Rationalizing Transformer Predictions via End-To-End Differentiable Self-Training
arxiv.org·2d
🧠Large Language Models (LLMs)
Towards Embodied Conversational Agents for Reducing Oral Exam Anxiety in Extended Reality
arxiv.org·2d
🧠Large Language Models (LLMs)
Diagnostic performance of deep learning for predicting glioma isocitrate dehydrogenase and 1p/19q co-deletion in MRI: a systematic review and meta-analysis
arxiv.org·1d
🧠Large Language Models (LLMs)
UniECS: Unified Multimodal E-Commerce Search Framework with Gated Cross-modal Fusion
arxiv.org·22h
🔍Retrieval-augmented generation
The Promise of Large Language Models in Digital Health: Evidence from Sentiment Analysis in Online Health Communities
arxiv.org·22h
🧠Large Language Models (LLMs)
Learning Differentiable Reachability Maps for Optimization-based Humanoid Motion Generation
arxiv.org·2d
✨Model optimizations in LLMs
SelfAdapt: Unsupervised Domain Adaptation of Cell Segmentation Models
arxiv.org·2d
🧠Large Language Models (LLMs)
Training-Free Anomaly Generation via Dual-Attention Enhancement in Diffusion Model
arxiv.org·2d
🔍Retrieval-augmented generation
Visuo-Tactile Feedback with Hand Outline Styles for Modulating Affective Roughness Perception
arxiv.org·22h
🔍Retrieval-augmented generation
Combating Homelessness Stigma with LLMs: A New Multi-Modal Dataset for Bias Detection
arxiv.org·22h
🧠Large Language Models (LLMs)
HeteroRAG: A Heterogeneous Retrieval-Augmented Generation Framework for Medical Vision Language Tasks
arxiv.org·1d
🧠Large Language Models (LLMs)
MAD: A Benchmark for Multi-Turn Audio Dialogue Fact-Checking
arxiv.org·1d
🧠Large Language Models (LLMs)
Zono-Conformal Prediction: Zonotope-Based Uncertainty Quantification for Regression and Classification Tasks
arxiv.org·2d
🔢Quantization of LLMs
Robust Convolution Neural ODEs via Contractivity-promoting regularization
arxiv.org·2d
🔢Quantization of LLMs
G-CUT3R: Guided 3D Reconstruction with Camera and Depth Prior Integration
arxiv.org·2d
📊AI Performance Profiling
CURE: Critical-Token-Guided Re-concatenation for Entropy-collapse Prevention
arxiv.org·2d
🧠Large Language Models (LLMs)
LaajMeter: A Framework for LaaJ Evaluation
arxiv.org·5d
🧠Large Language Models (LLMs)
Modeling and Detecting Company Risks from News: A Case Study in Bloomberg News
arxiv.org·2d
🧠Large Language Models (LLMs)
REFN: A Reinforcement-Learning-From-Network Framework against 1-day/n-day Exploitations
arxiv.org·5d
🔧Systems-level optimizations for LLM serving
Mitigating Modality Quantity and Quality Imbalance in Multimodal Online Federated Learning
arxiv.org·2d
⚡Real-time AI Systems