Ax Zihe Yan, Jiaping Gui, Zhuosheng Zhang, Gongshen Liu 4/8/2026

LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI Agents

LaSM defends GUI agents against pop-up injection attacks using layer-wise scaling on multimodal LLMs for safer screen interaction.

Ax Joosung Lee, Cheonbok Park, Hwiyeol Jo, Jeonghoon Kim, Joonsuk Park, Kang Min Yoo 4/8/2026

Enhancing Hallucination Detection via Future Context

Framework for detecting LLM hallucinations in black-box generators by leveraging future context patterns.

Ax Wangsong Yin, Daliang Xu, Mengwei Xu, Gang Huang, Xuanzhe Liu 4/8/2026

ShadowNPU: System and Algorithm Co-design for NPU-Centric On-Device LLM Inference

ShadowNPU enables efficient on-device LLM inference by redesigning attention operator for NPU execution, improving privacy and performance.

Ax Junsong Li, Jie Zhou, Bihao Zhan, Yutao Yang, Qianjun Pan, Shilian Chen, Tianyu Huai, Xin Li, Qin Chen, Liang He 4/8/2026

LifeAlign: Lifelong Alignment for Large Language Models with Memory-Augmented Focalized Preference Optimization

LifeAlign framework for lifelong LLM alignment across sequential tasks using memory-augmented preference optimization without catastrophic forgetting.

Ax Ziyi Liu 4/8/2026

A State-Update Prompting Strategy for Efficient and Robust Multi-turn Dialogue

Training-free prompt engineering strategy using state reconstruction and history reminders for efficient multi-turn LLM dialogue.

Ax Suhas Suresh Bharadwaj, Prerana Ramkumar 4/8/2026

Chiplet-Based RISC-V SoC with Modular AI Acceleration

Chiplet-based RISC-V SoC architecture with modular AI acceleration for edge AI devices with improved yield and efficiency.

Ax Xingyu Shen, Yingfa Chen, Zhen Leng Thai, Xu Han, Zhiyuan Liu, Maosong Sun 4/8/2026

StateX: Enhancing RNN Recall via Post-training State Expansion

StateX post-training method improves recall ability in RNNs and state-space models for long-context information retrieval.

Ax Hemang Jain, Shailender Goyal, Divyansh Pandey, Karthik Vaidhyanathan 4/8/2026

Dissecting Transformers: A CLEAR Perspective towards Green AI

Component-level energy assessment framework analyzing transformer efficiency to enable green AI development.

Ax Noor Islam S. Mohammad, Md Muntaqim Meherab 4/8/2026

Reveal-to-Revise: Explainable Bias-Aware Generative Modeling with Multimodal Attention

Explainable bias-aware generative framework combining multimodal attention, attribution methods, and iterative feedback for fair generation.

Ax Junhoo Lee, Seungyeon Kim, Nojun Kwak 4/8/2026

Unlocking the Potential of Diffusion Language Models through Template Infilling

Template Infilling conditioning strategy enables diffusion language models to handle flexible structural prompting beyond prefix-based generation.

Ax Xingrui Zhuo, Jiapu Wang, Gongqing Wu, Zhongyuan Wang, Jichen Zhang, Shirui Pan, Xindong Wu 4/8/2026

Knowledge Reasoning Language Model: Unifying Knowledge and Language for Inductive Knowledge Graph Reasoning

Knowledge Reasoning Language Model unifies language models with knowledge graphs for inductive reasoning over unknown entities and relations.

Ax Qing Yang, Zhenghao Liu, Yangfan Du, Pengcheng Huang, Tong Xiao 4/8/2026

RLAIF-SPA: Structured AI Feedback for Semantic-Prosodic Alignment in Speech Synthesis

RLAIF-SPA uses structured AI feedback to improve emotional expressiveness and semantic-prosodic alignment in text-to-speech synthesis.

Ax Afrozah Nadeem, Mark Dras, Usman Naseem 4/8/2026

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 4/8/2026

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 Jay Mohta, Kenan Emir Ak, Gwang Lee, Dimitrios Dimitriadis, Yan Xu, Mingwei Shen 4/8/2026

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 4/8/2026

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 4/8/2026

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 Oleksii Proniakin, Diego Fajardo, Ruslan Nazarenko, Razvan Marinescu 4/8/2026

Automatic Replication of LLM Mistakes in Medical Conversations

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

Ax Ruikang Zhang, Shuo Wang, Qi Su 4/8/2026

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 4/8/2026

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 4/8/2026

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 4/8/2026

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 4/8/2026

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 4/8/2026

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 4/8/2026

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 4/8/2026

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 4/8/2026

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 4/8/2026

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 Ehud Shapiro 4/8/2026

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 4/8/2026

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 4/8/2026

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 4/8/2026

"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 4/8/2026

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 4/8/2026

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 4/8/2026

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 4/8/2026

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 4/8/2026

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 4/8/2026

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 4/8/2026

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 4/8/2026

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 4/8/2026

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 4/8/2026

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 4/8/2026

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 4/8/2026

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 4/8/2026

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 4/8/2026

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 4/8/2026

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 Wei Zou, Mingwen Dong, Miguel Romero Calvo, Shuaichen Chang, Jiang Guo, Dongkyu Lee, Xing Niu, Xiaofei Ma, Yanjun Qi, Jiarong Jiang 4/8/2026

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 4/8/2026

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 4/8/2026

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.