FindIt: A Format-Informed Visual Detection Benchmark for Generalist Multimodal LLMs
Research
Research News
New papers, breakthroughs and academic AI research
Text-to-Image Models Need Less from Text Encoders Than You Think
Research
RefGC-SR$^2$: Reference-guided Super-Resolution and Refinement of AI Generated Content
Research
SAE++: Cascaded Sparse Autoencoders Learn Multi-Level Visual Concepts in Multimodal LLMs
Research
SalArt-VQA: Diagnosing Whether VLMs Understand Salient Artifacts in Generated Images
Research
On the Computational Tractability of Robust Bandits
Research
When Can World Models Recover Physical Laws?
Research
Online Neural Space Time Memory for Dynamic Novel View Synthesis
Research
RIGOR: Rig-Informed Geometry for Omnidirectional Reconstruction
Research
HARMONY: Hierarchical Agentic Reasoning for MONocular Image-to-Scene Synthesis
Research
UnitBoost: Managing Compound LLM Systems with a Merge Operator, Not a Model
Research
Reinforcement Learning with Conformal Action Sets: An Application to Sequential Recommendation
Research