AI Research Papers Daily

Rho-1: Not All Tokens Are What You Need

OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback

RecurrentGemma: Moving Past Transformers for Efficient Open Language Models

Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models

Best Practices and Lessons Learned on Synthetic Data for Language Models

LLoCO: Learning Long Contexts Offline

WILBUR: Adaptive In-Context Learning for Robust and Accurate Web Agents

HGRN2: Gated Linear RNNs with State Expansion

Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models

Sparse Laneformer