Hao Tan

The paper introduces RHELM, a new benchmark designed to test LLMs' long-term memory by simulating realistic, complex, and evolving dialogues that integrate multiple heterogeneous data sources.

FLARE is a systematic conversion framework that enables a single checkpoint to support both autoregressive (AR) and diffusion-style parallel decoding for hybrid-attention large language models, achieving competitive performance and throughput gains.

The paper proposes Fresco, a novel bidirectional type inference approach for first-class polymorphism that enables local type information to flow back and forth between functions and arguments.

This paper proposes PeakFlow, a framework for dynamic affective trajectory prediction in EEG data using a peak-guided coarse-to-refined approach.

This paper proposes CoHarden, a co-generation framework for automated program repair that uses a lax signal as an in-loop convergence criterion to prevent lax regressions.

The paper presents GrainGS, a dynamic Gaussian framework for scene reconstruction that balances fine-grained motion modeling, structural stability, and compact representation.