Profiles2020-2026
Jianye Hao
Tianjin University
59Papers
16Last author
91Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers59
- Embodied-R1: Reinforced Embodied Reasoning for General Robotic ManipulationAuthor 10 of 10ICLR 2026 · 48 citations
- From Seeing to Doing: Bridging Reasoning and Decision for Robotic ManipulationAuthor 10 of 10ICLR 2026 · 41 citations
- CellAgent: LLM-Driven Multi-Agent Framework for Natural Language-Based Single-Cell AnalysisAuthor 5 of 15ICLR 2026 · 11 citations
- Squeeze the Soaked Sponge: Efficient Off-policy RFT for Large Language ModelAuthor 8 of 8ICLR 2026 · 10 citations
- Scalable In-Context Q-LearningAuthor 4 of 9ICLR 2026 · 8 citations
- Re2: Unlocking LLM Reasoning via Reinforcement Learning with Re-solvingAuthor 6 of 7ICLR 2026 · 7 citations
- The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement LearningAuthor 6 of 6ICLR 2026 · 2 citations
- Bottleneck-Guided Spectral Subgoals For Offline Goal-Conditioned RLAuthor 8 of 8ICML 2026
- Neuro-evolutionary Continual Reinforcement LearningAuthor 6 of 6ICML 2026
- SheetAgent: Towards a Generalist Agent for Spreadsheet Reasoning and Manipulation via Large Language ModelsAuthor 8 of 10WWW 2025 · 13 citations
- Conditioning Matters: Training Diffusion Policies is Faster Than You ThinkAuthor 5 of 5NeurIPS 2025 · 10 citations
- LaRes: Evolutionary Reinforcement Learning with LLM-based Adaptive Reward SearchAuthor 5 of 5NeurIPS 2025 · 7 citations
- RoboAnnotatorX: A Comprehensive and Universal Annotation Framework for Accurate Understanding of Long-Horizon Robot DemonstrationAuthor 8 of 8ICCV 2025 · 6 citations
- COLA: Towards Efficient Multi-Objective Reinforcement Learning with Conflict Objective Regularization in Latent SpaceAuthor 4 of 6NeurIPS 2025 · 3 citations
- CORE: Collaborative Optimization with Reinforcement Learning and Evolutionary Algorithm for FloorplanningAuthor 3 of 8NeurIPS 2025 · 1 citation
- DualRAG: A Dual-Process Approach to Integrate Reasoning and Retrieval for Multi-Hop Question AnsweringAuthor 9 of 9ACL 2025
- MODULI: Unlocking Preference Generalization via Diffusion Models for Offline Multi-Objective Reinforcement LearningAuthor 4 of 4ICML 2025
- R*: Efficient Reward Design via Reward Structure Evolution and Parameter Alignment Optimization with Large Language ModelsAuthor 2 of 7ICML 2025
- SWAMamba: A Sliding Window Attention Mamba Framework for Predicting Translation Elongation RatesAuthor 5 of 6AAAI 2025
- War of Thoughts: Competition Stimulates Stronger Reasoning in Large Language ModelsAuthor 5 of 5ACL Findings 2025
- DiffuserLite: Towards Real-time Diffusion PlanningAuthor 2 of 8NeurIPS 2024 · 57 citations
- AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion ModelAuthor 3 of 10ICLR 2024 · 44 citations
- Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human FeedbackAuthor 2 of 9ICLR 2024 · 21 citations
- Rethinking Decision Transformer via Hierarchical Reinforcement LearningAuthor 4 of 4ICML 2024 · 15 citations
- Unlock the Cognitive Generalization of Deep Reinforcement Learning via Granular Ball RepresentationAuthor 2 of 4ICML 2024 · 15 citations
- OVD-Explorer: Optimism Should Not Be the Sole Pursuit of Exploration in Noisy EnvironmentsAuthor 4 of 9AAAI 2024 · 14 citations
- EvoRainbow: Combining Improvements in Evolutionary Reinforcement Learning for Policy SearchAuthor 5 of 5ICML 2024 · 13 citations
- PERIA: Perceive, Reason, Imagine, Act via Holistic Language and Vision Planning for ManipulationAuthor 2 of 10NeurIPS 2024 · 13 citations
- Iteratively Refined Behavior Regularization for Offline Reinforcement LearningAuthor 2 of 5NeurIPS 2024 · 11 citations
- Value-Evolutionary-Based Reinforcement LearningAuthor 2 of 5ICML 2024 · 10 citations
Showing the 30 most recent indexed papers.
