KI-Forschungspapiere Täglich

LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs

Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges

Towards Retrieval Augmented Generation over Large Video Libraries

Complexity of Symbolic Representation in Working Memory of Transformer Correlates with the Complexity of a Task

MantisScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation

Evaluating RAG-Fusion with RAGElo: an Automated Elo-based Framework

Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models

EvTexture: Event-driven Texture Enhancement for Video Super-Resolution

Reward Steering with Evolutionary Heuristics for Decoding-time Alignment

Jailbreaking as a Reward Misspecification Problem

Two Giraffes in a Dirt Field: Using Game Play to Investigate Situation Modelling in Large Multimodal Models

Cognitive Map for Language Models: Optimal Planning via Verbally Representing the World Model

4K4DGen: Panoramic 4D Generation at 4K Resolution

Data Contamination Can Cross Language Barriers

DELLA-Merging: Reducing Interference in Model Merging through Magnitude-Based Sampling

A Tale of Trust and Accuracy: Base vs. Instruct LLMs in RAG Systems

Learning Molecular Representation in a Cell

Ruby Teaming: Improving Quality Diversity Search with Memory for Automated Red Teaming

NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking

ICAL: Continual Learning of Multimodal Agents by Transforming Trajectories into Actionable Insights

Style-NeRF2NeRF: 3D Style Transfer From Style-Aligned Multi-View Images

RE-AdaptIR: Improving Information Retrieval through Reverse Engineered Adaptation

Multimodal Structured Generation: CVPR's 2nd MMFM Challenge Technical Report

ToVo: Toxicity Taxonomy via Voting

How Well Do LLMs Represent Values Across Cultures? Empirical Analysis of LLM Responses Based on Hofstede Cultural Dimensions

Low-Resource Machine Translation through the Lens of Personalized Federated Learning