Isolater - Feed

Ax Stella Su, Marc Harary, Scott J. Rodig, William Lotter 8d ago

AdvDINO: Domain-Adversarial Self-Supervised Representation Learning for Spatial Proteomics

AdvDINO: domain-adversarial self-supervised learning framework for spatial proteomics to handle batch effects in biomedical imaging.

Ax Abolfazl Ansari, Delvin Ce Zhang, Nafis Irtiza Tripto, Dongwon Lee 8d ago

Echoes of Automation: The Increasing Use of LLMs in Newsmaking

Analysis of LLM use in newsmaking across 40,000+ articles using AI-text detectors, showing increased GenAI adoption in local and college media.

Ax Peiran Peng, Tingfa Xu, Liqiang Song, Mengqi Zhu, Yuqiang Fang, Jianan Li 8d ago

COXNet: Cross-Layer Fusion with Adaptive Alignment and Scale Integration for RGBT Tiny Object Detection

COXNet: cross-layer fusion network for detecting tiny objects in multimodal RGB-thermal imagery for surveillance and autonomous navigation.

Ax Po-Hsien Yu, Yu-Syuan Tseng, Shao-Yi Chien 8d ago

FedKLPR: KL-Guided Pruning-Aware Federated Learning for Person Re-Identification

FedKLPR: federated learning approach for person re-identification with KL-guided pruning to reduce communication overhead and handle non-IID data.

Ax Wenhong Zhu, Ruobing Xie, Rui Wang, Xingwu Sun, Di Wang, Pengfei Liu 8d ago

Proximal Supervised Fine-Tuning

Proximal SFT: supervised fine-tuning method using trust-region constraints to prevent capability deterioration when adapting foundation models to new tasks.

Ax Shvetank Prakash, Andrew Cheng, Olof Kindgren, Ashiq Ahamed, Graham Knight, Jed Kufel, Francisco Rodriguez, Arya Tschand, David Kong, Mariam Elgamal, Jerry Huang, Emma Chen, Gage Hills, Richard Price, Emre Ozer, Vijay Janapa Reddi 8d ago

Lifetime-Aware Design for Item-Level Intelligence at the Extreme Edge

FlexiFlow: lifetime-aware design framework for integrated computation in disposable products using flexible electronics with kHz speeds.

Ax Nolan Platt, Pragyansmita Nayak 8d ago

Multi-Model Synthetic Training for Mission-Critical Small Language Models

LLM-based synthetic training reduces maritime domain model costs 261x by using LLMs as teachers for small language model training.

Ax Tianle Lyu, Junchuan Zhao, Ye Wang 8d ago

KSDiff: Keyframe-Augmented Speech-Aware Dual-Path Diffusion for Facial Animation

Diffusion model for audio-driven facial animation using keyframe augmentation and speech feature decomposition.

Ax Amin Karimi Monsefi, Nikhil Bhendawade, Manuel Rafael Ciosici, Dominic Culver, Yizhe Zhang, Irina Belousova 8d ago

FS-DFM: Fast and Accurate Long Text Generation with Few-Step Diffusion Language Models

FS-DFM enables fast long text generation using few-step diffusion language models with parallel position generation.

Ax Junyu Guo, Shangding Gu, Ming Jin, Costas Spanos, Javad Lavaei 8d ago

StyleBench: Evaluating thinking styles in Large Language Models

StyleBench evaluates trade-offs between structured reasoning styles and efficiency/robustness in LLM inference.

Ax Fang Wu, Aaron Tu, Weihao Xuan, Heli Qi, Xu Huang, Qingcheng Zeng, Shayan Talaei, Yijia Xiao, Peng Xia, Xiangru Tang, Yuchen Zhuang, Bing Hu, Hanqun Cao, Wenqi Shi, Rui Yang, Nan Liu, Huaxiu Yao, Ge Liu, Li Erran Li, Amin Saberi, Naoto Yokoya, Jure Leskovec, Yejin Choi 8d ago

Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards

Position paper analyzing measurement gaps in reinforcement learning with verifiable rewards for LLMs on structured tasks.

Ax Junkai Chen, Huihui Huang, Yunbo Lyu, Junwen An, Jieke Shi, Chengran Yang, Ting Zhang, Haoye Tian, Yikun Li, Zhenhao Li, Xin Zhou, Xing Hu, David Lo 8d ago

SecureVibeBench: Evaluating Secure Coding Capabilities of Code Agents with Realistic Vulnerability Scenarios

SecureVibeBench evaluates code generation security of LLM-powered code agents against realistic vulnerability scenarios.

Ax Merve G\"ulle, Junno Yun, Ya\c{s}ar Utku Al\c{c}alar, Mehmet Ak\c{c}akaya 8d ago

PnP-CM: Consistency Models as Plug-and-Play Priors for Inverse Problems

Consistency models as plug-and-play priors for solving inverse problems with reduced neural function evaluations.

Ax Muhammad Imran Hossain, Jignesh Solanki, Sarika Khushlani Solanki 8d ago

Unsupervised Detection of Spatiotemporal Anomalies in PMU Data Using Transformer-Based BiGAN

T-BiGAN framework combining Transformers and BiGAN for unsupervised anomaly detection in power grid synchrophasor data.

Ax Bipul Thapa, Biplov Paneru, Bishwash Paneru, Khem Narayan Poudyal 8d ago

EEG-based AI-BCI Wheelchair Advancement: Hybrid Deep Learning with Motor Imagery for Brain Computer Interface

Hybrid deep learning system for EEG-based brain-computer interface wheelchair control using motor imagery.

Ax Xue-Cheng Tai, Hao Liu, Lingfeng Li, Raymond H. Chan 8d ago

A Mathematical Explanation of Transformers

Mathematical framework interpreting Transformers as discretizations of integro-differential equations.

Ax Jie Luo, Yuxuan Jiang, Xin Jin, Mingyu Liu, Yihui Fan 8d ago

Semantic Segmentation Algorithm Based on Light Field and LiDAR Fusion

Semantic segmentation combining light field and LiDAR modalities for autonomous driving scene understanding.

Ax Bryan R. Christ, Penelope Molitz, Beau LeBlond, Zachary Gottesman, Jonathan Kropko, Thomas Hartvigsen 8d ago

EDUMATH: Generating Standards-aligned Educational Math Word Problems

LLM-based system for generating standards-aligned math word problems customized to student interests and ability levels.

Ax Jigang Fan, Xiaoran Jiao, Shengdong Lin, Zhanming Liang, Weian Mao, Chenchen Jing, Hao Chen, Chunhua Shen 8d ago

Evolutionary Profiles for Protein Fitness Prediction

Protein language models for fitness prediction interpreted as inverse reinforcement learning on evolutionary sequences.

Ax Peilin Wu, Mian Zhang, Kun Wan, Wentian Zhao, Kaiyu He, Xinya Du, Zhiyu Chen 8d ago

HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation

HiPRAG uses hierarchical process rewards to improve agentic RAG efficiency, reducing over-search and under-search behaviors.

Ax Jerome Sieber, Antonio Orvieto, Melanie N. Zeilinger, Carmen Amo Alonso 8d ago

Design Principles for Sequence Models via Coefficient Dynamics

Unified framework analyzing sequence models (Transformers, SSMs, gated RNNs) through coefficient dynamics lens.

Ax Kedi Chen, Dezhao Ruan, Yuhao Dan, Yaoting Wang, Siyu Yan, Xuecheng Wu, Yinqi Zhang, Qin Chen, Jie Zhou, Liang He, Biqing Qi, Linyang Li, Qipeng Guo, Xiaoming Shi, Wei Zhang 8d ago

A Survey of Inductive Reasoning for Large Language Models

Survey of inductive reasoning in LLMs, covering particular-to-general thinking patterns and knowledge generalization capabilities.

Ax Chris Xing Tian, Weihao Xie, Zhen Chen, Zhengyuan Yi, Hui Liu, Haoliang Li, Shiqi Wang, Siwei Ma 8d ago

Domain-Specific Data Generation Framework for RAG Adaptation

RAGen framework for generating domain-specific question-answer pairs to adapt RAG systems to specialized applications.

Ax Sarah Liaw, Benjamin Plaut 8d ago

Learning When Not to Learn: Risk-Sensitive Abstention in Bandits with Unbounded Rewards

Risk-sensitive abstention in bandit algorithms for high-stakes AI where errors are irreparable without expert guidance.

Ax Nishad Kulkarni, Krithika Iyer, Austin Tapp, Abhijeet Parida, Daniel Capell\'an-Mart\'in, Zhifan Jiang, Mar\'ia J. Ledesma-Carbayo, Syed Muhammad Anwar, Marius George Linguraru 8d ago

Post-Processing Methods for Improving Accuracy in MRI Inpainting

Post-processing methods for MRI brain image inpainting to handle lesions and tumors in medical imaging analysis.

Ax Jinliang Liu, Jiale Bai, Shaoning Zeng 8d ago

Think Parallax: Solving Multi-Hop Problems via Multi-View Knowledge-Graph-Based Retrieval-Augmented Generation

Multi-hop reasoning over knowledge graphs using multi-view RAG with LLMs, addressing Transformer attention specialization patterns.

Ax Michael Klamkin, Mathieu Tanneau, Pascal Van Hentenryck 8d ago

Self-Certifying Primal-Dual Optimization Proxies for Large-Scale Batch Economic Dispatch

Optimization proxies trained to minimize optimality gaps while providing worst-case guarantees for large-scale batch economic dispatch problems.

Ax Tiancheng Hu, Joachim Baumann, Lorenzo Lupo, Nigel Collier, Dirk Hovy, Paul R\"ottger 8d ago

SimBench: Benchmarking the Ability of Large Language Models to Simulate Human Behaviors

SimBench provides first standardized benchmark for evaluating how faithfully LLMs simulate human behaviors across diverse tasks and metrics.

Ax Haoyu Huang, Hong Ting Tsang, Jiaxin Bai, Xi Peng, Gong Zhang, Yangqiu Song 8d ago

AtlasKV: Augmenting LLMs with Billion-Scale Knowledge Graphs in 20GB VRAM

AtlasKV enables RAG systems to integrate billion-scale knowledge graphs efficiently in limited VRAM by avoiding expensive external retrieval modules.

Ax Hao Wang, Licheng Pan, Yuan Lu, Zhixuan Chu, Xiaoxi Li, Shuting He, Zhichao Chen, Haoxuan Li, Qingsong Wen, Zhouchen Lin 8d ago

DistDF: Time-Series Forecasting Needs Joint-Distribution Wasserstein Alignment

Proposes DistDF for time-series forecasting using Wasserstein alignment to handle autocorrelated label sequences better than standard approaches.

Ax Rajiv Movva, Smitha Milli, Sewon Min, Emma Pierson 8d ago

What's In My Human Feedback? Learning Interpretable Descriptions of Preference Data

Method to automatically extract and explain what features human feedback data encodes when training language models, addressing unpredictability in RLHF approaches.

Ax Deokhyung Kang, Seonjeong Hwang, Daehui Kim, Hyounghun Kim, Gary Geunbae Lee 8d ago

Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models?

Analysis of multilingual reasoning gaps in reasoning language models, showing deficits stem from language understanding failures in low-resource languages.

Ax Uzay Macar, Paul C. Bogdan, Senthooran Rajamanoharan, Neel Nanda 8d ago

Thought Branches: Interpreting LLM Reasoning Requires Resampling

Method for interpreting LLM reasoning by resampling multiple chain-of-thought branches to measure causal influence and underlying computation.

Ax Xiaohan Wang, Yuxin Hu, Kevin Leach 8d ago

Context-Guided Decompilation: A Step Towards Re-executability

LLM-guided decompilation framework using context to improve re-executability of decompiled binaries for security analysis.

Ax Zixuan Huang, Huaidian Hou, Dmitry Berenson 8d ago

Multimodal Diffusion Forcing for Forceful Manipulation

Multimodal diffusion approach for robot learning from expert trajectories, modeling interactions between observations, actions, and rewards.

Ax Zhaoyang Wang, Yiming Liang, Xuchao Zhang, Qianhui Wu, Siwei Han, Anson Bastos, Rujia Wang, Chetan Bansal, Baolin Peng, Jianfeng Gao, Saravan Rajmohan, Huaxiu Yao 8d ago

SynthAgent: Adapting Web Agents with Synthetic Supervision

SynthAgent: Framework for web agent adaptation using synthetic data generation with quality filtering to handle hallucinations and trajectory noise.

Ax Meixiu Long, Duolin Sun, Dan Yang, Yihan Jiao, Lei Liu, Jiahai Wang, BinBin Hu, Yue Shen, Jie Feng, Zhehao Tan, Junjie Wang, Lianzhen Zhong, Jian Wang, Peng Wei, Jinjie Gu 8d ago

GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs

GroupRank: Efficient passage reranking paradigm using LLMs with groupwise ranking to balance efficiency and accuracy.

Ax Pei-Fu Guo, Yun-Da Tsai, Chun-Chia Hsu, Kai-Xin Chen, Ya-An Tsai, Kai-Wei Chang, Nanyun Peng, Mi-Yen Yeh, Shou-De Lin 8d ago

LiveCLKTBench: Towards Reliable Evaluation of Cross-Lingual Knowledge Transfer in Multilingual LLMs

LiveCLKTBench: Benchmark pipeline for reliably measuring cross-lingual knowledge transfer in multilingual LLMs with time-sensitive queries.

Ax Shuyang Liu, Yang Chen, Rahul Krishna, Saurabh Sinha, Jatin Ganhotra, Reyhan Jabbarvand 8d ago

Process-Centric Analysis of Agentic Software Systems

Framework for process-centric evaluation of agentic software systems, analyzing execution trajectories and reasoning beyond outcome metrics.

Ax Yiming Tang, Harshvardhan Saini, Zhaoqian Yao, Zheng Lin, Yizhen Liao, Qianxiao Li, Mengnan Du, Dianbo Liu 8d ago

A Unified Theory of Sparse Dictionary Learning in Mechanistic Interpretability: Piecewise Biconvexity and Spurious Minima

Theoretical framework for sparse dictionary learning in neural networks, analyzing piecewise biconvexity and spurious minima in mechanistic interpretability.

Ax Li Ju, Jun Zhao, Mingxu Chai, Ziyu Shen, Xiangyang Wang, Yage Geng, Chunchun Ma, Hao Peng, Guangbin Li, Tao Li, Chengyong Liao, Fu Wang, Xiaolong Wang, Junshen Chen, Rui Gong, Shijia Liang, Feiyan Li, Ming Zhang, Kexin Tan, Junjie Ye, Zhiheng Xi, Shihan Dou, Tao Gui, Yuankai Ying, Yang Shi, Yue Zhang, Qi Zhang 8d ago

WisPaper: Your AI Scholar Search Engine

WisPaper: AI agent system for academic paper discovery and organization, addressing semantic search and workflow fragmentation challenges.

Ax Farica Zhuang, Shu Yang, Dinara Aliyeva, Zixuan Wen, Duy Duong-Tran, Christos Davatzikos, Tianlong Chen, Song Wang, Li Shen 8d ago

Interpretable Alzheimer's Diagnosis via Multimodal Fusion of Regional Brain Experts

Multimodal expert fusion approach for interpretable Alzheimer's disease diagnosis from neuroimaging data.

Ax Fengyi Xu, Jun Ma, Waishan Qiu, Cui Guo, Jack C. P. Cheng 8d ago

Enhancing Geo-localization for Crowdsourced Flood Imagery via LLM-Guided Attention

VPR-AttLLM framework using LLM semantic reasoning to improve geo-localization of crowdsourced flood imagery.

Ax Yuran Wang, Bohan Zeng, Chengzhuo Tong, Wenxuan Liu, Yang Shi, Xiaochen Ma, Hao Liang, Yuanxing Zhang, Wentao Zhang 8d ago

Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling

Method for multi-subject image generation with distinction capability, integrating composition and distinction in subject-driven synthesis.

Ax Hyeongcheol Park, Jiyoung Seo, Jaewon Mun, Hogun Park, Wonmin Byeon, Sung June Kim, Hyeonsoo Im, JeungSub Lee, Sangpil Kim 8d ago