KI-Forschungspapiere Täglich

Movie Gen: A Cast of Media Foundation Models

MixEval-X: Any-to-Any Evaluations from Real-World Data Mixtures

JudgeBench: A Benchmark for Evaluating LLM-based Judges

Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens

Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation

Roadmap towards Superhuman Speech Understanding using Large Language Models

MobA: A Two-Level Agent System for Efficient Mobile Task Automation

WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines

Harnessing Webpage UIs for Text-Rich Visual Understanding

DreamVideo-2: Zero-Shot Subject-Driven Video Customization with Precise Motion Control

MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models

MoH: Multi-Head Attention as Mixture-of-Head Attention

BenTo: Benchmark Task Reduction with In-Context Transferability

PopAlign: Diversifying Contrasting Patterns for a More Comprehensive Alignment

A Comparative Study on Reasoning Patterns of OpenAI's o1 Model

A Unified View of Delta Parameter Editing in Post-Trained Large-Scale Models

FlatQuant: Flatness Matters for LLM Quantization

VidPanos: Generative Panoramic Videos from Casual Panning Videos

Do LLMs Have Political Correctness? Analyzing Ethical Biases and Jailbreak Vulnerabilities in AI Systems

Can MLLMs Understand the Deep Implication Behind Chinese Images?

Failing Forward: Improving Generative Error Correction for ASR with Synthetic Data and Retrieval Augmentation

Retrospective Learning from Interactions

Remember, Retrieve and Generate: Understanding Infinite Visual Concepts as Your Personalized Assistant

MuVi: Video-to-Music Generation with Semantic Alignment and Rhythmic Synchronization

MedMobile: A mobile-sized language model with expert-level clinical capabilities

γ-MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models

LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning

Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models

Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats

Minimum Tuning to Unlock Long Output from LLMs with High Quality Data as the Key

Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment

AERO: Softmax-Only LLMs for Efficient Private Inference

TransAgent: Transfer Vision-Language Foundation Models with Heterogeneous Agent Collaboration

SBI-RAG: Enhancing Math Word Problem Solving for Students through Schema-Based Instruction and Retrieval-Augmented Generation