AI Research Papers Daily

Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA

Leveraging Self-Attention for Input-Dependent Soft Prompting in LLMs

MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning

FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion

PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

Sentinel: SOTA model to protect against prompt injections

Truth in the Few: High-Value Data Selection for Efficient Multi-Modal Reasoning

Is Extending Modality The Right Path Towards Omni-Modality?

STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis

Audio-Aware Large Language Models as Judges for Speaking Styles

Medical World Model: Generative Simulation of Tumor Evolution for Treatment Planning

CodeContests+: High-Quality Test Case Generation for Competitive Programming

Peer-Ranked Precision: Creating a Foundational Dataset for Fine-Tuning Vision Models from DataSeeds' Annotated Imagery

Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision

Splatting Physical Scenes: End-to-End Real-to-Sim from Imperfect Robot Data

3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model

MIRIAD: Augmenting LLMs with millions of medical query-response pairs

HASHIRU: Hierarchical Agent System for Hybrid Intelligent Resource Utilization

Prefix Grouper: Efficient GRPO Training through Shared-Prefix Forward

When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration

When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding

GuideX: Guided Synthetic Data Generation for Zero-Shot Information Extraction

AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenance

Sparsified State-Space Models are Efficient Highway Networks