Houfeng Wang

StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs

Distill Models by Aptitude: Efficient Reasoning Capability Distillation via Adaptive Data Curation and Overthinking Mitigation

Two Pathways to Truthfulness: On the Intrinsic Encoding of LLM Hallucinations

From Bias to Benefit: Place Good Documents in Good Positions

SWE-Ext: Extending and Scaling Augmented Data for Repository-Level Coding Tasks

CoCoPIF: Benchmarking Conversational Coding and Programmatic Instruction Following

Investigating Token-Level Supervision of Multi-Dimensional Attribute Combinations

Overconfidence in LLM-as-a-Judge: Diagnosis and Confidence-Driven Solution

SupMem: Support Memorization for Semiparametric Language Models