Papers
Research papers from arXiv and related sources
Understanding the Challenges in Iterative Generative Optimization with LLMs
Generative optimization uses large language models (LLMs) to iteratively improve artifacts (such as code, workflows or prompts) using execution feedback. It is a promising approach to building self...
Allen Nie, Xavier Daull, Zhiyi Kuang, Abhinav Akkiraju, Anish Chaudhuri, Max Piasevoli, Ryan Rong...
From Untamed Black Box to Interpretable Pedagogical Orchestration: The Ensemble of Specialized LLMs Architecture for Adaptive Tutoring
Monolithic Large Language Models (LLMs) used in educational dialogue often behave as "black boxes," where pedagogical decisions are implicit and difficult to audit, frequently violating instruction...
Nizam Kadir
CoCR-RAG: Enhancing Retrieval-Augmented Generation in Web Q&A via Concept-oriented Context Reconstruction
Retrieval-augmented generation (RAG) has shown promising results in enhancing Q&A by incorporating information from the web and other external sources. However, the supporting documents retrieved f...
Kaize Shi, Xueyao Sun, Qika Lin, Firoj Alam, Qing Li, Xiaohui Tao, Guandong Xu
Can we generate portable representations for clinical time series data using LLMs?
Deploying clinical ML is slow and brittle: models that work at one hospital often degrade under distribution shifts at the next. In this work, we study a simple question -- can large language model...
Zongliang Ji, Yifei Sun, Andre Amaral, Anna Goldenberg, Rahul G. Krishnan
Diet Your LLM: Dimension-wise Global Pruning of LLMs via Merging Task-specific Importance Score
Large language models (LLMs) have demonstrated remarkable capabilities, but their massive scale poses significant challenges for practical deployment. Structured pruning offers a promising solution...
Jimyung Hong, Jaehyung Kim
SafeFlow: Real-Time Text-Driven Humanoid Whole-Body Control via Physics-Guided Rectified Flow and Selective Safety Gating
Recent advances in real-time interactive text-driven motion generation have enabled humanoids to perform diverse behaviors. However, kinematics-only generators often exhibit physical hallucinations...
Hanbyel Cho, Sang-Hun Kim, Jeonguk Kang, Donghan Koo
BRIDG-Q: Barren-Plateau-Resilient Initialisation with Data-Aware LLM-Generated Quantum Circuits
Quantum circuit initialisation is a key bottleneck in variational quantum algorithms (VQAs), strongly impacting optimisation stability and convergence. Recent work shows that large language models ...
Ngoc Nhi Nguyen, Thai T Vu, John Le, Hoa Khanh Dam, Dung Hoang Duong, Dinh Thai Hoang
SilLang: Improving Gait Recognition with Silhouette Language Encoding
Gait silhouettes, which can be encoded into binary gait codes, are widely adopted to representing motion patterns of pedestrian. Recent approaches commonly leverage visual backbones to encode gait ...
Ruiyi Zhan, Guozhen Peng, Canyu Chen, Jian Lei, Annan Li
Grounding Arabic LLMs in the Doha Historical Dictionary: Retrieval-Augmented Understanding of Quran and Hadith
Large language models (LLMs) have achieved remarkable progress in many language tasks, yet they continue to struggle with complex historical and religious Arabic texts such as the Quran and Hadith....
Somaya Eltanbouly, Samer Rashwani
Policy-Guided Threat Hunting: An LLM enabled Framework with Splunk SOC Triage
With frequently evolving Advanced Persistent Threats (APTs) in cyberspace, traditional security solutions approaches have become inadequate for threat hunting for organizations. Moreover, SOC (Secu...
Rishikesh Sahay, Bell Eapen, Weizhi Meng, Md Rasel Al Mamun, Nikhil Kumar Dora, Manjusha Sumasada...
From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments
The remarkable progress of reinforcement learning (RL) is intrinsically tied to the environments used to train and evaluate artificial agents. Moving beyond traditional qualitative reviews, this wo...
Lijing Luo, Yiben Luo, Alexey Gorbatovski, Sergey Kovalchuk, Xiaodan Liang
Leave No Stone Unturned: Uncovering Holistic Audio-Visual Intrinsic Coherence for Deepfake Detection
The rapid progress of generative AI has enabled hyper-realistic audio-visual deepfakes, intensifying threats to personal security and social trust. Most existing deepfake detectors rely either on u...
Jielun Peng, Yabin Wang, Yaqi Li, Long Kong, Xiaopeng Hong
Towards Energy-aware Requirements Dependency Classification: Knowledge-Graph vs. Vector-Retrieval Augmented Inference with SLMs
The continuous evolution of system specifications necessitates frequent evaluation of conflicting requirements, a process that is traditionally labour intensive. Although large language models (LLM...
Shreyas Patil, Pragati Kumari, Novarun Deb, Gouri Ginde
VOLMO: Versatile and Open Large Models for Ophthalmology
Vision impairment affects millions globally, and early detection is critical to preventing irreversible vision loss. Ophthalmology workflows require clinicians to integrate medical images, structur...
Zhenyue Qin, Younjoon Chung, Elijah Lee, Wanyue Feng, Xuguang Ai, Serina Applebaum, Minjie Zou, Y...
From AI Assistant to AI Scientist: Autonomous Discovery of LLM-RL Algorithms with LLM Agents
Discovering improved policy optimization algorithms for language models remains a costly manual process requiring repeated mechanism-level modification and validation. Unlike simple combinatorial c...
Sirui Xia, Yikai Zhang, Aili Chen, Siye Wu, Siyu Yuan, Yanghua Xiao
Dialogue to Question Generation for Evidence-based Medical Guideline Agent Development
Evidence-based medicine (EBM) is central to high-quality care, but remains difficult to implement in fast-paced primary care settings. Physicians face short consultations, increasing patient loads,...
Zongliang Ji, Ziyang Zhang, Xincheng Tan, Matthew Thompson, Anna Goldenberg, Carl Yang, Rahul G. ...
Self-Distillation for Multi-Token Prediction
As Large Language Models (LLMs) scale up, inference efficiency becomes a critical bottleneck. Multi-Token Prediction (MTP) could accelerate LLM inference by predicting multiple future tokens in par...
Guoliang Zhao, Ruobing Xie, An Wang, Shuaipeng Li, Huaibing Xie, Xingwu Sun
AnalogAgent: Self-Improving Analog Circuit Design Automation with LLM Agents
Recent advances in large language models (LLMs) suggest strong potential for automating analog circuit design. Yet most LLM-based approaches rely on a single-model loop of generation, diagnosis, an...
Zhixuan Bao, Zhuoyi Lin, Jiageng Wang, Jinhai Hu, Yuan Gao, Yaoxin Wu, Xiaoli Li, Xun Xu
DUPLEX: Agentic Dual-System Planning via LLM-Driven Information Extraction
While Large Language Models (LLMs) provide semantic flexibility for robotic task planning, their susceptibility to hallucination and logical inconsistency limits their reliability in long-horizon d...
Keru Hua, Ding Wang, Yaoying Gu, Xiaoguang Ma
Latent Bias Alignment for High-Fidelity Diffusion Inversion in Real-World Image Reconstruction and Manipulation
Recent research has shown that text-to-image diffusion models are capable of generating high-quality images guided by text prompts. But can they be used to generate or approximate real-world images...
Weiming Chen, Qifan Liu, Siyi Liu, Yushun Tang, Yijia Wang, Zhihan Zhu, Zhihai He