Jianye Hao

13 papers Tianjin University

• Accurate KV Cache Eviction via Anchor Direction Projection for Efficient LLM Inference
• AttentionPredictor: Temporal Patterns Matter for KV Cache Compression
• Benchmarking End-To-End Performance of AI-Based Chip Placement Algorithms
• COLA: Towards Efficient Multi-Objective Reinforcement Learning with Conflict Objective Regularization in Latent Space
• CORE: Collaborative Optimization with Reinforcement Learning and Evolutionary Algorithm for Floorplanning
• Conditioning Matters: Training Diffusion Policies is Faster Than You Think
• Dynamic Configuration for Cutting Plane Separators via Reinforcement Learning on Incremental Graph
• High-Performance Arithmetic Circuit Optimization via Differentiable Architecture Search
• LaRes: Evolutionary Reinforcement Learning with LLM-based Adaptive Reward Search
• LogicTree: Improving Complex Reasoning of LLMs via Instantiated Multi-step Synthetic Logical Data
• OptiTree: Hierarchical Thoughts Generation with Tree Search for LLM Optimization Modeling
• Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control
• Uncertainty-quantified Rollout Policy Adaptation for Unlabelled Cross-domain Video Temporal Grounding