Tiantian Feng

tiantiaf's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a collection 6 days ago

benchmark

Collection

57 items • Updated 10 days ago • 2

upvoted a collection 8 days ago

Voxlect - Whisper-Small

Collection

A Speech Foundation Model Benchmark for Classifying Dialects and Regional Languages around the Globe - Whisper-Small Family • 10 items • Updated 6 days ago • 1

upvoted a paper 10 days ago

Voxlect: A Speech Foundation Model Benchmark for Modeling Dialects and Regional Languages Around the Globe

Paper • 2508.01691 • Published 12 days ago • 9

upvoted 2 collections 14 days ago

Voxlect - Whisper-Large-v3

Collection

A Speech Foundation Model Benchmark for Classifying Dialects and Regional Languages around the Globe - Whisper-Large-v3 Family • 10 items • Updated 10 days ago • 1

Voxlect - MMS-LID-256

Collection

A Speech Foundation Model Benchmark for Classifying Dialects and Regional Languages across the Globe - MMS-LID-256 Family • 10 items • Updated 10 days ago • 1

upvoted 7 papers 2 months ago

ReasonMed: A 370K Multi-Agent Generated Dataset for Advancing Medical Reasoning

Paper • 2506.09513 • Published Jun 11 • 98

Large Language Models for Data Synthesis

Paper • 2505.14752 • Published May 20 • 50

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

Paper • 2505.24864 • Published May 30 • 135

Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning

Paper • 2505.24726 • Published May 30 • 268

MiniCPM4: Ultra-Efficient LLMs on End Devices

Paper • 2506.07900 • Published Jun 9 • 90

Reinforcement Pre-Training

Paper • 2506.08007 • Published Jun 9 • 255

Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better

Paper • 2506.09040 • Published Jun 10 • 35

upvoted a collection 2 months ago

Vox-Profile

Collection

This collection includes the implementation of models described in the Vox-Profile benchmark. (https://arxiv.org/pdf/2505.14648). For review purposes. • 14 items • Updated 8 days ago • 2

upvoted 2 papers 2 months ago

CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech

Paper • 2506.02863 • Published Jun 3 • 8

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

Paper • 2505.07916 • Published May 12 • 132

upvoted 5 papers 3 months ago

Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence

Paper • 2505.23747 • Published May 29 • 68

StressTest: Can YOUR Speech LM Handle the Stress?

Paper • 2505.22765 • Published May 28 • 18

SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline

Paper • 2505.19314 • Published May 25 • 4

OmniConsistency: Learning Style-Agnostic Consistency from Paired Stylization Data

Paper • 2505.18445 • Published May 24 • 65

Shifting AI Efficiency From Model-Centric to Data-Centric Compression

Paper • 2505.19147 • Published May 25 • 145