AI Onderzoekspapers Dagelijks

Typhoon T1: An Open Thai Reasoning Model

CoSER: Coordinating LLM-Based Persona Simulation of Established Roles

Can this Model Also Recognize Dogs? Zero-Shot Model Search from Weights

SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models

mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data

Latent Radiance Fields with 3D-aware 2D Representations

An Open Recipe: Adapting Language-Specific LLMs to a Reasoning Model in One Day via Model Merging

InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU

DexTrack: Towards Generalizable Neural Tracking Control for Dexterous Manipulation from Human References

TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models

Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation

Exploring the Potential of Encoder-free Architectures in 3D LMMs

EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents

Mathematical Reasoning in Large Language Models: Assessing Logical and Arithmetic Errors across Wide Numerical Ranges

MME-CoT: Benchmarking Chain-of-Thought in Large Multimodal Models for Reasoning Quality, Robustness, and Efficiency

3CAD: A Large-Scale Real-World 3C Product Dataset for Unsupervised Anomaly

CoT-Valve: Length-Compressible Chain-of-Thought Tuning

Logical Reasoning in Large Language Models: A Survey

The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding

VFX Creator: Animated Visual Effect Generation with Controllable Diffusion Transformer

SQuARE: Sequential Question Answering Reasoning Engine for Enhanced Chain-of-Thought in Large Language Models