KI-Forschungspapiere Täglich

Seed-Music: A Unified Framework for High Quality and Controlled Music Generation

Kolmogorov-Arnold Transformer

RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval

jina-embeddings-v3: Multilingual Embeddings With Task LoRA

One missing piece in Vision and Language: A Survey on Comics Understanding

Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models

On the Diagram of Thought

ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds

Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types

Policy Filtration in RLHF to Fine-Tune LLM for Code Generation

Breaking reCAPTCHAv2

AudioBERT: Audio Knowledge Augmented Language Model

Towards Predicting Temporal Changes in a Patient's Chest X-ray Images based on Electronic Health Records

beeFormer: Bridging the Gap Between Semantic and Interaction Similarity in Recommender Systems

LLM-Powered Grapheme-to-Phoneme Conversion: Benchmark and Case Study