Papers
Advancing Oversight Reasoning across Languages for Audit Sycophantic Behaviour via X-Agent
Giulia Pucci, Leonardo Ranaldi
DeepResonance: Enhancing Multimodal Music Understanding via Music-centric Multi-way Instruction Tuning
Zhuoyuan Mao, Mengjie Zhao, Qiyu Wu et al.
AI Chatbots as Professional Service Agents: Developing a Professional Identity
Wenwen Li, Kangwei Shi, Yidong Chai
Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Units
Chao Hao, Zezheng Wang, Yanhua Huang et al.
CoPL: Collaborative Preference Learning for Personalizing LLMs
Youngbin Choi, Seunghyuk Cho, Minjong Lee et al.
PanicToCalm: A Proactive Counseling Agent for Panic Attacks
Jihyun Lee, Yejin Min, San Kim et al.
Speculative Safety-Aware Decoding
Xuekang Wang, Shengyu Zhu, Xueqi Cheng
Data to Defense: The Role of Curation in Aligning Large Language Models Against Safety Compromise
Xiaoqun Liu, Jiacheng Liang, Luoxi Tang et al.
DeepWell-Adol: A Scalable Expert-Based Dialogue Corpus for Adolescent Positive Mental Health and Wellbeing Promotion
Wenyu Qiu, Yuxiong Wang, Jiajun Tan et al.
Expanding before Inferring: Enhancing Factuality in Large Language Models through Premature Layers Interpolation
Dingwei Chen, Ziqiang Liu, Feiteng Fang et al.
MAIN: Mutual Alignment Is Necessary for instruction tuning
Fanyi Yang, Jianfeng Liu, Xin Zhang et al.
How do autoregressive transformers solve full addition?
Wang Peixu, Chen Yu, Yu Ming et al.
VCSearch: Bridging the Gap Between Well-Defined and Ill-Defined Problems in Mathematical Reasoning
Shi-Yu Tian, Zhi Zhou, Kun-Yang Yu et al.
Breaking Bad Tokens: Detoxification of LLMs Using Sparse Autoencoders
Agam Goyal, Vedant Rathi, William Yeh et al.
Evaluating LLM-Generated Diagrams as Graphs
Chumeng Liang, Jiaxuan You
Following the Autoregressive Nature of LLM Embeddings via Compression and Alignment
Jingcheng Deng, Zhongtao Jiang, Liang Pang et al.
MoMoE: Mixture of Moderation Experts Framework for AI-Assisted Online Governance
Agam Goyal, Xianyang Zhan, Yilun Chen et al.
Can GRPO Boost Complex Multimodal Table Understanding?
Xiaoqiang Kang, Shengen Wu, Zimu Wang et al.
R2I-Bench: Benchmarking Reasoning-Driven Text-to-Image Generation
Kaijie Chen, Zihao Lin, Zhiyang Xu et al.
ProcWorld: Benchmarking Large Model Planning in Reachability-Constrained Environments
Dong Wang, Xinghang Li, Zhengshen Zhang et al.
Exploring the Limitations of Mamba in COPY and CoT Reasoning
Ruifeng Ren, Zhicong Li, Yong Liu
Translationese-index: Using Likelihood Ratios for Graded and Generalizable Measurement of Translationese
Yikang Liu, Wanyang Zhang, Yiming Wang et al.
Examining False Positives under Inference Scaling for Mathematical Reasoning
Yu Wang, Nan Yang, Liang Wang et al.
Mitigating Hallucinations in Vision-Language Models through Image-Guided Head Suppression
Sreetama Sarkar, Yue Che, Alex Gavin et al.
CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space
Yong Zhao, Kai Xu, Zhengqiu Zhu et al.