Bo XU

Householder-Diagonalized Linear Attention (HDLA): Utilizing Enhanced Decay Mechanism for Efficient Sequence Modeling

OPRIDE: Efficient Offline Preference-based Reinforcement Learning via In-Dataset Exploration

Towards Knowledge‑and‑Data‑Driven Organic Reaction Prediction: RAG‑Enhanced and Reasoning‑Powered Hybrid System with LLMs

GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent System

COMPASS: Training-Free Guidance for Skill Discovery with Human Feedback

DIME: Tackling Density Imbalance for High-Performance and Low-Latency Event-Based Object Detection

SVL: Empowering Spiking Neural Networks for Efficient 3D Open-World Understanding

Parallel Training in Spiking Neural Networks

Spike-driven Large Language Model

Self-Verifying Reflection Helps Transformers with CoT Reasoning

Episodic Novelty Through Temporal Distance

STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning

DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning

Fewer May Be Better: Enhancing Offline Reinforcement Learning with Reduced Dataset

CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries

Enhancing Solutions for Complex PDEs: Introducing Translational Equivariant Attention in Fourier Neural Operators

Maximum Next-State Entropy for Efficient Reinforcement Learning

Fewer Questions, Better Answers: Efficient Offline Preference-based Reinforcement Learning via In-Dataset Exploration