new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

by AK and the research community

Apr 12

Submitted by

akhaliq

Rho-1: Not All Tokens Are What You Need

·
11 authors

Submitted by

akhaliq

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

·
17 authors

Submitted by

akhaliq

ControlNet++: Improving Conditional Controls with Efficient Consistency Feedback

·
7 authors

Submitted by

akhaliq

RecurrentGemma: Moving Past Transformers for Efficient Open Language Models

·
62 authors

Submitted by

akhaliq

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

·
11 authors

Submitted by

akhaliq

Best Practices and Lessons Learned on Synthetic Data for Language Models

·
11 authors

Submitted by

akhaliq

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

·
5 authors

Submitted by

akhaliq

LLoCO: Learning Long Contexts Offline

·
8 authors

Submitted by

akhaliq

HGRN2: Gated Linear RNNs with State Expansion

·
7 authors

Submitted by

akhaliq

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

·
6 authors

Submitted by

akhaliq

Sparse Laneformer

·
10 authors