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 14

Submitted by

MiniMax-AI

MiniMax-Speech: Intrinsic Zero-Shot Text-to-Speech with a Learnable Speaker Encoder

·
20 authors

3

Submitted by

ZacharyNovack

Fast Text-to-Audio Generation with Adversarial Post-Training

·
11 authors

Submitted by

Junjie-Ye

A Multi-Dimensional Constraint Framework for Evaluating and Improving Instruction Following in Large Language Models

·
15 authors

2

Submitted by

akhaliq

Aya Vision: Advancing the Frontier of Multilingual Multimodality

·
25 authors

Submitted by

nickatomlin

Measuring General Intelligence with Generated Games

·
5 authors

2

Submitted by

akhaliq

AM-Thinking-v1: Advancing the Frontier of Reasoning at 32B Scale

·
8 authors

Submitted by

jinghan23

Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging

·
8 authors

Submitted by

DarshanDeshpande

TRAIL: Trace Reasoning and Agentic Issue Localization

·
6 authors

Submitted by

Omartificial-Intelligence-Space

Advancing Arabic Reverse Dictionary Systems: A Transformer-Based Approach with Dataset Construction Guidelines

·
7 authors

Submitted by

EdBianchi

SkillFormer: Unified Multi-View Video Understanding for Proficiency Estimation

·
2 authors

2

Submitted by

Ksgk-fy

Memorization-Compression Cycles Improve Generalization

·
1 authors

2

Submitted by

taiwang

NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance

·
9 authors

Submitted by

Omartificial-Intelligence-Space

Optimizing Retrieval-Augmented Generation: Analysis of Hyperparameter Impact on Performance and Efficiency

·
4 authors

Submitted by

trucnguyen28

ViMRHP: A Vietnamese Benchmark Dataset for Multimodal Review Helpfulness Prediction via Human-AI Collaborative Annotation

·
4 authors

2

Submitted by

onekq

Tests as Prompt: A Test-Driven-Development Benchmark for LLM Code Generation

·
1 authors