QinyuanCheng

Cqy2019's activity

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

authored 5 papers 27 days ago

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections

Paper • 2507.00018 • Published Jun 15

XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs

Paper • 2506.23325 • Published Jun 29

Dynamic and Generalizable Process Reward Modeling

Paper • 2507.17849 • Published Jul 23

VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions

Paper • 2509.09716 • Published Sep 9 • 10

MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance

Paper • 2510.00499 • Published Oct 1 • 18

authored 13 papers 4 months ago

Evaluating Hallucinations in Chinese Large Language Models

Paper • 2310.03368 • Published Oct 5, 2023

Can AI Assistants Know What They Don't Know?

Paper • 2401.13275 • Published Jan 24, 2024 • 1

LLM can Achieve Self-Regulation via Hyperparameter Aware Generation

Paper • 2402.11251 • Published Feb 17, 2024 • 1

Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models

Paper • 2405.12939 • Published May 21, 2024 • 1

Cross-Modality Safety Alignment

Paper • 2406.15279 • Published Jun 21, 2024 • 5

Case2Code: Learning Inductive Reasoning with Synthetic Data

Paper • 2407.12504 • Published Jul 17, 2024 • 8

Improving Contrastive Learning of Sentence Embeddings from AI Feedback

Paper • 2305.01918 • Published May 3, 2023

Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective

Paper • 2412.14135 • Published Dec 18, 2024

Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?

Paper • 2502.12215 • Published Feb 17 • 16

World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning

Paper • 2503.10480 • Published Mar 13 • 55

VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search

Paper • 2504.09130 • Published Apr 12 • 12

Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT

Paper • 2402.12201 • Published Feb 19, 2024

InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems

Paper • 2506.16381 • Published Jun 19 • 2