Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections
Paper
•
2507.00018
•
Published
QinyuanCheng
Cqy2019
AI & ML interests
None yet
Recent Activity
updated
a Space
about 10 hours ago
OpenMOSS-Team/MOSS-TTSD
liked
a model
4 days ago
microsoft/VibeVoice-ASR
liked
a model
4 days ago
Qwen/Qwen3-TTS-12Hz-1.7B-VoiceDesign
Organizations
authored
5
papers
4 months ago
XY-Tokenizer: Mitigating the Semantic-Acoustic Conflict in Low-Bitrate Speech Codecs
Paper
•
2506.23325
•
Published
Dynamic and Generalizable Process Reward Modeling
Paper
•
2507.17849
•
Published
VStyle: A Benchmark for Voice Style Adaptation with Spoken Instructions
Paper
•
2509.09716
•
Published
•
12
MOSS-Speech: Towards True Speech-to-Speech Models Without Text Guidance
Paper
•
2510.00499
•
Published
•
19
authored
13
papers
8 months ago
Evaluating Hallucinations in Chinese Large Language Models
Paper
•
2310.03368
•
Published
Can AI Assistants Know What They Don't Know?
Paper
•
2401.13275
•
Published
•
1
LLM can Achieve Self-Regulation via Hyperparameter Aware Generation
Paper
•
2402.11251
•
Published
•
1
Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models
Paper
•
2405.12939
•
Published
•
1
Cross-Modality Safety Alignment
Paper
•
2406.15279
•
Published
•
5
Case2Code: Learning Inductive Reasoning with Synthetic Data
Paper
•
2407.12504
•
Published
•
8
Improving Contrastive Learning of Sentence Embeddings from AI Feedback
Paper
•
2305.01918
•
Published
Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective
Paper
•
2412.14135
•
Published
Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?
Paper
•
2502.12215
•
Published
•
16
World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning
Paper
•
2503.10480
•
Published
•
55
VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search
Paper
•
2504.09130
•
Published
•
12
Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT
Paper
•
2402.12201
•
Published
InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems
Paper
•
2506.16381
•
Published
•
4