hai zhao

MaskSearch: Towards Scalable Agentic Pre-Training for Search-Enhanced Reasoning

Don't Lose Sight: Visually-Grounded Credit Assignment for Multimodal Reasoning

TrigReason: Trigger-Based Collaboration between Small and Large Reasoning Models

RACER: Retrieval-Augmented Contextual Rapid Speculative Decoding

Chain-of-Trigger: An Agentic Backdoor that Paradoxically Enhances Agentic Robustness

EAT: Expert Account Tracker for Efficient MoE Inference

On the Efficiency-Safety Dilemma in Large Reasoning Models

The Hunger Game Debate: On the Emergence of Over-Competition in Multi-Agent Systems

BriLLM: Brain-inspired Large Language Model

SmallKV: Small Model Assisted Compensation of KV Cache Compression for Efficient LLM Inference

Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints

What Limits Bidirectional Model's Generative Capabilities? A Uni-Bi-Directional Mixture-of-Expert Method For Bidirectional Fine-tuning

KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing

Evolving Virtual World with Delta-Engine

BriLLM: Brain-inspired Large Language Model