Mengdi Wang
~Mengdi_Wang1
45
论文总数
22.5
年均投稿
平均评分
接收情况29/45
会议分布
ICLR
24
NeurIPS
16
ICML
3
COLM
2
发表论文 (45 篇)
202526 篇
3
SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths
ICLR 2025Rejected
5
LIAR: Leveraging Inverse Alignment to Jailbreak LLMs in Seconds
ICLR 2025Rejected
3
SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths
COLM 2025Poster
4
NoWag: A Unified Framework for Shape Preserving Com- pression of Large Language Models
COLM 2025Poster
4
Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Models
NeurIPS 2025Poster
5
Securing the Language of Life: Inheritable Watermarks from DNA Language Models to Proteins
NeurIPS 2025Poster
4
Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow
ICLR 2025Poster
4
Regularized DeepIV with Model Selection
ICLR 2025Rejected
4
Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models
ICML 2025Poster
4
AIME: AI System Optimization via Multiple LLM Evaluators
ICLR 2025withdrawn
5
Relative-Translation Invariant Wasserstein Distance
ICLR 2025Rejected
4
Online Detection for Black-Box Large Language Models with Adaptive Prompt Selection
ICLR 2025Rejected
4
Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process Data
ICLR 2025Poster
4
CURE: Co-Evolving Coders and Unit Testers via Reinforcement Learning
NeurIPS 2025Spotlight
4
Does Thinking More Always Help? Mirage of Test-Time Scaling in Reasoning Models
NeurIPS 2025Poster
4
A Common Pitfall of Margin-based Language Model Alignment: Gradient Entanglement
ICLR 2025Poster
5
Towards Understanding Text Hallucination of Diffusion Models via Local Generation Bias
ICLR 2025Poster
4
Collab: Controlled Decoding using Mixture of Agents for LLM Alignment
ICLR 2025Poster
4
DISC: Dynamic Decomposition Improves LLM Inference Scaling
NeurIPS 2025Poster
4
A First-order Generative Bilevel Optimization Framework for Diffusion Models
ICML 2025Poster
4
ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs
NeurIPS 2025Poster
4
SAIL: Self-improving Efficient Online Alignment of Large Language Models
ICLR 2025Rejected
4
MMaDA: Multimodal Large Diffusion Language Models
NeurIPS 2025Poster
5
IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation
ICLR 2025Poster
4
GuideCO: Training Objective-Guided Diffusion Solver with Imperfect Data for Combinatorial Optimization
ICLR 2025withdrawn
4
MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations
ICML 2025Poster
202419 篇
4
FlexSBDD: Structure-Based Drug Design with Flexible Protein Modeling
NeurIPS 2024Poster
4
Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning?
ICLR 2024Rejected
3
Reinforcement Learning with Human Feedback: Learning Dynamic Choices via Pessimism
ICLR 2024withdrawn
4
A Theoretical Perspective for Speculative Decoding Algorithm
NeurIPS 2024Poster
4
Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks
ICLR 2024Rejected
4
Transfer Q-star : Principled Decoding for LLM Alignment
NeurIPS 2024Poster
4
Gradient Guidance for Diffusion Models: An Optimization Perspective
NeurIPS 2024Poster
4
Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight
ICLR 2024Poster
4
Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks
NeurIPS 2024Poster
3
On Provable Benefits of Policy Learning from Human Preferences in Contextual Bandit Problems
ICLR 2024Rejected
3
Posterior Sampling via Langevin Monte Carlo for Offline Reinforcement Learning
ICLR 2024Rejected
5
Global Convergence in Training Large-Scale Transformers
NeurIPS 2024Poster
4
Offline Multitask Representation Learning for Reinforcement Learning
NeurIPS 2024Poster
4
Scalable Normalizing Flows Enable Boltzmann Generators for Macromolecules
ICLR 2024Rejected
4
PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback
ICLR 2024Poster
4
Protein Language Models Enable Accurate Cryptic Ligand Binding Pocket Prediction
ICLR 2024Rejected
3
Deep Reinforcement Learning for Efficient and Fair Allocation of Health Care Resources
ICLR 2024Rejected
3
Fast Best-of-N Decoding via Speculative Rejection
NeurIPS 2024Poster
4
One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
NeurIPS 2024Poster