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 30

Submitted by

akhaliq

MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series

·
45 authors

Submitted by

akhaliq

Self-Exploring Language Models: Active Preference Elicitation for Online Alignment

·
7 authors

1

Submitted by

akhaliq

T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback

·
7 authors

Submitted by

akhaliq

LLMs achieve adult human performance on higher-order theory of mind tasks

·
10 authors

Submitted by

akhaliq

Nearest Neighbor Speculative Decoding for LLM Generation and Attribution

·
7 authors

Submitted by

akhaliq

Offline Regularised Reinforcement Learning for Large Language Models Alignment

·
18 authors

Submitted by

akhaliq

EasyAnimate: A High-Performance Long Video Generation Method based on Transformer Architecture

·
8 authors

1

Submitted by

akhaliq

Zipper: A Multi-Tower Decoder Architecture for Fusing Modalities

·
4 authors

Submitted by

akhaliq

NPGA: Neural Parametric Gaussian Avatars

·
5 authors

Submitted by

akhaliq

Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF

·
9 authors

Submitted by

akhaliq

SoundCTM: Uniting Score-based and Consistency Models for Text-to-Sound Generation

·
7 authors

Submitted by

akhaliq

Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication

·
8 authors