Yang Li

18 papers Beihang University

• A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning
• Bridging Crypto with ML-based Solvers: the SAT Formulation and Benchmarks
• Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation
• Collaborative Reasoner: Self-Improving Social Agents with Synthetic Conversations
• Exploiting Task Relationships in Continual Learning via Transferability-Aware Task Embeddings
• From Judgment to Interference: Early Stopping LLM Harmful Outputs via Streaming Content Monitoring
• Generation as Search Operator for Test-Time Scaling of Diffusion-based Combinatorial Optimization
• Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks
• ML4CO-Bench-101: Benchmark Machine Learning for Classic Combinatorial Problems on Graphs
• MPS-Prover: Advancing Stepwise Theorem Proving by Multi-Perspective Search and Data Curation
• Meta CLIP 2: A Worldwide Scaling Recipe
• NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions
• Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning
• ProteinConformers: Benchmark Dataset for Simulating Protein Conformational Landscape Diversity and Plausibility
• REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing
• StruDiCO: Structured Denoising Diffusion with Gradient-free Inference-stage Boosting for Memory and Time Efficient Combinatorial Optimization
• THD-BAR: Topology Hierarchical Derived Brain Autoregressive Modeling for EEG Generic Representations
• Theory-Driven Label-Specific Representation for Incomplete Multi-View Multi-Label Learning