Junchi Yan

15 papers Shanghai Jiao Tong University

• Bootstrapping Hierarchical Autoregressive Formal Reasoner with Chain-of-Proxy-Autoformalization
• Bridging Crypto with ML-based Solvers: the SAT Formulation and Benchmarks
• CORE: Collaborative Optimization with Reinforcement Learning and Evolutionary Algorithm for Floorplanning
• Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing
• Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing
• Fractional Langevin Dynamics for Combinatorial Optimization via Polynomial-Time Escape
• Generation as Search Operator for Test-Time Scaling of Diffusion-based Combinatorial Optimization
• ML4CO-Bench-101: Benchmark Machine Learning for Classic Combinatorial Problems on Graphs
• MS-Bench: Evaluating LMMs in Ancient Manuscript Study through a Dunhuang Case Study
• NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective
• Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)
• Repurposing AlphaFold3-like Protein Folding Models for Antibody Sequence and Structure Co-design
• StruDiCO: Structured Denoising Diffusion with Gradient-free Inference-stage Boosting for Memory and Time Efficient Combinatorial Optimization
• Train on Pins and Test on Obstacles for Rectilinear Steiner Minimum Tree
• VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models