Profiles2020-2026
Jie Wang
MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China
67Papers
13Last author
74Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers67
- Why Attention Patterns Exist: A Unifying Temporal Perspective AnalysisAuthor 2 of 9ICLR 2026 · 5 citations
- Opt-Verifier: Unleashing the Power of LLMs for Optimization Modeling via Dual-Side VerificationAuthor 2 of 11ICML 2026 · 4 citations
- Short Chains, Deep Thoughts: Balancing Reasoning Efficiency and Intra-Segment Capability via Split-Merge OptimizationAuthor 2 of 6ICML 2026 · 1 citation
- A Hierarchical Circuit Symbolic Discovery Framework for Efficient Logic OptimizationAuthor 2 of 7ICLR 2026
- Adversarial Latent Embedding Repair for LLM Continual LearningAuthor 3 of 11ICML 2026
- Boosting Multi-Domain Reasoning of LLMs via Curvature-Guided Policy OptimizationAuthor 3 of 9ICLR 2026
- D-ARL: A Distribution-Matched Asynchronous Reinforcement Learning Framework for Language ReasoningAuthor 3 of 10ICML 2026
- Evolving Graph Structured Programs for Circuit Generation with Large Language ModelsAuthor 2 of 9ICLR 2026
- Following the Navigation: Enhancing Small Language Models Contextual Reasoning with LLM GuidanceAuthor 2 of 7ICLR 2026
- Latent-Guided Reasoning: Empowering Small LLMs with Large-Model ThinkingAuthor 3 of 7ICLR 2026
- Opt-Miner: Empowering Information-Seeking Agent with Tree-Guided Data Synthesis for Optimization ModelingAuthor 3 of 9ICML 2026
- Tackling Heavy-Tailed Q-Value Bias in Offline-to-Online Reinforcement Learning with Laplace-Robust ModelingAuthor 6 of 7ICLR 2026
- OptiTree: Hierarchical Thoughts Generation with Tree Search for LLM Optimization ModelingAuthor 2 of 6NeurIPS 2025 · 33 citations
- Mixture-of-Experts Operator Transformer for Large-Scale PDE Pre-TrainingAuthor 3 of 7NeurIPS 2025 · 15 citations
- RoME: Domain-Robust Mixture-of-Experts for MILP Solution Prediction across DomainsAuthor 5 of 8NeurIPS 2025 · 11 citations
- AttentionPredictor: Temporal Patterns Matter for KV Cache CompressionAuthor 2 of 11NeurIPS 2025 · 8 citations
- Accurate KV Cache Eviction via Anchor Direction Projection for Efficient LLM InferenceAuthor 2 of 12NeurIPS 2025 · 6 citations
- SymMaP: Improving Computational Efficiency in Linear Solvers through Symbolic PreconditioningAuthor 2 of 5NeurIPS 2025 · 6 citations
- LogicTree: Improving Complex Reasoning of LLMs via Instantiated Multi-step Synthetic Logical DataAuthor 3 of 10NeurIPS 2025 · 5 citations
- STNet: Spectral Transformation Network for Solving Operator Eigenvalue ProblemAuthor 3 of 6NeurIPS 2025 · 4 citations
- High-Performance Arithmetic Circuit Optimization via Differentiable Architecture SearchAuthor 2 of 7NeurIPS 2025 · 3 citations
- Dynamic Configuration for Cutting Plane Separators via Reinforcement Learning on Incremental GraphAuthor 2 of 9NeurIPS 2025 · 1 citation
- A Graph Enhanced Symbolic Discovery Framework For Efficient Logic OptimizationAuthor 2 of 8ICLR 2025
- Accelerating Large Language Model Reasoning via Speculative SearchAuthor 2 of 8ICML 2025
- Accurate and Scalable Graph Neural Networks via Message InvarianceAuthor 2 of 6ICLR 2025
- Apollo-MILP: An Alternating Prediction-Correction Neural Solving Framework for Mixed-Integer Linear ProgrammingAuthor 2 of 8ICLR 2025
- Boosting Multi-Domain Fine-Tuning of Large Language Models through Evolving Interactions between SamplesAuthor 3 of 7ICML 2025
- Computing Circuits Optimization via Model-Based Circuit Genetic EvolutionAuthor 2 of 9ICLR 2025
- HyperTree Planning: Enhancing LLM Reasoning via Hierarchical ThinkingAuthor 3 of 10ICML 2025
- Knowledge Graph Finetuning Enhances Knowledge Manipulation in Large Language ModelsAuthor 3 of 9ICLR 2025
Showing the 30 most recent indexed papers.
