02 / Research
Research
Publications and preprints.
Publications
2025 · TMLRHoSNNs: Adversarially-Robust Homeostatic Spiking Neural Networks with Adaptive Firing Thresholds2025 · EMNLPReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks2025 · arXivReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks2025 · arXivKhan-GCL: Kolmogorov-Arnold Network Based Graph Contrastive Learning with Hard Negatives2025 · arXivThe Landscape of Agentic Reinforcement Learning for LLMs: A Survey2025 · arXivDiagnose, Localize, Align: A Full-Stack Framework for Reliable LLM Multi-Agent Systems under Instruction Conflicts2025 · arXivBeyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE2025 · arXivScaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning2025 · arXivLiveSearchBench: An Automatically Constructed Benchmark for Retrieval and Reasoning over Dynamic Knowledge
2024 · arXivDS2TA: Denoising Spiking Transformer with Attenuated Spatiotemporal Attention2024 · Frontiers in NeuroscienceComposing Recurrent Spiking Neural Networks using Locally-Recurrent Motifs and Risk-Mitigating Architectural Optimization
2023 · arXivHoSNN: Adversarially-Robust Homeostatic Spiking Neural Networks with Adaptive Firing Thresholds2023 · arXivUPAR: A Kantian-Inspired Prompting Framework for Enhancing Large Language Model Capabilities2023 · arXivDISTA: Denoising Spiking Transformer with intrinsic plasticity and spatiotemporal attention