10 papers
Learning from Evolving Errors: Adaptive Iterative Repair for On-Policy Distillation
Rui Li, Liyang He, Zheng Zhang +3
On-policy self-distillation (OPSD) supplies dense token-level feedback on trajectories sampled from the student's own policy, a richer training signal than the outcome-level reward…
CubicSplat: Differentiable Vector Graphics via Error-Bounded Forward Relaxation
Chenglong Liu, Xin Zhang, Yimeng Zhu +5
Vector graphics are prized for their resolution independence, compact storage, and direct editability, making differentiable optimization of their parametric primitives an attracti…
A Survey on Deep Text Hashing: Efficient Semantic Text Retrieval with Binary Representation
Liyang He, Zhenya Huang, Cheng Yang +6
With the rapid growth of textual content on the Internet, efficient large-scale semantic text retrieval has garnered increasing attention from both academia and industry. Text hash…
ChronoPlay: A Framework for Modeling Dual Dynamics and Authenticity in Game RAG Benchmarks
Liyang He, Yuren Zhang, Ziwei Zhu +2
Retrieval Augmented Generation (RAG) systems are increasingly vital in dynamic domains like online gaming, yet the lack of a dedicated benchmark has impeded standardized evaluation…
BlueLM-2.5-3B Technical Report
Baojiao Xiong, Boheng Chen, Chengzhi Wang +58
We present BlueLM-2.5-3B, a compact and unified dense Multimodal Large Language Model (MLLM) designed for efficient edge-device deployment, offering strong general-purpose and reas…
MGS3: A Multi-Granularity Self-Supervised Code Search Framework
Rui Li, Junfeng Kang, Qi Liu +5
In the pursuit of enhancing software reusability and developer productivity, code search has emerged as a key area, aimed at retrieving code snippets relevant to functionalities ba…
Refining Sentence Embedding Model through Ranking Sentences Generation with Large Language Models
Liyang He, Chenglong Liu, Rui Li +4
Sentence embedding is essential for many NLP tasks, with contrastive learning methods achieving strong performance using annotated datasets like NLI. Yet, the reliance on manual la…
Nested Hash Layer: A Plug-and-play Module for Multiple-length Hash Code Learning
Liyang He, Yuren Zhang, Rui Li +3
Deep supervised hashing is essential for efficient storage and search in large-scale image retrieval. Traditional deep supervised hashing models generate single-length hash codes,…
Aligning LLMs through Multi-perspective User Preference Ranking-based Feedback for Programming Question Answering
Hongyu Yang, Liyang He, Min Hou +5
Code Community Question Answering (CCQA) seeks to tackle programming-related issues, thereby boosting productivity in both software engineering and academic research. Recent advanc…
Bit-mask Robust Contrastive Knowledge Distillation for Unsupervised Semantic Hashing
Liyang He, Zhenya Huang, Jiayu Liu +4
Unsupervised semantic hashing has emerged as an indispensable technique for fast image search, which aims to convert images into binary hash codes without relying on labels. Recent…