Research Hot Topics
📁 Other (163 papers)
Other research directions
- The Ultimate Tutorial for AI-driven Scale Development in Generative PsLara Russell-Lasalandra, Hudson Golino, Luis Eduardo Garrido et al.
- Crossing the NL/PL Divide: Information Flow Analysis Across the NL/PL Zihao Xu, Xiao Cheng, Ruijie Meng et al.
- A First Step Towards Even More Sparse Encodings of Probability DistribFlorian Andreas Marwitz, Tanya Braun, Ralf Möller
- KEditVis: A Visual Analytics System for Knowledge Editing of Large LanZhenning Chen, Hanbei Zhan, Yanwei Huang et al.
- Baby Scale: Investigating Models Trained on Individual Children's LangSteven Y. Feng, Alvin W. M. Tan, Michael C. Frank
🤖 LLM Agents (155 papers)
Agent systems, multi-agent collaboration, autonomous decision making
- CirrusBench: Evaluating LLM-based Agents Beyond Correctness in Real-WoYi Yu, Guangquan Hu, Chenghuang Shen et al.
- FeDMRA: Federated Incremental Learning with Dynamic Memory Replay AlloTiantian Wang, Xiang Xiang, Simon S. Du
- COvolve: Adversarial Co-Evolution of Large-Language-Model-Generated PoAlkis Sygkounas, Rishi Hazra, Andreas Persson et al.
- Deep Research of Deep Research: From Transformer to Agent, From AI to Yipeng Yu
- CoE: Collaborative Entropy for Uncertainty Quantification in Agentic MKangkang Sun, Jun Wu, Jianhua Li et al.
📚 RAG Memory (84 papers)
Retrieval augmentation, dynamic indexing
- Mapping data literacy trajectories in K-12 educationRobert Whyte, Manni Cheung, Katharine Childs et al.
- Real-Time Band-Grouped Vocal Denoising Using Sigmoid-Driven Ideal RatiDaniel Williams
- MacTok: Robust Continuous Tokenization for Image GenerationHengyu Zeng, Xin Gao, Guanghao Li et al.
- Quantifying Cross-Modal Interactions in Multimodal Glioma Survival PreIain Swift, JingHua Ye, Ruairi O'Reilly
- To Memorize or to Retrieve: Scaling Laws for RAG-Considerate PretrainiKaran Singh, Michael Yu, Varun Gangal et al.
🧠 Reasoning (75 papers)
Chain-of-thought, multi-step reasoning
- Beyond the Answer: Decoding the Behavior of LLMs as Scientific ReasoneRohan Pandey, Eric Ye, Michael Li
- Hallucination-aware intermediate representation edit in large vision-lWei Suo, Hanzu Zhang, Lijun Zhang et al.
- SLOW: Strategic Logical-inference Open Workspace for Cognitive AdaptatYuang Wei, Ruijia Li, Bo Jiang
- SARL: Label-Free Reinforcement Learning by Rewarding Reasoning TopologYifan Wang, Bolian Li, David Cho et al.
- CARV: A Diagnostic Benchmark for Compositional Analogical Reasoning inYongkang Du, Xiaohan Zou, Minhao Cheng et al.
🛡 Safety Alignment (68 papers)
Model safety, privacy, adversarial defense
- Why Aggregate Accuracy is Inadequate for Evaluating Fairness in Law EnKhalid Adnan Alsayed
- CIPHER: Counterfeit Image Pattern High-level Examination via RepresentKyeonghun Kim, Youngung Han, Seoyoung Ju et al.
- FedFG: Privacy-Preserving and Robust Federated Learning via Flow-MatchRuiyang Wang, Rong Pan, Zhengan Yao
- Adversarial Attacks on Multimodal Large Language Models: A ComprehensiBhavuk Jain, Sercan Ö. Arık, Hardeo K. Thakur
- CIPHER: Counterfeit Image Pattern High-level Examination via RepresentKyeonghun Kim, Youngung Han, Seoyoung Ju et al.
🔋 Efficiency (36 papers)
Quantization, pruning, acceleration
- Dynamic Lookahead Distance via Reinforcement Learning-Based Pure PursuMohamed Elgouhary, Amr S. El-Wakeel
- Optimizing Donor Outreach for Blood Collection Sessions: A Scalable DeAndré Carneiro, Pedro T. Monteiro, Rui Henriques
- End-to-End Image Compression with Segmentation Guided Dual Coding for Raül Pérez-Gonzalo, Andreas Espersen, Søren Forchhammer et al.
- Flow-based Policy With Distributional Reinforcement Learning in TrajecRuijie Hao, Longfei Zhang, Yang Dai et al.
- Prompt-Guided Prefiltering for VLM Image CompressionBardia Azizian, Ivan V. Bajic
Featured Papers
Why Aggregate Accuracy is Inadequate for Evaluating Fairness in Law Enforcement Facial Recognition Systems
Khalid Adnan Alsayed
Facial recognition systems are increasingly deployed in law enforcement and security contexts, where algorithmic decisions can carry significant societal consequences. Despite high reported accuracy, growing evidence demonstrates that such systems often exhibit uneven performance across demographic ...
The Ultimate Tutorial for AI-driven Scale Development in Generative Psychometrics: Releasing AIGENIE from its Bottle
Lara Russell-Lasalandra, Hudson Golino, Luis Eduardo Garrido, Alexander P. Christensen
Psychological scale development has traditionally required extensive expert involvement, iterative revision, and large-scale pilot testing before psychometric evaluation can begin. The `AIGENIE` R package implements the AI-GENIE framework (Automatic Item Generation with Network-Integrated Evaluation...
Dynamic Lookahead Distance via Reinforcement Learning-Based Pure Pursuit for Autonomous Racing
Mohamed Elgouhary, Amr S. El-Wakeel
Pure Pursuit (PP) is a widely used path-tracking algorithm in autonomous vehicles due to its simplicity and real-time performance. However, its effectiveness is sensitive to the choice of lookahead distance: shorter values improve cornering but can cause instability on straights, while longer values...
CirrusBench: Evaluating LLM-based Agents Beyond Correctness in Real-World Cloud Service Environments
Yi Yu, Guangquan Hu, Chenghuang Shen, Xingyan Liu, Jing Gu et al.
The increasing agentic capabilities of Large Language Models (LLMs) have enabled their deployment in real-world applications, such as cloud services, where customer-assistant interactions exhibit high technical complexity and long-horizon dependencies, making robustness and resolution efficiency cri...
FeDMRA: Federated Incremental Learning with Dynamic Memory Replay Allocation
Tiantian Wang, Xiang Xiang, Simon S. Du
In federated healthcare systems, Federated Class-Incremental Learning (FCIL) has emerged as a key paradigm, enabling continuous adaptive model learning among distributed clients while safeguarding data privacy. However, in practical applications, data across agent nodes within the distributed framew...
COvolve: Adversarial Co-Evolution of Large-Language-Model-Generated Policies and Environments via Two-Player Zero-Sum Game
Alkis Sygkounas, Rishi Hazra, Andreas Persson, Pedro Zuidberg Dos Martires, Amy Loutfi
A central challenge in building continually improving agents is that training environments are typically static or manually constructed. This restricts continual learning and generalization beyond the training distribution. We address this with COvolve, a co-evolutionary framework that leverages lar...
Deep Research of Deep Research: From Transformer to Agent, From AI to AI for Science
Yipeng Yu
With the advancement of large language models (LLMs) in their knowledge base and reasoning capabilities, their interactive modalities have evolved from pure text to multimodality and further to agentic tool use. Consequently, their applications have broadened from question answering to AI assistants...
CoE: Collaborative Entropy for Uncertainty Quantification in Agentic Multi-LLM Systems
Kangkang Sun, Jun Wu, Jianhua Li, Minyi Guo, Xiuzhen Che et al.
Uncertainty estimation in multi-LLM systems remains largely single-model-centric: existing methods quantify uncertainty within each model but do not adequately capture semantic disagreement across models. To address this gap, we propose Collaborative Entropy (CoE), a unified information-theoretic me...
Crossing the NL/PL Divide: Information Flow Analysis Across the NL/PL Boundary in LLM-Integrated Code
Zihao Xu, Xiao Cheng, Ruijie Meng, Yuekang Li
LLM API calls are becoming a ubiquitous program construct, yet they create a boundary that no existing program analysis can cross: runtime values enter a natural-language prompt, undergo opaque processing inside the LLM, and re-emerge as code, SQL, JSON, or text that the program consumes. Every anal...
Mapping data literacy trajectories in K-12 education
Robert Whyte, Manni Cheung, Katharine Childs, Jane Waite, Sue Sentance
Data literacy skills are fundamental in computer science education. However, understanding how data-driven systems work represents a paradigm shift from traditional rule-based programming. We conducted a systematic literature review of 84 studies to understand K-12 learners' engagement with data acr...
Top Authors
- Kyeonghun Kim (5 papers)
- Nam-Joon Kim (5 papers)
- Hyuk-Jae Lee (5 papers)
- Payal Fofadiya (5 papers)
- Sunil Tiwari (5 papers)
- Lei Wang (5 papers)
- Youngung Han (4 papers)
- Steven Y. Feng (4 papers)
Trends
- Agent collaboration and autonomous decision making
- Safety and alignment deep exploration
- Reasoning capability breakthroughs
- RAG architecture innovations
- RL new paradigms (GRPO, policy distillation)
评论