Yang Li

The paper introduces SpikeWFM, a novel hybrid architecture combining spiking neural networks (SNNs) and transformers, which significantly improves the robustness and accuracy of wireless foundation models for channel prediction against noise and interference.

The paper introduces SpikeWFM, a novel hybrid architecture combining spiking neural networks (SNNs) and transformers, which significantly improves the robustness and accuracy of wireless foundation models for channel prediction against noise and interference.

The paper proposes CAST, an answer-free self-distillation method that enhances Group Relative Policy Optimization (GRPO) for verifiable rewards, allowing token-level advantage signals even when all sampled trajectories are uniformly correct or incorrect.

The paper proposes CAST, an answer-free self-distillation method that enhances Group Relative Policy Optimization (GRPO) for verifiable rewards, allowing token-level advantage signals even when all sampled trajectories are uniformly correct or incorrect.

SIRIUS-SQL introduces a robust multi-candidate text-to-SQL system that addresses weaknesses in candidate generation, error handling, and selection, achieving state-of-the-art performance on complex benchmarks.

SIRIUS-SQL introduces a robust multi-candidate text-to-SQL system that addresses weaknesses in candidate generation, error handling, and selection, achieving state-of-the-art performance on complex benchmarks.

Introduces Looped World Models, a looped architecture for world modelling that iteratively refines latent environment states for up to 100x parameter efficiency.

This paper presents Clarus, a collaboration infrastructure for coordinating autonomous research agents towards web-scale scientific collaboration.

This paper proposes a Neural-Collapse-Inspired Prioritization (NCIP) framework for reducing model validation costs in safety-critical domains by using cross-checkpoint prediction variability instead of absolute confidence.

This paper proposes GUMPIM, a PIM system that enables interleaved CPU and PIM pages to coexist in a single memory space.

The authors introduce S$^2$-MAS, a society-scale multi-agent simulation framework that models household decisions and financial behaviors.