13 papers
Repo2Skill-Evo: Repository Skills Go Stale in Silence
Chenyuan Duan, Ge Shi, Zineng Mao +10
Large language model (LLM) agents increasingly operate over evolving software repositories, where success depends on repository-specific procedural knowledge: which APIs to call, w…
PolyWorkBench: Benchmarking LLM Agents for Cross-Lingual Long-Horizon Workflows
Hongliang Li, Yijin Liu, Zhiwei Zhang +5
While Large Language Model (LLM) agents excel at monolingual long-horizon planning and tool use, enterprise workflows inherently require processing multilingual resources across ex…
Beyond English: Uncovering the Multilingual Gap in Vision-Language-Action Models
Hanyang Chen, Hongliang Li, Jiarui Cao +6
Vision-Language-Action models have recently demonstrated promising capabilities in learning generalist robot policies from large-scale multimodal data. However, most existing VLA s…
Multi-Aspect Knowledge Distillation for Language Model with Low-rank Factorization
Zihe Liu, Yulong Mao, Jinan Xu +2
Knowledge distillation is an effective technique for pre-trained language model compression. However, existing methods only focus on the knowledge distribution among layers, which…
Imagination Helps Visual Reasoning, But Not Yet in Latent Space
You Li, Chi Chen, Yanghao Li +4
Latent visual reasoning aims to mimic human's imagination process by meditating through hidden states of Multimodal Large Language Models. While recognized as a promising paradigm…
Workflow-R1: Group Sub-sequence Policy Optimization for Multi-turn Workflow Construction
Mingze Kong, Zikun Qu, Zhongquan Zhou +7
The rapid evolution of agentic workflows has demonstrated strong performance of LLM-based agents in addressing complex reasoning tasks. However, existing workflow optimization meth…
When Helpers Become Hazards: A Benchmark for Analyzing Multimodal LLM-Powered Safety in Daily Life
Xinyue Lou, Jinan Xu, Jingyi Yin +8
As Multimodal Large Language Models (MLLMs) become an indispensable assistant in human life, the unsafe content generated by MLLMs poses a danger to human behavior, perpetually ove…
Think Natively: Unlocking Multilingual Reasoning with Consistency-Enhanced Reinforcement Learning
Xue Zhang, Yunlong Liang, Fandong Meng +5
Large Reasoning Models (LRMs) have achieved remarkable performance on complex reasoning tasks by adopting the ``think-then-answer'' paradigm, which enhances both accuracy and inter…
Long Story Generation via Knowledge Graph and Literary Theory
Ge Shi, Kaiyu Huang, Guochen Feng
The generation of a long story consisting of several thousand words is a sub-task in the field of long text generation~(LTG). Previous research has addressed this challenge through…
MUCAR: Benchmarking Multilingual Cross-Modal Ambiguity Resolution for Multimodal Large Language Models
Xiaolong Wang, Zhaolu Kang, Wangyuxuan Zhai +8
Multimodal Large Language Models (MLLMs) have demonstrated significant advances across numerous vision-language tasks. MLLMs have shown promising capability in aligning visual and…
Think in Safety: Unveiling and Mitigating Safety Alignment Collapse in Multimodal Large Reasoning Model
Xinyue Lou, You Li, Jinan Xu +3
The rapid development of Multimodal Large Reasoning Models (MLRMs) has demonstrated broad application potential, yet their safety and reliability remain critical concerns that requ…
Migician: Revealing the Magic of Free-Form Multi-Image Grounding in Multimodal Large Language Models
You Li, Heyu Huang, Chi Chen +8
The recent advancement of Multimodal Large Language Models (MLLMs) has significantly improved their fine-grained perception of single images and general comprehension across multip…
Improving Cross-lingual Representation for Semantic Retrieval with Code-switching
Mieradilijiang Maimaiti, Yuanhang Zheng, Ji Zhang +3
Semantic Retrieval (SR) has become an indispensable part of the FAQ system in the task-oriented question-answering (QA) dialogue scenario. The demands for a cross-lingual smart-cus…