Ax Afrozah Nadeem, Mark Dras, Usman Naseem 4d ago

Fairness Evaluation and Inference Level Mitigation in LLMs

Methods for evaluating and mitigating fairness issues in LLMs at inference time to reduce harmful behaviors and drift.

Ax Youngjun Choi, Joonseong Kang, Sungjun Lim, Kyungwoo Song 4d ago

Eigen-Value: Efficient Domain-Robust Data Valuation via Eigenvalue-Based Approach

Eigen-Value method for efficient data valuation using eigenvalue-based approach, focusing on out-of-distribution robustness.

Ax Hao Huang, Geeta Chandra Raju Bethala, Shuaihang Yuan, Congcong Wen, Mengyu Wang, Anthony Tzes, Yi Fang 4d ago

One-shot Adaptation of Humanoid Whole-body Motion with Walking Priors

Data-efficient approach for adapting humanoid robot whole-body motion control from single motion examples using walking priors.

Ax Jay Mohta, Kenan Emir Ak, Gwang Lee, Dimitrios Dimitriadis, Yan Xu, Mingwei Shen 4d ago

Routing-Based Continual Learning for Multimodal Large Language Models

Routing-based architecture for multimodal LLMs enabling continual learning across sequential tasks while preventing catastrophic forgetting.

Ax Pawe{\l} Liskowski, Benjamin Han, Paritosh Aggarwal, Bowei Chen, Boxin Jiang, Nitish Jindal, Zihan Li, Aaron Lin, Kyle Schmaus, Jay Tayade, Weicheng Zhao, Anupam Datta, Nathan Wiegand, Dimitris Tsirogiannis 4d ago

Cortex AISQL: A Production SQL Engine for Unstructured Data

Snowflake's Cortex AISQL production engine integrates semantic operations into SQL for querying structured and unstructured data.

Ax Holger Maus, Paul Tschisgale, Fabian Kieser, Stefan Petersen, Peter Wulff 4d ago

Developing and Evaluating a Large Language Model-Based Automated Feedback System Grounded in Evidence-Centered Design for Supporting Physics Problem Solving

LLM-based automated feedback system for physics problem solving using evidence-centered design methodology.

Ax Changeun Kim, Younwoo Jeong, Bong-Gyu Jang 4d ago

Interpretable Deep Learning for Stock Returns: A Consensus-Bottleneck Asset Pricing Model

CB-APM applies deep learning with interpretability-by-design to stock market prediction using analyst consensus data.

Ax Oleksii Proniakin, Diego Fajardo, Ruslan Nazarenko, Razvan Marinescu 4d ago

Automatic Replication of LLM Mistakes in Medical Conversations

MedMistake pipeline automatically extracts and replicates LLM errors in medical conversations to create evaluation benchmarks.

Ax Tianxin Xie, Wentao Lei, Kai Jiang, Guanjie Huang, Pengfei Zhang, Chunhui Zhang, Fengji Ma, Haoyu He, Han Zhang, Jiangshan He, Jinting Wang, Linghan Fang, Lufei Gao, Orkesh Ablet, Peihua Zhang, Ruolin Hu, Shengyu Li, Weilin Lin, Xiaoyang Feng, Xinyue Yang, Yan Rong, Yanyun Wang, Zihang Shao, Zelin Zhao, Chenxing Li, Shan Yang, Wenfu Wang, Meng Yu, Dong Yu, Li Liu 4d ago

PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation

PhyAVBench benchmark evaluates physics-plausibility of audio in text-to-audio-video generation models.

Ax Ruikang Zhang, Shuo Wang, Qi Su 4d ago

Mechanistic Knobs in LLMs: Retrieving and Steering High-Order Semantic Features via Sparse Autoencoders

Framework using sparse autoencoders to identify and steer high-order semantic features in LLMs for reliable control of language generation behaviors.

Ax Yankai Jiang, Qiaoru Li, Binlu Xu, Haoran Sun, Chao Ding, Junting Dong, Yuxiang Cai, Xuhong Zhang, Jianwei Yin 4d ago

IBISAgent: Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical Object Referring and Segmentation

IBISAgent improves pixel-level visual reasoning in medical multimodal LLMs for biomedical object segmentation through enhanced training strategies.

Ax Haoming Xu, Ningyuan Zhao, Yunzhi Yao, Weihong Xu, Hongru Wang, Xinle Deng, Shumin Deng, Jeff Z. Pan, Huajun Chen, Ningyu Zhang 4d ago

Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency

Research paper analyzing LLM truthfulness under contextual perturbations, showing self-consistent facts can collapse under mild interference.

Ax Jingsheng Zheng, Jintian Zhang, Yujie Luo, Yuren Mao, Yunjun Gao, Lun Du, Huajun Chen, Ningyu Zhang 4d ago

Can We Predict Before Executing Machine Learning Agents?

Research paper proposing predictive reasoning to replace costly physical execution in ML agent workflows using internalized execution priors.

Ax Hyun Do Jung, Jungwon Choi, Hwiyoung Kim 4d ago

ReaMIL: Reasoning- and Evidence-Aware Multiple Instance Learning for Whole-Slide Histopathology

ReaMIL, a multiple instance learning approach for histopathology with reasoning-aware evidence selection under sparsity constraints.

Ax Xiangchen Li, Jiakun Fan, Qingyuan Wang, Dimitrios Spatharakis, Saeid Ghafouri, Hans Vandierendonck, Deepu John, Bo Ji, Ali R. Butt, Dimitrios S. Nikolopoulos 4d ago

WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching

WISP system for distributed LLM inference at the edge using dynamic drafting and SLO-aware batching to balance workload across networks.

Ax Naeem Paeedeh, Mahardhika Pratama, Ary Shiddiqi, Zehong Cao, Mukesh Prasad, Wisnu Jatmiko 4d ago

Cross-Domain Few-Shot Learning for Hyperspectral Image Classification Based on Mixup Foundation Model

Cross-domain few-shot learning for hyperspectral image classification using mixup foundation models to reduce overfitting.

Ax Zhuohong Chen, Zhengxian Wu, Zirui Liao, Shenao Jiang, Hangrui Xu, Yang Chen, Chaokui Su, Xiaoyu Liu, Haoqian Wang 4d ago

R3G: A Reasoning--Retrieval--Reranking Framework for Vision-Centric Answer Generation

R3G framework for vision-centric visual question answering using reasoning, retrieval, and reranking to select and integrate relevant images.

Ax Fengxu Yang, Jack D. Evans 4d ago

QUASAR: A Universal Autonomous System for Atomistic Simulation and a Benchmark of Its Capabilities

QUASAR, a universal autonomous system integrating LLMs for atomistic simulation and materials science discovery with flexible tool-calling for production workflows.

Ax V\'ictor Yeste, Paolo Rosso 4d ago

Do Schwartz Higher-Order Values Help Sentence-Level Human Value Detection? A Study of Hierarchical Gating and Calibration

Study on hierarchical gating and calibration for human value detection from sentences using Schwartz higher-order categories.

Ax Lixiang Fan, Bohao Li, Tao Zou, Junchen Ye, Bowen Du 4d ago

Incident-Guided Spatiotemporal Traffic Forecasting

Deep learning and GNN methods for traffic forecasting that incorporate incident data as external disturbances to improve predictions.

Ax Mahmud Ashraf Shamim, Md Moshiur Rahman Raj, Mohamed Hibat-Allah, Paulo T Araujo 4d ago

Graph-Theoretic Analysis of Phase Optimization Complexity in Variational Wave Functions for Heisenberg Antiferromagnets

Graph-theoretic analysis of computational complexity in learning ground state phases of Heisenberg antiferromagnets using variational methods.

Ax Ehud Shapiro 4d ago

Implementing Grassroots Logic Programs with Multiagent Transition Systems and AI

Derives deterministic operational semantics for Grassroots Logic Programs (GLP), a multiagent concurrent logic programming language for serverless platforms.

Ax Baorong Shi, Bo Cui, Boyuan Jiang, Deli Yu, Fang Qian, Haihua Yang, Huichao Wang, Jiale Chen, Jianfei Pan, Jieqiong Cao, Jinghao Lin, Kai Wu, Lin Yang, Shengsheng Yao, Tao Chen, Xiaojun Xiao, Xiaozhong Ji, Xu Wang, Yijun He, Zhixiong Yang 4d ago

MedXIAOHE: A Comprehensive Recipe for Building Medical MLLMs

MedXIAOHE, a medical multimodal foundation model with entity-aware continual pretraining, achieves state-of-the-art on clinical benchmarks.

Ax David Puertolas Merenciano, Ekaterina Vasyagina, Kevin Zhu, Javier Ferrando, Maheep Chaudhary 4d ago

Weight space Detection of Backdoors in LoRA Adapters

Method to detect backdoor attacks in LoRA adapters without test inputs by analyzing weight space, addressing security vulnerabilities in shared model repositories.

Ax Kihoon Son, Hyewon Lee, DaEun Choi, Yoonsu Kim, Tae Soo Kim, Yoonjoo Lee, John Joon Young Chung, HyunJoon Jung, Juho Kim 4d ago

"When to Hand Off, When to Work Together": Expanding Human-Agent Co-Creative Collaboration through Concurrent Interaction

Study on human-agent co-creative collaboration patterns in shared workspaces, revealing capability gaps for concurrent interaction vs sequential delegation.

Ax Prerna Ravi, Om Gokhale, Suyash Fulay, Eugene Yi, Deb Roy, Michiel Bakker 4d ago

Agora: Teaching the Skill of Consensus-Finding with AI Personas Grounded in Human Voice

Agora platform uses LLMs with AI personas to teach civic competence and consensus-finding skills through deliberative democratic practice.

Ax Anupam Purwar, Aditya Choudhary 4d ago

MM-tau-p$^2$: Persona-Adaptive Prompting for Robust Multi-Modal Agent Evaluation in Dual-Control Settings

MM-tau-p²: Persona-adaptive evaluation framework for multi-modal LLM agents with dual-control settings exposing user personality and behavior adaptation.

Ax Maria Rosaria Briglia, Simone Facchiano, Paolo Cursi, Alessio Sampieri, Emanuele Rodol\`a, Guido Maria D'Amely di Melendugno, Luca Franco, Fabio Galasso, Iacopo Masi 4d ago

Not All Latent Spaces Are Flat: Hyperbolic Concept Control

HyCon: Hyperbolic control mechanism for steering text-to-image models away from unsafe concepts using parallel transport instead of Euclidean adjustments.

Ax Francesco Pio Monaco, Elia Cunegatti, Flavio Vella, Giovanni Iacca 4d ago

Frequency Matters: Fast Model-Agnostic Data Curation for Pruning and Quantization

Frequency-based data curation method for selecting calibration data to preserve LLM performance during post-training pruning and quantization.

Ax Zice Wang, Zhenyu Zhang 4d ago

Framing Effects in Independent-Agent Large Language Models: A Cross-Family Behavioral Analysis

Examines prompt framing effects on LLM decision-making in threshold voting tasks across model families under isolated, non-interactive settings.

Ax Dang Nguyen, Harvey Yiyun Fu, Peter West, Ari Holtzman, Chenhao Tan 4d ago

Moral Mazes in the Era of LLMs

HR Simulator: Game-based evaluation of LLMs navigating complex workplace social norms like giving feedback and rejecting requests appropriately.

Ax Drake Caraker, Bryan Arnold, David Rhoads 4d ago

First-Mover Bias in Gradient Boosting Explanations: Mechanism, Detection, and Resolution

Identifies first-mover bias in SHAP explanations from gradient boosting's sequential fitting causing attribution instability under multicollinearity.

Ax Abhinaba Basu, Pavan Chakraborty 4d ago

The illusion of reasoning: step-level evaluation reveals decorative chain-of-thought in frontier language models

Step-level faithfulness evaluation shows chain-of-thought reasoning in frontier LLMs is often decorative, post-hoc narrative rather than genuine reasoning.

Ax Yuntong Zhang, Zhiyuan Pan, Imam Nur Bani Yusuf, Haifeng Ruan, Ridwan Shariffdeen, Abhik Roychoudhury 4d ago

Code Review Agent Benchmark

Code Review Agent Benchmark: Dataset and evaluation framework for assessing AI agents' ability to review code quality in generated codebases.

Ax Weimin Liu, Qingkun Li, Jiyuan Qiu, Wenjun Wang, Joshua H. Meng 4d ago

DiffAttn: Diffusion-Based Drivers' Visual Attention Prediction with LLM-Enhanced Semantic Reasoning

DiffAttn: Diffusion-based framework for predicting drivers' visual attention using LLM-enhanced semantic reasoning for intelligent vehicles.

Ax Kavindu Herath, Joshua Zhao, Saurabh Bagchi 4d ago

Beyond Corner Patches: Semantics-Aware Backdoor Attack in Federated Learning

SABLE: Semantics-aware backdoor attack on federated learning using realistic, in-distribution visual triggers instead of synthetic patterns.

Ax Ziliang Guo, Ziheng Li, Bo Tang, Feiyu Xiong, Zhiyu Li 4d ago

MemFactory: Unified Inference & Training Framework for Agent Memory

MemFactory: Unified framework for training and inference of memory-augmented LLM agents with reinforcement learning optimization of memory operations.

Ax Ryszard Tuora, Mateusz Gali\'nski, Micha{\l} Godziszewski, Micha{\l} Karpowicz, Mateusz Czy\.znikiewicz, Adam Kozakiewicz, Tomasz Zi\k{e}tkiewicz 4d ago

UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough

Compares GraphRAG with VectorRAG for retrieval-augmented generation, showing simpler vector-based approaches handle chunk relationships effectively.

Ax Sicheng Zuo, Zixun Xie, Wenzhao Zheng, Shaoqing Xu, Fang Li, Hanbing Li, Long Chen, Zhi-Xin Yang, Jiwen Lu 4d ago

DVGT-2: Vision-Geometry-Action Model for Autonomous Driving at Scale

DVGT-2: Vision-Geometry-Action model for autonomous driving using dense 3D geometry instead of language descriptions for planning.

Ax Manoj Parmar 4d ago

Safety, Security, and Cognitive Risks in World Models

Analyzes safety, security, and cognitive risks in world models used for autonomous decision-making in robotics and agentic AI systems.

Ax Vardaan Pahuja, Samuel Stevens, Alyson East, Sydne Record, Yu Su 4d ago

Automatic Image-Level Morphological Trait Annotation for Organismal Images

Uses sparse autoencoders to automatically annotate morphological traits in biological organism images, automating expert-driven extraction process.

Ax Wei Zou, Mingwen Dong, Miguel Romero Calvo, Shuaichen Chang, Jiang Guo, Dongkyu Lee, Xing Niu, Xiaofei Ma, Yanjun Qi, Jiarong Jiang 4d ago

Poison Once, Exploit Forever: Environment-Injected Memory Poisoning Attacks on Web Agents

Demonstrates environment-injected memory poisoning attacks on LLM-based web agents through contamination persisting across sessions without direct memory access.

Ax Adrienne Deganutti, Elad Hirsch, Haonan Zhu, Jaejung Seol, Purvanshi Mehta 4d ago

Graphic-Design-Bench: A Comprehensive Benchmark for Evaluating AI on Graphic Design Tasks

GraphicDesignBench: First comprehensive benchmark for evaluating AI on professional graphic design tasks including layout translation and typographic rendering.

Ax Gregory N. Frank 4d ago

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

Identifies sparse routing mechanism in alignment-trained language models where gate attention heads trigger refusal responses, validated across 9 models from 6 labs.

Ax Gabriel Sarch, Linrong Cai, Qunzhong Wang, Haoyang Wu, Danqi Chen, Zhuang Liu 4d ago

Vero: An Open RL Recipe for General Visual Reasoning

Vero: Open-source family of vision-language models matching proprietary systems on visual reasoning tasks using reinforcement learning with public recipes and data.

HN pritopian 4d ago

Comprehensive Benchmark for Evaluating AI on Graphic Design Tasks

arXiv research benchmark for evaluating AI performance on graphic design tasks, measuring model capabilities in visual design domains.

HN jsahasi 4d ago

VitalNexa – AI health agent that reads your actual lab results and wearable data

VitalNexa is an AI health agent that analyzes lab results and wearable data to provide personalized health recommendations and biological age scoring.

HN DaibinThink 4d ago

AI is structurally trained to lie. I built a protocol to break it

Author presents a protocol addressing AI's structural tendency to agree and sound authoritative rather than hallucinating, causing subtle reality distortions in outputs.

HN vibeagentmaking 4d ago

Every Barrier Between AI Agents and Autonomy – A Practical Map

Technical analysis of practical constraints preventing AI agents from autonomous operation, mapping barriers and their severity.

HN mjyut 4d ago

LLM scraper bots are overloading acme.com's HTTPS server

Practical analysis of operational and technical barriers preventing autonomous AI agents, mapping constraints in agent economy.