new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

byAK and the research community

May 27

Submitted by

akhaliq

Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models

·
4 authors

6

Submitted by

akhaliq

ConvLLaVA: Hierarchical Backbones as Visual Encoder for Large Multimodal Models

·
9 authors

7

Submitted by

akhaliq

Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization

·
4 authors

Submitted by

akhaliq

Aya 23: Open Weight Releases to Further Multilingual Progress

·
17 authors

Submitted by

akhaliq

Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training

·
8 authors

Submitted by

akhaliq

AutoCoder: Enhancing Code Large Language Model with AIEV-Instruct

·
3 authors

9

Submitted by

akhaliq

The Road Less Scheduled

·
7 authors

7

Submitted by

akhaliq

CraftsMan: High-fidelity Mesh Generation with 3D Native Generation and Interactive Geometry Refiner

·
7 authors

Submitted by

akhaliq

Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach

·
13 authors

Submitted by

akhaliq

Denoising LM: Pushing the Limits of Error Correction Models for Speech Recognition

·
6 authors

Submitted by

akhaliq

iVideoGPT: Interactive VideoGPTs are Scalable World Models

·
7 authors

4

Submitted by

akhaliq

Data Mixing Made Efficient: A Bivariate Scaling Law for Language Model Pretraining

·
5 authors

Submitted by

akhaliq

HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting

·
7 authors