Dong Yu
~Dong_Yu2
32
论文总数
16.0
年均投稿
平均评分
接收情况16/32
会议分布
ICLR
21
NeurIPS
9
ICML
2
发表论文 (32 篇)
202525 篇
4
HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows
ICLR 2025Rejected
5
Controllable Text-to-Speech Synthesis with Masked-Autoencoded Style Representation
ICLR 2025withdrawn
5
ParallelSpec: Parallel Drafter for Efficient Speculative Decoding
ICLR 2025Rejected
4
MultiMedia-Agent: A Multimodal Agent for Multimedia Content Generation
ICLR 2025withdrawn
4
MPS-Prover: Advancing Stepwise Theorem Proving by Multi-Perspective Search and Data Curation
NeurIPS 2025Poster
4
DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search
ICLR 2025Poster
4
LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
ICLR 2025Poster
3
SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models
ICLR 2025withdrawn
5
DeFine: Enhancing LLM Decision-Making with Factor Profiles and Analogical Reasoning
ICLR 2025Rejected
3
Video-to-Audio generation with Hidden Alignment
ICLR 2025withdrawn
4
Improving LLM General Preference Alignment via Optimistic Online Mirror Descent
NeurIPS 2025Spotlight
4
UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression
NeurIPS 2025Poster
4
Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning
ICLR 2025Oral
4
Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards
NeurIPS 2025Poster
5
DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?
ICLR 2025Poster
4
SePPO: Semi-Policy Preference Optimization for Diffusion Alignment
ICLR 2025withdrawn
4
DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects
ICLR 2025Rejected
3
Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks
ICLR 2025withdrawn
5
RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph
ICLR 2025Poster
4
LeVo: High-Quality Song Generation with Multi-Preference Alignment
NeurIPS 2025Poster
4
The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
NeurIPS 2025Poster
4
Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs
ICML 2025Rejected
4
Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models
NeurIPS 2025Spotlight
4
Do NOT Think That Much for 2+3=? On the Overthinking of Long Reasoning Models
ICML 2025Poster
4
Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training
NeurIPS 2025Poster
20247 篇
4
A Stitch in Time Saves Nine: Detecting and Mitigating Hallucinations of LLMs by Actively Validating Low-Confidence Generation
ICLR 2024withdrawn
4
Generative Pre-Trained Speech Language Model with Efficient Hierarchical Transformer
ICLR 2024Rejected
4
Skills-in-Context Prompting: Unlocking Compositionality in Large Language Models
ICLR 2024Rejected
3
From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning
ICLR 2024withdrawn
4
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
NeurIPS 2024Poster
5
The Trickle-down Impact of Reward Inconsistency on RLHF
ICLR 2024Poster
4
MVoice: Multilingual Unified Voice Generation With Discrete Representation at Scale
ICLR 2024withdrawn