Ax Mahmoud Abdelfattah, Hamid Nasiri, Peter Garraghan 29d ago

kNNGuard: Turning LLM Hidden Activations into a Training-Free Configurable Guardrail

kNNGuard: Training-free guardrail for LLMs using activation space and k-NN to detect unsafe/adversarial prompts without fine-tuning.

Ax Jian Xu, Delu Zeng, John Paisley, Qibin Zhao 29d ago

Ask the Right Comparison:Bias-Aware Bayesian Active Top-$k$ Ranking with LLM Judges

Bayesian active ranking method using LLM judges to identify top-k candidates while accounting for systematic biases and position effects.

Ax Yilie Huang, Wenpin Tang, Xun Yu Zhou 29d ago

ART for Diffusion Sampling: Continuous-Time Control and Actor-Critic Learning

ART: continuous-time control framework using actor-critic learning to optimize timestep allocation in score-based diffusion sampling.

Ax Jijie Zhang, Zhe Ren, Quan Zhang, Dandan Guo 29d ago

Bayesian Sparse Low-Rank Adaptation for Large Language Model Uncertainty Estimation

DALorRA: Bayesian sparse low-rank adaptation method for uncertainty quantification in fine-tuned LLMs to improve trustworthy deployment.

Ax Xavier Mart\'inez-Lua\~na, Alba Gude-Santos, Manuel Fern\'andez-Veiga, Rebeca P. D\'iaz-Redondo 29d ago

Privacy-Preserving and Verifiable Approximate Distributed Coded Computing

Privacy-preserving distributed coded computing framework addressing privacy leakage and malicious manipulation in federated and decentralized learning.

Ax Ziyun Qiao, Yue Min, Ruining Chen, Yujun Li 29d ago

HERMES: A Multi-Granularity Labeling Substrate for Pre-training Data Mixtures

HERMES provides hierarchical multi-granularity labeling system for organizing pre-training data mixtures across different semantic axes.

Ax Max Weltevrede, Matthijs T. J. Spaan, Wendelin B\"ohmer 29d ago

Generalization in offline RL: The structure is more important than the amount of pessimism

Study of generalization in offline reinforcement learning showing structure of pessimism matters more than degree for contextual MDPs.

Ax Ruihang Li, Mengde Xu, Shuyang Gu, Leigang Qu, Fuli Feng, Han Hu, Wenjie Wang 29d ago

Optimizing Visual Generative Models via Distribution-wise Rewards

Framework for training visual generative models using distribution-wise rewards to prevent reward hacking and improve image diversity.

Ax Juliette Decugis, Fabian Gloeckle, Francis Bach, Taco Cohen, Gabriel Synnaeve 29d ago

DecompRL: Solving Harder Problems by Learning Modular Code Generation

DecompRL uses reinforcement learning to teach LLMs modular code generation for solving hard problems by decomposing into solvable subcomponents.

Ax Zhuowei Chen, Liwei Chen, Christian Schunn, Raquel Coelho, Xiang Lorraine Li 29d ago

Neuron-Aware Active Few-Shot Learning for LLMs

Active few-shot learning method for LLMs that identifies valuable unlabeled samples for annotation to reduce human labeling costs and improve domain-specific adaptation.

Ax Quoc Bao Phan, Tuy Tan Nguyen 29d ago

QFedAgent: Quantum-Enhanced Personalized Federated Learning for Multi-Agent Activity Recognition

Federated learning with quantum enhancement for multi-agent activity recognition in distributed robotic systems addressing non-IID heterogeneous sensor data.

Ax Xuanyu Chen, Nan Yang, Shuai Wang, Dong Yuan 29d ago

Understanding the Robustness of Distributed Self-Supervised Learning Frameworks Against Non-IID Data

Theoretical analysis of distributed self-supervised learning robustness under non-IID data heterogeneity in decentralized settings.

Ax Zhuowei Chen, Xiang Lorraine Li 29d ago

Neuron-Aware Data Selection for Annotation-Free LLM Self-Distillation

Neuron-aware data selection method for annotation-free LLM self-distillation in specialized domains without human-labeled supervision.

Ax Gil Harari, Yoel Zimmermann, Ola Tangen Kulseng, Laura Zichi, Chuin Wei Tan, Marc L. Descoteaux, Boris Kozinsky 29d ago

Beyond Adam: SOAP and Muon for Faster, Label-Efficient Training of Machine Learning Interatomic Potentials

Compares alternative optimizers (SOAP, Muon) to Adam for training machine learning interatomic potentials for scientific simulation.

Ax Yunhe Li, Hao Shi, Wenhao Liu, Mengzhe Ruan, Hanxu Hou, Zhongxiang Dai, Shuang Qiu, Linqi Song 29d ago

DemoPSD: Disagreement-Modulated Policy Self-Distillation

On-policy self-distillation for LLMs using disagreement-modulated approach to improve reasoning while reducing overfitting and improving cross-domain generalization.

Ax Wentao Zhang, Liliana Hotsko, Woojeong Kim, Pengyu Nie, Stuart Shieber, Yuntian Deng 29d ago

Program-as-Weights: A Programming Paradigm for Fuzzy Functions

Fuzzy-function programming paradigm compiling natural language specifications into locally-executable neural artifacts as alternative to LLM APIs.

Ax Firoz Shaik, Mateus Pican\c{c}o Lima Gomes, Tanvir Aumi, Jingci Wang, Milos Milunovic, Filip Basara, Ivana Jovanovic, Vishwas Suryanarayanan, Neha Nandan Kenkare, Weiyao Xie, Zhipeng Han, Zheng Zhang, Waleed Shahid, Jay Rathi, Russell Scherer, Thong Q. Nguyen, Michael Bentley, Tamara Stankovic, Rasika Chakravarthy, Vishal Chowdhary 29d ago

Office Comprehension Benchmark

Office Comprehension Bench: first benchmark for evaluating LLM systems on Word, Excel, and PowerPoint document understanding.

Ax Clemens Kinn, Philipp Petersen 29d ago

Fast approximation and learning of binary classification tasks in o-minimal structures using ReLU neural networks

Theoretical analysis of ReLU neural network approximation for binary classification over o-minimal definable sets.

Ax Aizierjiang Aiersilan 29d ago

Benchmarking Federated Learning and Knowledge Distillation for Point Cloud Classification

Benchmark comparing 13 federated learning and 10 knowledge distillation algorithms for 3D point cloud classification on edge devices.

Ax Qijun Chen, Shaofan Li 29d ago

eXact-Prior Variational Autoencoder (X-VAE): Learning Data-Adaptive Gaussian Mixture Priors for Latent Distributions

X-VAE: variational autoencoder framework learning data-adaptive Gaussian mixture priors instead of standard isotropic priors.

Ax Cedric Fitiavana Raelijohn, S\'ebastien Gambs, Jean-Francois Rajotte 29d ago

Embedding Inference Attack

Research on black-box embedding inference attacks against dense IR systems without knowledge of target embedding models.

Ax Yanxiong Li, Jiaxin Tan, Qianqian Li, Guoqing Chen, Sen Huang, Tuomas Virtanen 29d ago

Few-Shot Open-Set Audio Classification Using Attention Information-Fused Prototypes

Research on few-shot audio classification handling unseen classes with attention-based prototype methods.

Ax Jiefei Liu, Abu Saleh Md Tayeen, Pratyay Kumar, Qixu Gong, Wenbin Jiang, Huiping Cao, Satyajayant Misra, Jayashree Harikumar 29d ago

Generative AI and Federated Learning for Intrusion Detection Systems: A Survey

Survey of generative AI and federated learning approaches for intrusion detection systems in IoT and distributed networks.

Ax Felix J. Beckmann, Jo\~ao F. Bravo 29d ago

Ravines in quantum cost landscapes: opportunities for improved VQA predictions

Research paper on quantum cost landscape geometry and optimization paths in variational quantum algorithms using nudged elastic band methods.

Ax Zihao Qi, Christopher Earls 29d ago

Mechanistic Interpretability and Causal Feature Steering of Neural Quantum States via Sparse Autoencoders

Research paper analyzing neural quantum states using sparse autoencoders for mechanistic interpretability and causal feature steering.

Ax Longfeng Wu, Yao Zhou, Tong Zeng, Zhimin Peng, Bhanu Pratap Singh Rawat, Lecheng Zheng, Giovanni Seni, Dawei Zhou 29d ago

Bi-NAS: Towards Effective and Personalized Explanation for Recommender Systems via Bi-Level Neural Architecture Search

Bi-NAS: bi-level neural architecture search for generating personalized and effective explanations in recommender systems.

Ax Parv Agarwal, Asif Ekbal 29d ago

GPUAlert: A Zero-Instrumentation Process-Boundary Monitor for Diagnosing GPU Training-Job Failures

GPUAlert: zero-instrumentation process-boundary monitor for diagnosing GPU training job failures without modifying training scripts.

Ax Yunfu Deng, Josiah P. Hanna 29d ago

BIFROST: Bridging Invariant Feature Representation for Observation-space Sim2Real Transfer

BIFROST: sim-to-real transfer method for robot policy learning that learns invariant feature representations addressing both visual and kinematic domain gaps.

Ax Samuel Schapiro, Core Francisco Park, Felix Sosa, Lav R. Varshney 29d ago

CreativityNeuro: Steering Language Model Weights to Improve Divergent Thinking and Reduce Mode Collapse

CreativityNeuro: data-free method using contrastive weight steering to enhance divergent thinking in LLMs and reduce mode collapse on open-ended generation.

Ax Max Van Puyvelde, Halil Ibrahim Gulluk, Wim Van Criekinge, Olivier Gevaert 29d ago

Discrete Diffusion Language Models for Interactive Radiology Report Drafting

Adapts mixture-of-experts diffusion language model DiffusionGemma-26B for medical radiology report generation and benchmarks against autoregressive baseline.

Ax Ye Liu, Srijan Bansal, Bo Pang, Yang Li, Zeyu Leo Liu, Yifei Ming, Zixuan Ke, Shafiq Joty, Semih Yavuz 29d ago

Procedural Memory Distillation: Online Reflection for Self-Improving Language Models

Procedural Memory Distillation: method for language models to retain and reuse procedural information across episodes for self-improvement through online reflection.

Ax Hongyang He, Jiuming Liu, Victor Sanchez 29d ago

Revisiting Chain-of-Thought Reasoning under Limited Supervision: Semi-supervised Chain-of-Thought Learning

Semi-CoT: framework for semi-supervised chain-of-thought learning that reuses generated reasoning traces as learning signals to improve LLM reasoning capabilities.

Ax Ren\'e Carmona, Mathieu Lauri\`ere 29d ago

Mean Field Reinforcement Learning

Monograph introducing mean field reinforcement learning through Markov decision processes and large-population stochastic control with mathematical framework.

Ax David Courtis, Wenhao Li, Scott Sanner 29d ago

OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration

OPINE-World: programmatic world modeling using LLMs and counterexample-guided synthesis to generate data-efficient, reusable environment models for agent adaptation.

Ax Jinliang Xu, Liping Ma 29d ago

MMAO-Cls: Metabolic Multi-Agent Optimization for Joint Feature Selection and Classifier Tuning

Proposes MMAO-Cls using metabolic multi-agent optimization as outer-loop optimizer for joint feature selection and classifier hyperparameter tuning.

Ax Zhaoyan Sun, Shan Zhong, Daizhou Wen, Jiaxing Han, Guoliang Li, Ying Yan, Peng Zhang, Yu Su, Xiang Qi, Baolin Sun, Chengyuan Yang, Tao Fang, Huaiyu Ruan 29d ago

AgenticDataBench: A Comprehensive Benchmark for Data Agents

AgenticDataBench: benchmark for evaluating LLM-based data agents on automating data science workflows including data wrangling, analysis, and visualization tasks.

Ax Mona Rajhans, Vishal Khawarey 29d ago

Beyond Gradient-Based Attacks: Adversarial Robustness and Explainability Stability in Cybersecurity Classifiers

Studies adversarial robustness and explainability stability of cybersecurity classifiers using SHAP-based explanations across multiple datasets and attack methods.

Ax Joshua Penman 29d ago

Epistemic Goggles: A Pretrained Module that Induces an Epistemic Frame via Gradient Editing

Introduces Goggles, a learned module using gradient editing to improve language models' ability to recognize fictional content, addressing the negation neglect problem.

Ax Zongxia Li, Dawei Liu, Fuxiao Liu, Yuhang Zhou, Xiyang Wu, Jingxi Chen, Jing Xie, Xiaomin Wu, Lichao Sun 29d ago

COMFYCLAW: Self-Evolving Skill Harnesses for Image Generation Workflows

COMFYCLAW: agentic system with self-evolving skill harnesses for image generation workflows, enabling agents to recall patterns and user preferences from prior runs.

Ax Stefano Masini, Cecilia Viscardi, Michela Baccini 29d ago

Full Bayesian Reinforcement Learning via LF-IBIS

Full Bayesian reinforcement learning approach via Likelihood-Free Iterative Bayesian Importance Sampling for data-scarce settings.

Ax Andikawati P Widjaja, Yongjun Kim, Hyounghun Kim, Jaeho Lee 29d ago

PARTREP: Learning What to Repeat for Decoder-only LLMs

PARTREP method enabling decoder-only LLMs to learn selective prompt repetition patterns, improving reasoning by redistributing contextual grounding across positions.

Ax Wenchen Han, Gingfung Matthew Yeung, Marco Barletta, William Toner, Amory Hoste, Adam Barker 29d ago

Lynx: Progressive Speculative Quantization for accelerating KV Transfer in Long-Context Inference

Lynx: progressive speculative KV cache quantization technique for accelerating long-context LLM inference in retrieval-augmented generation and agentic systems.

Ax Peng Yun, Shouwang Huang, Hao Li, Jinxi Li, Jianan Wang, Bo Yang 29d ago

PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation

PhysMani framework coupling physics-principled 3D Gaussian world model with action policy for dynamic object manipulation in embodied AI.

Ax Jan Drchal 29d ago

Object Aligner: A Configurable JSON Schema Similarity Score for Graphs, Applied to LLM Prompt Optimization

Object Aligner: configurable JSON schema similarity scoring for measuring LLM output alignment with structured schemas, enabling agentic planning and tool calling evaluation.

Ax Sofiane Ouaari, Kevin Vorwalder, Nico Pfeifer 29d ago

Assessing VLM Reliability for Medical Image Quality Evaluation Under Corruption and Bias

Evaluation of Vision-Language Model reliability for medical image quality assessment under image corruption and demographic bias.

Ax Ya Gao, Pekka Marttinen 29d ago

Evidence-State Rewards for Long-Context Reasoning

Maven RL framework with editable evidence memory for long-context reasoning, rewarding intermediate evidence state changes rather than just final answers.

Ax Navaneeth Sangameswaran, Preetham S, Ashmiya Lenin 29d ago

HaloGuard 1.0: An Open Weights Constitutional Classifier for Multilingual AI Safety

Open-weights constitutional classifier for multilingual AI safety filtering, achieving SOTA on prompt-safety benchmarks at 1/10th the size of competing models.

Ax Tien-Huy Nguyen, Minh-Nhat Nguyen, Nguyen Nhat Huy, Hung Viet Nguyen, Huy Nguyen Minh Nhat, Thanh-Huy Nguyen, Cuong Tuan Nguyen, Hoang M. Le, Dat Nguyen, Phat Kim Huynh, Min Xu, Ulas Bagci 29d ago

ESC: Emotional Self-Correction for Reliable Vision-Language Models

Emotional Self-Correction method improves vision-language model reliability by activating latent self-correction without post-training.

Ax Samiha A. Ismail, Fan X. Chen, Ali Merali 29d ago

A rubric-based controlled comparison of frontier language models on expert-authored clinical reasoning tasks

Evaluates frontier LLMs on expert-authored clinical reasoning scenarios, showing open-ended medical performance remains unsolved with 32% hard subset score.

Ax Preston Pitzer, Anish Pradhan, Harpreet S. Dhillon 29d ago

Fourier Preconditioning for Neural Feature Learning

Proposes Fourier-based preconditioning for mutual information-inspired feature learning, proving H-Score invariance properties.