of Financial Markets
arxiv.org·5d
✨Model optimizations in LLMs
Minimal Convolutional RNNs Accelerate Spatiotemporal Learning
arxiv.org·5d
⚡Real-time AI Systems
Hide and Seek with LLMs: An Adversarial Game for Sneaky Error Generation and Self-Improving Diagnosis
arxiv.org·5d
✨Model optimizations in LLMs
Interpretable Rheumatoid Arthritis Scoring via Anatomy-aware Multiple Instance Learning
arxiv.org·4h
📊AI Performance Profiling
FVGen: Accelerating Novel-View Synthesis with Adversarial Video Diffusion Distillation
arxiv.org·4h
🔍Retrieval-augmented generation
An Explainable Machine Learning Framework for Railway Predictive Maintenance using Data Streams from the Metro Operator of Portugal
arxiv.org·3d
⚙️AI Infrastructure Automation
Getting out of the Big-Muddy: Escalation of Commitment in LLMs
arxiv.org·6d
🤖Agents using LLMs
Data Overdose? Time for a Quadruple Shot: Knowledge Graph Construction using Enhanced Triple Extraction
arxiv.org·5d
🔍Retrieval-augmented generation
ANPrompt: Anti-noise Prompt Tuning for Vision-Language Models
arxiv.org·4d
💬Prompt optimizations for LLM serving
Dual Prompt Learning for Adapting Vision-Language Models to Downstream Image-Text Retrieval
arxiv.org·4d
🔍Retrieval-augmented generation
Understanding the Embedding Models on Hyper-relational Knowledge Graph
arxiv.org·5d
✨Model optimizations in LLMs
Latent Preference Bandits
arxiv.org·3d
✨Model optimizations in LLMs