Ax Tunazzina Islam 8d ago

Who Gets Which Message? Auditing Demographic Bias in LLM-Generated Targeted Text

Systematic analysis of demographic bias in LLM-generated targeted messaging across GPT-4o, Llama-3.3, and Mistral-Large models.

Ax Yupeng Cao, Chengyang He, Yangyang Yu, Ping Wang, K. P. Subbalakshmi 8d ago

MERMAID: Memory-Enhanced Retrieval and Reasoning with Multi-Agent Iterative Knowledge Grounding for Veracity Assessment

MERMAID: Multi-agent system for fact-checking using LLMs with memory-enhanced retrieval and iterative reasoning to assess veracity of claims.

Ax Zhanghao Hu, Qinglin Zhu, Di Liang, Hanqi Yan, Yulan He, Lin Gui 8d ago

Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregation

Agent memory system beyond RAG addressing agent-specific needs: bounded coherent dialogue retrieval with decoupling and aggregation.

Ax Ziwen Xu, Chenyan Wu, Hengyu Sun, Haiwen Hong, Mengru Wang, Yunzhi Yao, Longtao Huang, Hui Xue, Shumin Deng, Zhixuan Chu, Huajun Chen, Ningyu Zhang 8d ago

Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics

Unified framework explaining LLM steering methods (fine-tuning, LoRA, activation interventions) as dynamic weight updates from control signals.

Ax Changhyeok Choi, Yunheng Zou, Marcel M\"uller, Han Hao, Yeonghun Kang, Juan B. P\'erez-S\'anchez, Ignacio Gustin, Hanyong Xu, Andrew Wang, Mohammad Ghazi Vakili, Chris Crebolder, Al\'an Aspuru-Guzik, Varinia Bernales 8d ago

El Agente Estructural: An Artificially Intelligent Molecular Editor

El Agente Estructural multimodal agent for autonomous molecular geometry generation and manipulation using natural language and vision.

Ax Changjiang Jiang, Xinkuan Sha, Fengchang Yu, Jingjing Liu, Jian Liu, Mingqi Fang, Chenfeng Zhang, Wei Lu 8d ago

Fake-HR1: Rethinking Reasoning of Vision Language Model for Synthetic Image Detection

Fake-HR1 hybrid-reasoning model for synthetic image detection balancing chain-of-thought reasoning with computational efficiency.

Ax Jakub Breier, \v{S}tefan Ku\v{c}er\'ak, Xiaolu Hou 8d ago

The Weight of a Bit: EMFI Sensitivity Analysis of Embedded Deep Learning Models

Study of electromagnetic fault injection attacks on embedded deep learning models analyzing influence of number representations on resilience.

Ax Rong Fu, Muge Qi, Chunlei Meng, Shuo Yin, Kun Liu, Zhaolu Kang, Simon Fong 8d ago

AdvSynGNN: Structure-Adaptive Graph Neural Nets via Adversarial Synthesis and Self-Corrective Propagation

AdvSynGNN resilient graph neural network architecture addressing structural noise and non-homophilous topologies via adversarial synthesis.

Ax Rong Fu, Zijian Zhang, Kun Liu, Jiekai Wu, Xianda Li, Simon Fong 8d ago

SubQuad: Near-Quadratic-Free Structure Inference with Distribution-Balanced Objectives in Adaptive Receptor framework

SubQuad pipeline for immune repertoire analysis combining subquadratic retrieval with GPU-accelerated affinity kernels and multimodal fusion.

Ax Lin Huang, Arthur Jiang, XiaoLi Liu, Zion Wang, Jason Zhao, Chu Wang, HaoCheng Lu, ChengXiang Huang, JiaJun Cheng, YiYue Du, Jia Zhang 8d ago

UBio-MolFM: A Universal Molecular Foundation Model for Bio-Systems

UBio-MolFM universal molecular foundation model framework for bio-system simulation bridging quantum accuracy and biological scale.

Ax Arindam Khaled 8d ago

Pyramid MoA: A Probabilistic Framework for Cost-Optimized Anytime Inference

Pyramid MoA hierarchical mixture-of-agents architecture with decision-theoretic router for cost-optimized anytime LLM inference.

Ax Yifei Zhang, Xu Yang, Xiao Yang, Bowen Xian, Qizheng Li, Shikai Fang, Jingyuan Li, Jian Wang, Mingrui Xu, Weiqing Liu, Jiang Bian 8d ago

Reasoning as Gradient: Scaling MLE Agents Beyond Tree Search

Gome agent for machine learning engineering using gradient-based optimization instead of tree search, scaling LLM-based reasoning.

Ax Ziwen Xu, Kewei Xu, Haoming Xu, Haiwen Hong, Longtao Huang, Hui Xue, Ningyu Zhang, Yongliang Shen, Guozhou Zheng, Huajun Chen, Shumin Deng 8d ago

How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities

SteerEval benchmark for evaluating LLM controllability across language features, sentiment, and personality at multiple specification levels.

Ax Gyujun Jeong (School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA), Sungwon Cho (School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA), Minji Shon (School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA), Namhoon Kim (School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA), Woohyun Hwang (Semiconductor Research and Development, Samsung Electronics Co., Ltd, South Korea), Kwangyou Seo (Semiconductor Research and Development, Samsung Electronics Co., Ltd, South Korea), Suhwan Lim (Semiconductor Research and Development, Samsung Electronics Co., Ltd, South Korea), Wanki Kim (Semiconductor Research and Development, Samsung Electronics Co., Ltd, South Korea), Daewon Ha (Semiconductor Research and Development, Samsung Electronics Co., Ltd, South Korea), Prasanna Venkatesan (NVIDIA, Santa Clara, CA, USA), Kihang Youn (NVIDIA, Santa Clara, CA, USA), Ram Cherukuri (NVIDIA, Santa Clara, CA, USA), Yiyi Wang (NVIDIA, Santa Clara, CA, USA), Suman Datta (School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA), Asif Khan (School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA), Shimeng Yu (School of Electrical and Computer Engineering, Georgia Institute of Technology, GA, USA) 8d ago

Physics-informed AI Accelerated Retention Analysis of Ferroelectric Vertical NAND: From Day-Scale TCAD to Second-Scale Surrogate Model

Physics-informed surrogate model for ferroelectric NAND retention analysis reducing computational cost from day-scale to second-scale.

Ax Pranav Mantini, Shishir K. Shah 8d ago

BiCLIP: Domain Canonicalization via Structured Geometric Transformation

BiCLIP extends vision-language models to specialized domains via structured geometric transformation and domain canonicalization.

Ax Zhen Zhang, Jielei Chu, Tianrui Li 8d ago

Causally Sufficient and Necessary Feature Expansion for Class-Incremental Learning

Causally-informed feature expansion method for class-incremental learning addressing catastrophic forgetting through feature collision mitigation.

Ax Charles Ye, Jasmine Cui, Dylan Hadfield-Menell 8d ago

Prompt Injection as Role Confusion

Analysis of prompt injection attacks as role confusion where models infer text source by content style rather than origin.

Ax Yuanhe Zhang, Xinyue Wang, Zhican Chen, Weiliu Wang, Zilu Zhang, Zhengshuo Gong, Zhenhong Zhou, Kun Wang, Li Sun, Yang Liu, Sen Su 8d ago

Resource Consumption Threats in Large Language Models

Survey of resource consumption threats in LLMs including excessive generation attacks, resource efficiency requirements, and mitigation strategies.

Ax Gregory N. Frank 8d ago

Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails

Study of LLM alignment evaluation focusing on routing from concept detection to behavioral policy, using Chinese language models as case study.

Ax Shuwei Huang, Shizhuo Liu, Zijun Wei 8d ago

LPNSR: Optimal Noise-Guided Diffusion Image Super-Resolution Via Learnable Noise Prediction

Diffusion-based image super-resolution framework addressing inference efficiency vs reconstruction quality trade-off with learnable noise prediction.

Ax Junyi An, Xinyu Lu, Yun-Fei Shi, Li-Cheng Xu, Nannan Zhang, Chao Qu, Yuan Qi, Fenglei Cao 8d ago

Suiren-1.0 Technical Report: A Family of Molecular Foundation Models

Suiren-1.0 family of molecular foundation models for organic systems with 1.8B parameters pre-trained on 70M samples.

Ax Kejia Liu, Haoyang Zhou, Ruoyu Xu, Peicheng Wang, Mingli Song, Haofei Zhang 8d ago

Beyond Matching to Tiles: Bridging Unaligned Aerial and Satellite Views for Vision-Only UAV Navigation

Cross-view geo-localization method for UAV navigation in GNSS-denied environments using aerial and satellite image matching.

Ax Cl\'ement Hongler, Franck Gabriel, Valentin Hartmann, Arthur Renard, Andrew Emil 8d ago

Cognitive Training for Language Models: Towards General Capabilities via Cross-Entropy Games

Curriculum learning framework using cross-entropy games to automatically build general capabilities and discover skills in language models.

Ax Abhinaba Basu, Pavan Chakraborty 8d ago

Measuring and curing reasoning rigidity: from decorative chain-of-thought to genuine faithfulness

Introduces Step-Level Reasoning Capacity metric and LC-CoSR training method to measure and reduce reasoning rigidity in chain-of-thought reasoning.

Ax Shaobo Ju, Baiyang Song, Tao Chen, Jiapeng Zhang, Qiong Wu, Chao Chang, HuaiXi Wang, Yiyi Zhou, Rongrong Ji 8d ago

ForestPrune: High-ratio Visual Token Compression for Video Multimodal Large Language Models via Spatial-Temporal Forest Modeling

Training-free spatial-temporal token compression method for video MLLMs achieving high-ratio visual token reduction via forest modeling.

Ax Benjamin Lange 8d ago

Unilateral Relationship Revision Power in Human-AI Companion Interaction

Philosophical analysis of control dynamics and relational ethics in human-AI companion interactions examining provider authority.

Ax Yu Chen, Runkai Chen, Sheng Yi, Xinda Zhao, Xiaohong Li, Jianjin Zhang, Jun Sun, Chuanrui Hu, Yunyun Han, Lidong Bing, Yafeng Deng, Tianqiao Chen 8d ago

MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens

Memory-sparse attention mechanism enabling LLMs to scale context to 100M tokens through efficient memory modeling instead of full attention.

Ax Jiajian Huang, Dongliang Zhu, Zitong YU, Hui Ma, Jiayu Zhang, Chunmei Zhu, Xiaochun Cao 8d ago

DecepGPT: Schema-Driven Deception Detection with Multicultural Datasets and Robust Multimodal Learning

Multimodal deception detection using schema-driven approach with audiovisual analysis across multicultural datasets for forensics applications.

Ax Rishikesh Sahay, Bell Eapen, Weizhi Meng, Md Rasel Al Mamun, Nikhil Kumar Dora, Manjusha Sumasadan, Sumit Kumar Tetarave, Elyson De La Cruz 8d ago

Policy-Guided Threat Hunting: An LLM enabled Framework with Splunk SOC Triage

LLM-enabled threat hunting framework for SOC analysts integrating Splunk with policy-guided decision making for APT detection.

Ax Yunzhe Wang, Runhui Xu, Kexin Zheng, Tianyi Zhang, Jayavibhav Niranjan Kogundi, Soham Hans, Volkan Ustun 8d ago

GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents

Benchmark framework for evaluating multimodal LLMs as perceptual backbones for autonomous agents in 3D environments with decision-dense scenarios.

Ax Xuanpu Zhao, Zhentao Tan, Dianmo Sheng, Tianxiang Chen, Yao Liu, Yue Wu, Tao Gong, Qi Chu, Nenghai Yu 8d ago

Learning to Focus and Precise Cropping: A Reinforcement Learning Framework with Information Gaps and Grounding Loss for MLLMs

Reinforcement learning framework enabling multimodal LLMs to autonomously crop and focus on regions of interest for improved perception in complex visual scenes.

Ax Miaosen Luo, Zhenhao Yang, Jieshen Long, Jinghu Sun, Yichu Liu, Sijie Mai 8d ago

C2F-Thinker: Coarse-to-Fine Reasoning with Hint-Guided Reinforcement Learning for Multimodal Sentiment Analysis

Coarse-to-fine reasoning framework using reinforcement learning for interpretable multimodal sentiment analysis with MLLMs and hint-guided training.

Ax Jinliang Xu, Bingqi Li 8d ago

DarwinNet: An Evolutionary Network Architecture for Agent-Driven Protocol Synthesis

Bio-inspired self-evolving network architecture for autonomous agents using evolutionary approaches instead of static human-defined protocols.

Ax Ga\"etan Hadjeres, Marc Ferras, Khaled Koutini, Benno Weck, Alexandre Bittar, Thomas Hummel, Zineb Lahrici, Hakim Missoum, Joan Serr\`a, Yuki Mitsufuji 8d ago

Woosh: A Sound Effects Foundation Model

Open source sound effect foundation model from Sony AI with audio encoder/decoder and text-to-audio capabilities.

Ax Dun Yuan, Fuyuan Lyu, Ye Yuan, Weixu Zhang, Bowei He, Jiayi Geng, Linfeng Du, Zipeng Sun, Yankai Chen, Changjiang Han, Jikun Kang, Xi Chen, Haolun Wu, Xue Liu 8d ago

Beyond Message Passing: A Semantic View of Agent Communication Protocols

Framework analyzing agent communication protocols for LLM systems across three layers: communication, syntactic, and semantic. Systematically organizes 18 representative protocols.

Ax Zonghan Li, Feng Ji 8d ago

When simulations look right but causal effects go wrong: Large language models as behavioral simulators

Evaluates whether LLMs can infer causal intervention effects from natural language descriptions using behavioral simulation on climate-psychology interventions.

Ax Mengtian Li, Yuwei Lu, Feifei Li, Chenqi Gan, Zhifeng Xie, Xi Wang 8d ago

VERTIGO: Visual Preference Optimization for Cinematic Camera Trajectory Generation

Generative camera system using visual preference optimization for cinematic trajectory generation. Addresses framing and composition without director feedback loop.

Ax Hita Kambhamettu, Bhavana Dalvi Mishra, Andrew Head, Jonathan Bragg, Aakanksha Naik, Joseph Chee Chang, Pao Siangliulue 8d ago

LitPivot: Developing Well-Situated Research Ideas Through Dynamic Contextualization and Critique within the Literature Landscape

LitPivot: tool supporting iterative research idea development through dynamic literature contextualization and AI-driven critique.

Ax Lihao Sun, Lewen Yan, Xiaoya Lu, Andrew Lee, Jie Zhang, Jing Shao 8d ago

Valence-Arousal Subspace in LLMs: Circular Emotion Geometry and Multi-Behavioral Control

Method to identify valence-arousal emotional subspace in LLM representations for emotion steering and behavioral control.

Ax Nolan Platt, Sehrish Nizamani, Alp Tural, Elif Tural, Saad Nizamani, Andrew Katz, Yoonje Lee, Nada Basit 8d ago

Can LLMs Reason About Attention? Towards Zero-Shot Analysis of Multimodal Classroom Behavior

Privacy-preserving system using LLMs to analyze student attention in classroom videos without storing identifiable footage.

Ax Daniele Solombrino, Antonio Andrea Gargiulo, Adrian Robert Minut, Luca Zhou, Alessandro Zirilli, Emanuele Rodol\`a 8d ago

Zero-Shot Quantization via Weight-Space Arithmetic

Zero-shot quantization method using weight-space arithmetic to improve post-training quantization robustness across models.

Ax Michael Caosun, Sinan Aral 8d ago

The Augmentation Trap: AI Productivity and the Cost of Cognitive Offloading

Economic analysis of AI productivity gains showing sustained tool use erodes worker expertise over time.

Ax Benjamin Rombaut 8d ago

Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures

Taxonomy of LLM-based coding agent architectures via source-code analysis, categorizing control loops, tool definitions, and context strategies.

Ax Gregory N. Frank 8d ago

How Alignment Routes: Localizing, Scaling, and Controlling Policy Circuits in Language Models

Analysis of policy routing circuits in alignment-trained LLMs, localizing attention gates and amplifier heads controlling refusal behavior.

Ax Zheng Li, Jerry Cheng, Huanying Helen Gu 8d ago

StableTTA: Training-Free Test-Time Adaptation that Improves Model Accuracy on ImageNet1K to 96%

StableTTA: training-free test-time adaptation improving image classification accuracy via novel ensemble strategies.

Ax Shuzhen Bi, Mingzi Zhang, Zhuoxuan Li, Xiaolong Wang, Keqian Li, Aimin Zhou 8d ago

EduIllustrate: Towards Scalable Automated Generation Of Multimodal Educational Content

EduIllustrate: benchmark evaluating LLMs on automated generation of diagram-rich educational content combining visuals and reasoning.

Ax Honghao Fu, Miao Xu, Yiwei Wang, Dailing Zhang, Liu Jun, Yujun Cai 8d ago

VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG

VideoStir: retrieval-augmented generation system for understanding long videos with multimodal LLMs using spatio-temporal structure.

Ax Manish Bhatt, Sarthak Munshi, Vineeth Sai Narajala, Idan Habler, Ammar Al-Kahfah, Ken Huang, Joel Webb, Blake Gatto, Md Tamjidul Hoque 8d ago

The Defense Trilemma: Why Prompt Injection Defense Wrappers Fail?

Theoretical analysis proving limitations of continuous wrapper defenses against prompt injection attacks in LLMs.

Ax Zhixiong Zhao, Zukang Xu, Zhixuan Chen, Dawei Yang 8d ago

MoBiE: Efficient Inference of Mixture of Binary Experts under Post-Training Quantization

MoBiE: binarization framework for efficient inference in Mixture-of-Experts LLMs via post-training quantization.

Ax Benjamin J. Choi, Melanie Weber 8d ago

Latent Structure of Affective Representations in Large Language Models

Analysis of emotional representation geometry in LLM latent spaces for transparency and safety.