Papers
Research papers from arXiv and related sources
SecureBreak -- A dataset towards safe and secure models
Large language models are becoming pervasive core components in many real-world applications. As a consequence, security alignment represents a critical requirement for their safe deployment. Altho...
Marco Arazzi, Vignesh Kumar Kembu, Antonino Nocera
Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipe
Reinforcement Learning (RL) is essential for evolving Large Language Models (LLMs) into autonomous agents capable of long-horizon planning, yet a practical recipe for scaling RL in complex, multi-t...
Xixi Wu, Qianguo Sun, Ruiyang Zhang, Chao Song, Junlong Wu, Yiyan Qi, Hong Cheng
Parameter-Efficient Fine-Tuning for Medical Text Summarization: A Comparative Study of Lora, Prompt Tuning, and Full Fine-Tuning
Fine-tuning large language models for domain-specific tasks such as medical text summarization demands substantial computational resources. Parameter-efficient fine-tuning (PEFT) methods offer prom...
Ulugbek Shernazarov, Rostislav Svitsov, Bin Shi
Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention
Video large language models (Video-LLMs) face high computational costs due to large volumes of visual tokens. Existing token compression methods typically adopt a two-stage spatiotemporal compressi...
Junhao Du, Jialong Xue, Anqi Li, Jincheng Dai, Guo Lu
You See It, They Don't: An Exploratory Study of User-to-User Variation in Instagram Comments
In March 2025, Meta announced a new AI system to rank the order of the comments shown to Instagram users. With existing research showing how feed personalization systems can lead to increased polar...
Brahmani Nutakki, Manon Lilott Kempermann, Ingmar Weber
Look, Listen and Segment: Towards Weakly Supervised Audio-visual Semantic Segmentation
Audio-Visual Semantic Segmentation (AVSS) aligns audio and video at the pixel level but requires costly per-frame annotations. We introduce Weakly Supervised Audio-Visual Semantic Segmentation (WSA...
Chengzhi Li, Heyan Huang, Ping Jian, Yanghao Zhou
FeatDistill: A Feature Distillation Enhanced Multi-Expert Ensemble Framework for Robust AI-generated Image Detection
The rapid iteration and widespread dissemination of deepfake technology have posed severe challenges to information security, making robust and generalizable detection of AI-generated forged images...
Zhilin Tu, Kemou Li, Fengpeng Li, Jianwei Fei, Jiamin Zhang, Haiwei Wu
MultiBind: A Benchmark for Attribute Misbinding in Multi-Subject Generation
Subject-driven image generation is increasingly expected to support fine-grained control over multiple entities within a single image. In multi-reference workflows, users may provide several subjec...
Wenqing Tian, Hanyi Mao, Zhaocheng Liu, Lihua Zhang, Qiang Liu, Jian Wu, Liang Wang
Guideline-grounded retrieval-augmented generation for ophthalmic clinical decision support
In this work, we propose Oph-Guid-RAG, a multimodal visual RAG system for ophthalmology clinical question answering and decision support. We treat each guideline page as an independent evidence uni...
Shuying Chen, Sen Cui, Zhong Cao
APEG: Adaptive Physical Layer Authentication with Channel Extrapolation and Generative AI
With the rapid advancement of 6G, identity authentication has become increasingly critical for ensuring wireless security. The lightweight and keyless Physical Layer Authentication (PLA) is regarde...
Xiqi Cheng, Rui Meng, Xiaodong Xu, Haixiao Gao, Ping Zhang, Dusit Niyato
P^2O: Joint Policy and Prompt Optimization
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of Large Language Models (LLMs). However, vanilla RLVR suffers from...
Xinyu Lu, Kaiqi Zhang, Jinglin Yang, Boxi Cao, Yaojie Lu, Hongyu Lin, Min He, Xianpei Han, Le Sun
Tacit Knowledge Management with Generative AI: Proposal of the GenAI SECI Model
The emergence of generative AI is bringing about a significant transformation in knowledge management. Generative AI has the potential to address the limitations of conventional knowledge managemen...
Naoshi Uchihira
Adaptive Video Distillation: Mitigating Oversaturation and Temporal Collapse in Few-Step Generation
Video generation has recently emerged as a central task in the field of generative AI. However, the substantial computational cost inherent in video synthesis makes model distillation a critical te...
Yuyang You, Yongzhi Li, Jiahui Li, Yadong Mu, Quan Chen, Peng Jiang
Climate Prompting: Generating the Madden-Julian Oscillation using Video Diffusion and Low-Dimensional Conditioning
Generative Deep Learning is a powerful tool for modeling of the Madden-Julian oscillation (MJO) in the tropics, yet its relationship to traditional theoretical frameworks remains poorly understood....
Sulian Thual, Feiyang Cai, Jingjing Wang, Feng Luo
Reasoning or Rhetoric? An Empirical Analysis of Moral Reasoning Explanations in Large Language Models
Do large language models reason morally, or do they merely sound like they do? We investigate whether LLM responses to moral dilemmas exhibit genuine developmental progression through Kohlberg's st...
Aryan Kasat, Smriti Singh, Aman Chadha, Vinija Jain
Riding Brainwaves in LLM Space: Understanding Activation Patterns Using Individual Neural Signatures
Consumer-grade EEG is entering everyday devices, from earbuds to headbands, raising the question of whether language models can be adapted to individual neural responses. We test this by asking whe...
Ajan Subramanian, Sumukh Bettadapura, Rohan Sathish
Agentic Personas for Adaptive Scientific Explanations with Knowledge Graphs
AI explanation methods often assume a static user model, producing non-adaptive explanations regardless of expert goals, reasoning strategies, or decision contexts. Knowledge graph-based explanatio...
Susana Nunes, Tiago Guerreiro, Catia Pesquita
Take the Train: Africa at the Crossroad of Modern AI
Africa's participation in modern AI development is constrained by severe infrastructural and policy gaps. Important barriers include limited access to high-performance computing (HPC), restricted c...
Cédric Manouan, Miquilina Anagbah, N'guessan Yves-Roland Douha, João Barros
A Curated List of Open-source Software-only Energy Efficiency Measurement Tools: A GitHub Mining Study
Energy efficiency has become a growing concern in software development, leading to the need for tools designed to measure energy consumption. While several energy measurement tools are available as...
Manuela Bechara Cannizza, Michel Albonico
The Presupposition Problem in Representation Genesis
Large language models are the first systems to achieve high cognitive performance without clearly undergoing representation genesis: the transition from a non-representing physical system to one wh...
Yiling Wu