Papers
Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs
Wai Man Si, Mingjie Li, Michael Backes et al.
TimeSAF: Towards LLM-Guided Semantic Asynchronous Fusion for Time Series Forecasting
Fan Zhang, Shiming Fan, Hua Wang
Inhibitory Attacks on Backdoor-based Fingerprinting for Large Language Models
Hang fu, Wanli Peng, Yinghan Zhou et al.
Compiling Activation Steering into Weights via Null-Space Constraints for Stealthy Backdoors
Rui Yin, Tianxu Han, Naen Xu et al.
Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models
Boyan Han, Yiwei Wang, Yi Song et al.
TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles
Yirong Zeng, Yufei Liu, Xiao Ding et al.
CIRAG: Construction–Integration Retrieval and Adaptive Generation for Multi-hop Question Answering
Zili Wei, Yilin Wang, Xiaocui Yang et al.
MaDS: Long-Horizon GUI Automation via Synergizing Dual-Layer Memory and Multi-Round Debate
Pengchen Chen, Shi Chen, Qiming Ye et al.
SAFE-QAQ: End-to-End Slow-Thinking Audio-Text Fraud Detection via Reinforcement Learning
Peidong Wang, Zhiming Ma, Xin Dai et al.
Beyond Surface Features: Advancing Medical Vision-Language Alignment via Dynamic Evidence-Guided Preference Optimization
Zixuan Huang, Zhihong Zhu, Xiaolong Liu et al.
RRAtention: Dynamic Block Sparse Attention via Per-Head Round-Robin Shifts for Long-Context Inference
Siran Liu, Guoxia Wang, Sa Wang et al.
Attention Basin: Why Contextual Position Matters in Large Language Models
Zihao Yi, Zhenqing Ling, Delong Zeng et al.
Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agents
Yanxu Mao, Peipei Liu, Tiehan Cui et al.
CoreCodeBench: Decoupling Code Intelligence via Fine-Grained Repository-Level Tasks
Lingyue Fu, Hao Guan, Bolun Zhang et al.
TransLLM: A Unified Multi-Task Large Language Model for Urban Transportation via Learnable Prompting
Jiaming Leng, Yunying Bi, Chuan Qin et al.
Mixture-of-Experts with Intermediate CTC Supervision for Accented Speech Recognition
Wonjun Lee, Hyounghun Kim, Gary Lee
Selective Knowledge Distillation: Fusing LLM Semantic Strengths with DNN Efficiency for Binary Code Similarity Detection
Shize Zhou, Peiyu Liu, Lirong Fu et al.
VisRet: Visualization Improves Knowledge-Intensive Text-to-Image Retrieval
Di Wu, Yixin Wan, Kai-Wei Chang
Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation
Jeongho Yoon, Chanhee Park, Yongchan Chun et al.
CogEvolve: A Multimodal Benchmark for Evaluating Relational Reasoning in Semantic Extension
Jingjie Zeng, Huayang Li, Liang Yang et al.
From Logical to Computational Sparsity: Structure-Aware Block-Sparse Attention for Long-Code Completion
Yanli Wang, Yanlin Wang, Bowen Zhang et al.
Stable-RAG: Mitigating Retrieval-Permutation-Induced Hallucinations in Retrieval-Augmented Generation
Qianchi Zhang, Hainan Zhang, Liang Pang et al.
HAG: Hierarchical Demographic Tree-based Agent Generation for Topic-Adaptive Simulation
Rongxin Chen, Tianyu Wu, Bingbing Xu et al.
Jailbreaking Multimodal Large Language Models using Multi-Clip Video
Choongwon Kang, Seungjong Sun, Hyunmin Jun et al.
S2G-RAG: Structured Sufficiency and Gap Judging for Iterative Retrieval-Augmented QA
Minghan Li, Junjie Zou, Xinxuan Lv et al.