1 citations · 2 across the 18 of their papers we have counts for
20 papers
Functional Subnetwork Localization for Efficient Continual Learning in Large Language Models
Shuoran Jiang, Wentao Zhu, Yang Xiang +8
Biological intelligence continually adapts to new information while retaining prior skills through localized plasticity. In contrast, continual learning in large language models (L…
Breaking the Curse of Multilinguality in Many-to-Many Speech-to-Text Translation via a Resource-Aware Mixture of Speech Encoders
Yexing Du, Kaiyuan Liu, Youcheng Pan +4
Multimodal large language models (MLLMs) have achieved significant success in speech-to-text translation (S2TT). However, when processing multilingual speech inputs, a single speec…
DualAnchor: Preserving Language Priors and Improving Lexical Fidelity in Gloss-Free Sign Language Translation
Hongbin Zhang, Junhao Liu, Xuefeng Bai +3
Recent advances in large language models (LLMs) have led sign language translation (SLT), the task of converting sign-language videos into spoken-language text, to increasingly ado…
Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning
Hongbin Zhang, Chaozheng Wang, Kehai Chen +4
On-policy self-distillation (OPSD) is an emerging LLM post-training paradigm in which the model serves as its own teacher: conditioned on privileged information such as a reference…
Parameter- and Bandwidth-Efficient Edge--cloud Many-to-Many Speech-to-Text Translation
Yexing Du, Kaiyuan Liu, Youcheng Pan +5
Multimodal large language models (MLLMs) have demonstrated significant potential for speech-to-text translation (S2TT). However, existing deployment paradigms face critical challen…
Reason Analogically via Cross-domain Prior Knowledge: An Empirical Study of Cross-domain Knowledge Transfer for In-Context Learning
Le Liu, Zhiming Li, Jianzhi Yan +7
Despite its success, existing in-context learning (ICL) relies on in-domain expert demonstrations, limiting its applicability when expert annotations are scarce. We posit that diff…
Towards Effective In-context Cross-domain Knowledge Transfer via Domain-invariant-neurons-based Retrieval
Jianzhi Yan, Zhiming Li, Le Liu +6
Large language models (LLMs) have made notable progress in logical reasoning, yet still fall short of human-level performance. Current boosting strategies rely on expert-crafted in…
Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck
Hongbin Zhang, Kehai Chen, Xuefen Bai +4
Large language models (LLMs) have become a standard for multilingual evaluation, yet they exhibit a severe systematic translationese bias. In this paper, translationese bias is cha…
Scalable Multilingual Multimodal Machine Translation with Speech-Text Fusion
Yexing Du, Youcheng Pan, Zekun Wang +7
Multimodal Large Language Models (MLLMs) have achieved notable success in enhancing translation performance by integrating multimodal information. However, existing research primar…
Decoupling Skeleton and Flesh: Efficient Multimodal Table Reasoning with Disentangled Alignment and Structure-aware Guidance
Yingjie Zhu, Xuefeng Bai, Kehai Chen +4
Reasoning over table images remains challenging for Large Vision-Language Models (LVLMs) due to complex layouts and tightly coupled structure-content information. Existing solution…
MCGA: A Multi-task Classical Chinese Literary Genre Audio Corpus
Yexing Du, Kaiyuan Liu, Bihe Zhang +9
With the rapid advancement of Multimodal Large Language Models (MLLMs), their potential has gained significant attention in Chinese Classical Studies (CCS). While existing research…
MCAT: Scaling Many-to-Many Speech-to-Text Translation with MLLMs to 70 Languages
Yexing Du, Kaiyuan Liu, Youcheng Pan +7
Multimodal Large Language Models (MLLMs) have achieved great success in Speech-to-Text Translation (S2TT) tasks. However, current research is constrained by two key challenges: lan…
Towards Efficient CoT Distillation: Self-Guided Rationale Selector for Better Performance with Fewer Rationales
Jianzhi Yan, Le Liu, Youcheng Pan +3
Chain-of-thought (CoT) distillation aims to enhance small language models' (SLMs) reasoning by transferring multi-step reasoning capability from the larger teacher models. However,…
From Long to Lean: Performance-aware and Adaptive Chain-of-Thought Compression via Multi-round Refinement
Jianzhi Yan, Le Liu, Youcheng Pan +4
Chain-of-Thought (CoT) reasoning improves performance on complex tasks but introduces significant inference latency due to verbosity. We propose Multiround Adaptive Chain-of-Though…
Beyond the Vision Encoder: Identifying and Mitigating Spatial Bias in Large Vision-Language Models
Yingjie Zhu, Xuefeng Bai, Kehai Chen +6
Large Vision-Language Models (LVLMs) have achieved remarkable success across a wide range of multimodal tasks, yet their robustness to spatial variations remains insufficiently und…
CCFQA: A Benchmark for Cross-Lingual and Cross-Modal Speech and Text Factuality Evaluation
Yexing Du, Kaiyuan Liu, Youcheng Pan +5
As Large Language Models (LLMs) are increasingly popularized in the multilingual world, ensuring hallucination-free factuality becomes markedly crucial. However, existing benchmark…
KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model
Xinping Zhao, Xinshuo Hu, Zifei Shan +14
Recent advancements in Large Language Models (LLMs)-based text embedding models primarily focus on data scaling or synthesis, yet limited exploration of training techniques and dat…
ProjectEval: A Benchmark for Programming Agents Automated Evaluation on Project-Level Code Generation
Kaiyuan Liu, Youcheng Pan, Yang Xiang +4
Recently, LLM agents have made rapid progress in improving their programming capabilities. However, existing benchmarks lack the ability to automatically evaluate from users' persp…
ZO-AdaMU Optimizer: Adapting Perturbation by the Momentum and Uncertainty in Zeroth-order Optimization
Shuoran Jiang, Qingcai Chen, Youchen Pan +5
Lowering the memory requirement in full-parameter training on large models has become a hot research area. MeZO fine-tunes the large language models (LLMs) by just forward passes i…
Confounder Balancing in Adversarial Domain Adaptation for Pre-Trained Large Models Fine-Tuning
Shuoran Jiang, Qingcai Chen, Yang Xiang +2
The excellent generalization, contextual learning, and emergence abilities in the pre-trained large models (PLMs) handle specific tasks without direct training data, making them th…