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

Oct 23

Submitted by

akhaliq

Contrastive Prefence Learning: Learning from Human Feedback without RL

·
7 authors

Submitted by

akhaliq

Let's Synthesize Step by Step: Iterative Dataset Synthesis with Large Language Models by Extrapolating Errors from Small Models

·
3 authors

Submitted by

akhaliq

DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics

·
4 authors

Submitted by

akhaliq

SALMONN: Towards Generic Hearing Abilities for Large Language Models

·
9 authors

Submitted by

akhaliq

Democratizing Reasoning Ability: Tailored Learning from Large Language Model

·
11 authors

Submitted by

akhaliq

ToolChain: Efficient Action Space Navigation in Large Language Models with A Search

·
8 authors

Submitted by

akhaliq

DreamSpace: Dreaming Your Room Space with Text-Driven Panoramic Texture Propagation

·
7 authors

Submitted by

akhaliq

Teaching Language Models to Self-Improve through Interactive Demonstrations

·
5 authors

Submitted by

akhaliq

Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models

DM2-ND

University of Notre Dame DM2 Lab

Submitted by

akhaliq

Tuna: Instruction Tuning using Feedback from Large Language Models

·
5 authors

Submitted by

akhaliq

Creative Robot Tool Use with Large Language Models

·
10 authors

Submitted by

akhaliq

SILC: Improving Vision Language Pretraining with Self-Distillation

·
6 authors

Submitted by

akhaliq

H2O Open Ecosystem for State-of-the-art Large Language Models

·
7 authors

Submitted by

akhaliq

Towards Understanding Sycophancy in Language Models

·
19 authors

Submitted by

akhaliq

ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection

·
4 authors