Neural Tangent Knowledge Distillation for Optical Convolutional Networks
arxiv.org·21h
🔢Quantization of LLMs
Selective Contrastive Learning for Weakly Supervised Affordance Grounding
arxiv.org·1d
🔍Retrieval-augmented generation
CATP: Contextually Adaptive Token Pruning for Efficient and Enhanced Multimodal In-Context Learning
arxiv.org·1d
🧠Large Language Models (LLMs)
Artificial Intelligence Software Structured to Simulate Human Working Memory, Mental Imagery, and Mental Continuity
arxiv.org·21h
🔍Retrieval-augmented generation
Hierarchical Verification of Speculative Beams for Accelerating LLM Inference
arxiv.org·6d
🧠Large Language Models (LLMs)
CognitiveArm: Enabling Real-Time EEG-Controlled Prosthetic Arm Using Embodied Machine Learning
arxiv.org·1d
🧠Large Language Models (LLMs)
Intersectoral Knowledge in AI and Urban Studies: A Framework for Transdisciplinary Research
arxiv.org·1d
📊AI Performance Profiling
From Product Hilbert Spaces to the Generalized Koopman Operator and the Nonlinear Fundamental Lemma
arxiv.org·1d
🔢Quantization of LLMs
Can Large Language Models Generate Effective Datasets for Emotion Recognition in Conversations?
arxiv.org·5d
🧠Large Language Models (LLMs)
EventRR: Event Referential Reasoning for Referring Video Object Segmentation
arxiv.org·1d
🔍Retrieval-augmented generation
Propagation Tree Is Not Deep: Adaptive Graph Contrastive Learning Approach for Rumor Detection
arxiv.org·1d
🧠Large Language Models (LLMs)
Incident Response Planning Using a Lightweight Large Language Model with Reduced Hallucination
arxiv.org·5d
🔧Systems-level optimizations for LLM serving
SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs
arxiv.org·2d
💬Prompt optimizations for LLM serving
A Parametric Bi-Directional Curvature-Based Framework for Image Artifact Classification and Quantification
arxiv.org·21h
🔢Quantization of LLMs
Shaping a Profession, Building a Community: A Practitioner-Led Investigation of Public Interest Technologists in Civil Society
arxiv.org·1d
🏋️LLM training frameworks
Emoji Reactions on Telegram Often Reflect Social Approval Over Emotional Resonance
arxiv.org·2d
🧠Large Language Models (LLMs)
Onsager Principle-Based Domain Embedding for Thermodynamically Consistent Cahn-Hilliard Model in Arbitrary Domain
arxiv.org·1d
🔢Quantization of LLMs
When and how can inexact generative models still sample from the data manifold?
arxiv.org·1d
🔍Retrieval-augmented generation
"Draw me a curator" Examining the visual stereotyping of a cultural services profession by generative AI
arxiv.org·1d
🔍Retrieval-augmented generation
Silicon Minds versus Human Hearts: The Wisdom of Crowds Beats the Wisdom of AI in Emotion Recognition
arxiv.org·21h
📊AI Performance Profiling