4 papers
Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software Evolution
Liliana Hotsko, Yinxi Li, Yuntian Deng +1
Code language models need repository-level context to resolve imports, APIs, and project conventions. Existing methods inject this knowledge as long inputs (retrieved through RAG o…
NoiseRater: Meta-Learned Noise Valuation for Diffusion Model Training
Fang Wu, Haokai Zhao, Da Xing +17
Diffusion models have achieved remarkable success across a wide range of generative tasks, yet their training paradigm largely treats injected noise as uniformly informative. In th…
Proteo-R1: Reasoning Foundation Models for De Novo Protein Design
Fang Wu, Weihao Xuan, Heli Qi +26
Deep learning in de novo protein design has achieved atomic-level fidelity. However, existing models remain largely non-deliberative: they directly synthesize molecular geometries…
TokDrift: When LLM Speaks in Subwords but Code Speaks in Grammar
Yinxi Li, Yuntian Deng, Pengyu Nie
Large language models (LLMs) for code rely on subword tokenizers, such as byte-pair encoding (BPE), learned from mixed natural language text and programming language code but drive…