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

Aug 29

Submitted by

akhaliq

Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

·
15 authors

Submitted by

dongguosheng

BaichuanSEED: Sharing the Potential of ExtensivE Data Collection and Deduplication by Introducing a Competitive Large Language Model Baseline

·
20 authors

Submitted by

akhaliq

Dolphin: Long Context as a New Modality for Energy-Efficient On-Device Language Models

·
4 authors

Submitted by

akhaliq

LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation

·
16 authors

Submitted by

Viol2000

Efficient LLM Scheduling by Learning to Rank

·
6 authors

Submitted by

yolay

Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models

·
12 authors

Submitted by

SYZhang0805

Distribution Backtracking Builds A Faster Convergence Trajectory for One-step Diffusion Distillation

·
9 authors

Submitted by

Uri-ka

Knowledge Navigator: LLM-guided Browsing Framework for Exploratory Search in Scientific Literature

·
3 authors

Submitted by

osanseviero

Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts

·
5 authors

Submitted by

akhaliq

ReMamba: Equip Mamba with Effective Long-Sequence Modeling

·
7 authors

Submitted by

mlfu7

In-Context Imitation Learning via Next-Token Prediction

·
8 authors

Submitted by

akhaliq

Towards Realistic Example-based Modeling via 3D Gaussian Stitching

·
6 authors

Submitted by

akhaliq

TEDRA: Text-based Editing of Dynamic and Photoreal Actors

·
6 authors