Articles de Recherche en IA Quotidiens

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

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

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

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

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

Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models

TEDRA: Text-based Editing of Dynamic and Photoreal Actors

In-Context Imitation Learning via Next-Token Prediction

LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation

Efficient LLM Scheduling by Learning to Rank

Towards Realistic Example-based Modeling via 3D Gaussian Stitching

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

ReMamba: Equip Mamba with Effective Long-Sequence Modeling