Isolater - Feed

Ax Jun Zhuang, Chaowen Guan 4/14/2026

Large Language Models Can Help Mitigate Barren Plateaus in Quantum Neural Networks

Proposes using LLMs to help mitigate barren plateaus in quantum neural network training through adaptive parameter initialization.

Ax Siqi Fan, Xiusheng Huang, Yiqun Yao, Xuezhi Fang, Kang Liu, Peng Han, Shuo Shang, Aixin Sun, Yequan Wang 4/14/2026

If an LLM Were a Character, Would It Know Its Own Story? Evaluating Lifelong Learning in LLMs

Study evaluating emergent lifelong learning behaviors in LLMs during multi-turn interactions, proposing new evaluation benchmarks for character-like consistency.

Ax Lei Jiang, Chunzhao Xie, Tongxuan Liu, Yuting Zeng, jinrong Guo, Yunheng Shen, Weizhe Huang, Jing Li, Xiaohua Xu 4/14/2026

TARAC: Mitigating Hallucination in LVLMs via Temporal Attention Real-time Accumulative Connection

TARAC method addresses hallucinations in vision-language models by improving temporal attention mechanisms during generation without extensive retraining.

Ax Tahniat Khan, Soroor Motie, Sedef Akinli Kocak, Shaina Raza 4/14/2026

Optimizing Large Language Models: Metrics, Energy Efficiency, and Case Study Insights

Research on energy-efficient optimization techniques for LLM deployment, including quantization and local inference strategies to reduce carbon emissions.

Ax Yixuan Even Xu, Yash Savani, Fei Fang, J. Zico Kolter 4/14/2026

Not All Rollouts are Useful: Down-Sampling Rollouts in LLM Reinforcement Learning

PODS decouples rollout generation from policy updates in LLM RL, addressing compute asymmetry through down-sampling.

Ax Md Abtahi Majeed Chowdhury, Md Rifat Ur Rahman, Akil Ahmad Taki 4/14/2026

LOOPE: Learnable Optimal Patch Order in Positional Embeddings for Vision Transformers

LOOPE method learns optimal patch ordering in Vision Transformer positional embeddings for improved spatial information encoding.

Ax Kusha Sareen, Morgane M Moss, Alessandro Sordoni, Rishabh Agarwal, Arian Hosseini 4/14/2026

Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers

RL^V framework unifies LLM reasoners with verifiers using value functions for improved test-time compute scaling during reasoning.

Ax Tobias Jan Wieczorek, Nathalie Daun, Mohammad Emtiyaz Khan, Marcus Rohrbach 4/14/2026

Variational Visual Question Answering for Uncertainty-Aware Selective Prediction

Bayesian approach for Vision Language Models to reduce hallucinations and overconfidence in VQA through selective prediction.

Ax Tunyu Zhang, Haizhou Shi, Yibin Wang, Hengyi Wang, Xiaoxiao He, Zhuowei Li, Haoxian Chen, Ligong Han, Kai Xu, Huan Zhang, Dimitris Metaxas, Hao Wang 4/14/2026

TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoning

TokUR enables LLMs to self-assess uncertainty at token-level for improved reasoning and response reliability in multi-step tasks.

Ax Haoning Wu, Xiao Huang, Yaohui Chen, Ya Zhang, Yanfeng Wang, Weidi Xie 4/14/2026

SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligence

SpatialScore: comprehensive benchmark for evaluating spatial intelligence of multimodal LLMs with data-driven and agent-based assessment approaches.

Ax Chengqi Duan, Rongyao Fang, Yuqing Wang, Kun Wang, Linjiang Huang, Xingyu Zeng, Hongsheng Li, Xihui Liu 4/14/2026

GoT-R1: Unleashing Reasoning Capability of MLLM for Visual Generation with Reinforcement Learning

GoT-R1: reinforcement learning framework enhancing multimodal LLM reasoning for complex visual generation with precise spatial relationships and attributes.

Ax Fanjin Meng, Jingtao Ding, Jiahui Gong, Chen Yang, Hong Chen, Zuojian Wang, Haisheng Lu, Yong Li 4/14/2026

Tuning Language Models for Robust Prediction of Diverse User Behaviors

Fine-tuning approach for LLMs to predict diverse user behaviors, addressing overfitting to frequent behaviors while capturing long-tailed behavior distribution.

Ax Taiye Chen, Xun Hu, Zihan Ding, Chi Jin 4/14/2026

Learning World Models for Interactive Video Generation

World models for interactive video generation with action conditioning and autoregressive decoding to support planning and future prediction.

Ax Yongjie Fu, Ruijian Zha, Pei Tian, Xuan Di 4/14/2026

LLM-based Realistic Safety-Critical Driving Video Generation

Framework using LLMs for few-shot code generation to create safety-critical driving scenarios in CARLA simulator for autonomous driving evaluation.

Ax Xu Yang, Chenhui Lin, Licheng Sha, Liping Yang, Shuzhou Wu, Xichen Tian, Haotian Liu, Wenchuan Wu 4/14/2026

Large Language Model as An Operator: An Experience-Driven Solution for Distribution Network Voltage Control

LLM-based autonomous agent for power system voltage control, using experience-driven learning to generate dispatch strategies in distribution networks.

Ax Kailai Yang, Xiao Liu, Lei Ji, Hao Li, Xiao Liang, Zhiwei Liu, Yeyun Gong, Peng Cheng, Mao Yang 4/14/2026

Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training

Data Mixing Agent: LLM-based method to automatically re-weight training data domains during continual pre-training, preventing catastrophic forgetting.

Ax Maciej K. Wozniak, Lianhang Liu, Yixi Cai, Patric Jensfelt 4/14/2026

PRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Driving

PRIX: efficient end-to-end autonomous driving model planning from raw camera pixels without LiDAR, reducing model size and computational requirements.

Ax Haris Khan, Sadia Asif, Shumaila Asif, Muhammad Zeeshan Karamat, Rajesh Upadhayaya 4/14/2026

Modular Delta Merging with Orthogonal Constraints: A Scalable Framework for Continual and Reversible Model Composition

MDM-OC: framework for scalable, reversible model composition enabling continual learning without task interference or catastrophic forgetting.

Ax Soumyadeep Dhar, Kei Sen Fong, Mehul Motani 4/14/2026

Teaching the Teacher: The Role of Teacher-Student Smoothness Alignment in Genetic Programming-based Symbolic Distillation

Genetic programming approach for symbolic distillation of neural networks, using teacher-student smoothness alignment to improve explainable AI model accuracy.

Ax Kisu Yang, Yoonna Jang, Hwanseok Jang, Kenneth Choi, Isabelle Augenstein, Heuiseok Lim 4/14/2026

Reliable Evaluation Protocol for Low-Precision Retrieval

Protocol for reliable evaluation of low-precision retrieval systems, addressing spurious ties and variability in relevance scoring with reduced numerical precision.

Ax Abolfazl Ansari, Delvin Ce Zhang, Nafis Irtiza Tripto, Dongwon Lee 4/14/2026

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 Wenhong Zhu, Ruobing Xie, Rui Wang, Xingwu Sun, Di Wang, Pengfei Liu 4/14/2026

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 Nolan Platt, Pragyansmita Nayak 4/14/2026

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 Amin Karimi Monsefi, Nikhil Bhendawade, Manuel Rafael Ciosici, Dominic Culver, Yizhe Zhang, Irina Belousova 4/14/2026

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 4/14/2026

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 4/14/2026

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 4/14/2026

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 Xue-Cheng Tai, Hao Liu, Lingfeng Li, Raymond H. Chan 4/14/2026

A Mathematical Explanation of Transformers

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

Ax Bryan R. Christ, Penelope Molitz, Beau LeBlond, Zachary Gottesman, Jonathan Kropko, Thomas Hartvigsen 4/14/2026

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 Peilin Wu, Mian Zhang, Kun Wan, Wentian Zhao, Kaiyu He, Xinya Du, Zhiyu Chen 4/14/2026

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 4/14/2026

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 4/14/2026

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 4/14/2026

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 4/14/2026

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 Jinliang Liu, Jiale Bai, Shaoning Zeng 4/14/2026

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 Tiancheng Hu, Joachim Baumann, Lorenzo Lupo, Nigel Collier, Dirk Hovy, Paul R\"ottger 4/14/2026

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 4/14/2026

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 Rajiv Movva, Smitha Milli, Sewon Min, Emma Pierson 4/14/2026

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 4/14/2026

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 4/14/2026

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 4/14/2026

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 Zhaoyang Wang, Yiming Liang, Xuchao Zhang, Qianhui Wu, Siwei Han, Anson Bastos, Rujia Wang, Chetan Bansal, Baolin Peng, Jianfeng Gao, Saravan Rajmohan, Huaxiu Yao 4/14/2026

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 4/14/2026

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 4/14/2026

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 4/14/2026

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 4/14/2026

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 4/14/2026