Ax Xinshun Feng, Xinhao Song, Lijun Li, Gongshen Liu, Jing Shao 8d ago

SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents

SEARL framework enables self-evolving agents through joint optimization of policy and tool graph memory, reducing reliance on large-scale LLMs.

Ax Mohamed Elfeki, Tu Trinh, Kelvin Luu, Guangze Luo, Nathan Hunt, Ernesto Montoya, Nandan Marwaha, Yannis He, Charles Wang, Fernando Crabedo, Alessa Castilo, Bing Liu 8d ago

HiL-Bench (Human-in-Loop Benchmark): Do Agents Know When to Ask for Help?

HiL-Bench evaluates whether coding agents know when to request help with incomplete specifications, exposing judgment gaps in frontier models.

Ax Gonzalo Ballestero, Hadi Hosseini, Samarth Khanna, Ran I. Shorrer 8d ago

Strategic Algorithmic Monoculture: Experimental Evidence from Coordination Games

Empirical study of how LLM agents coordinate in multi-agent games, distinguishing baseline action similarity from strategic algorithmic monoculture.

Ax Paul Geertsema, Helen Lu 8d ago

AXIL: Exact Instance Attribution for Gradient Boosting

AXIL derives exact instance attribution method for gradient boosting machines, expressing predictions as weighted sums of training targets.

Ax Minsik Oh, Jiwei Li, Guoyin Wang 8d ago

Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings

Proposes contrastive learning method for dialogue sentence embeddings using token-level template annotations instead of utterance-level labels.

Ax Sameera Horawalavithana, Sai Munikoti, Ian Stewart, Henry Kvinge, Karl Pazdernik 8d ago

SCITUNE: Aligning Large Language Models with Human-Curated Scientific Multimodal Instructions

SciTune framework aligns LLMs with scientific domain knowledge through instruction fine-tuning on multimodal scientific publication data.

Ax Lai Wei, Xiaozhe Li, Zihao Jiang, Weiran Huang, Lichao Sun 8d ago

MM-LIMA: Less Is More for Alignment in Multi-Modal Datasets

MM-LIMA demonstrates multimodal LLM fine-tuning achieves strong results with only 200 high-quality instruction examples, reducing data requirements.

Ax Hao Li, Xiao-Hu Zhou, Shu-Hai Li, Mei-Jiang Gui, Xiao-Liang Xie, Shi-Qi Liu, Shuang-Yi Wang, Zhen-Qiu Feng, Zeng-Guang Hou 8d ago

CROP: Conservative Reward for Model-based Offline Policy Optimization

Proposes CROP, a model-based offline reinforcement learning method addressing distribution shift through conservative reward estimation.

Ax Congchi Yin, Ziyi Ye, Piji Li 8d ago

Language Reconstruction with Brain Predictive Coding from fMRI Data

Uses predictive coding theory to decode and reconstruct language from fMRI brain signals, advancing neuroscience understanding of speech perception.

Ax Hengran Zhang, Keping Bi, Jiafeng Guo, Xueqi Cheng 8d ago

An Iterative Utility Judgment Framework Inspired by Philosophical Relevance via LLMs

Framework using LLMs with philosophical relevance concepts to improve utility-based result ranking in retrieval-augmented generation systems.

Ax Xiao Siyao, Huang Libing, Zhang Shunsheng 8d ago

Linear Attention Based Deep Nonlocal Means Filtering for Multiplicative Noise Removal

Linear attention-based deep learning approach for multiplicative noise removal in radar and medical images.

Ax Yifei Li, Erik-Jan van Kampen 8d ago

Deep deterministic policy gradient with symmetric data augmentation for lateral attitude tracking control of a fixed-wing aircraft

Sample-efficient offline reinforcement learning for aircraft control using symmetric data augmentation to exploit system symmetries.

Ax Lionel Z. Wang, Ka Chung Ng, Yiming Ma, Wenqi Fan 8d ago

MegaFake: A Theory-Driven Dataset of Fake News Generated by Large Language Models

MegaFake dataset of LLM-generated fake news for studying mechanisms of misinformation generation and detection methods.

Ax Avinash Maurya, Jie Ye, M. Mustafa Rafique, Franck Cappello, Bogdan Nicolae 8d ago

Deep Optimizer States: Towards Scalable Training of Transformer Models Using Interleaved Offloading

Deep Optimizer States method enables scalable training of transformer models using interleaved offloading to overcome memory constraints.

Ax Zhibai Huang, Chen Chen, James Yen, Yihan Shen, Yongchen Xie, Zhixiang Wei, Kailiang Xu, Yun Wang, Fangxin Liu, Tao Song, Mingyuan Xia, Zhengwei Qi 8d ago

The Phantom of PCIe: Constraining Generative Artificial Intelligences for Practical Peripherals Trace Synthesizing

Framework for synthesizing realistic PCIe transaction layer packet traces using constrained generative AI for device development.

Ax Qingyang Mao, Qi Liu, Zhi Li, Mingyue Cheng, Zheng Zhang, Rui Li 8d ago

PoTable: Towards Systematic Thinking via Plan-then-Execute Stage Reasoning on Tables

PoTable framework improves table reasoning in LLMs using plan-then-execute reasoning stages for systematic thinking.

Ax Charlie F. Ruan, Yucheng Qin, Akaash R. Parthasarathy, Xun Zhou, Ruihang Lai, Hongyi Jin, Yixin Dong, Bohan Hou, Meng-Shiun Yu, Yiyan Zhai, Sudeep Agarwal, Hangrui Cao, Siyuan Feng, Tianqi Chen 8d ago

WebLLM: A High-Performance In-Browser LLM Inference Engine

WebLLM inference engine enabling high-performance LLM execution directly in web browsers for on-device deployment without server GPUs.

Ax Ting Zhou, Daoyuan Chen, Qirui Jiao, Bolin Ding, Yaliang Li, Ying Shen 8d ago

HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized Benchmarks

HumanVBench benchmark for evaluating human-centric video understanding in multimodal large language models with 16 fine-grained tasks.

Ax Narasimha Raghavan Veeraragavan, Svetlana Boudko, Jan Franz Nyg{\aa}rd 8d ago

A Multiparty Homomorphic Encryption Approach to Confidential Federated Kaplan Meier Survival Analysis

Privacy-preserving federated framework for survival analysis using threshold homomorphic encryption across multiple institutions.

Ax Stephane Hatgis-Kessell, W. Bradley Knox, Serena Booth, Peter Stone 8d ago

Influencing Humans to Conform to Preference Models for RLHF

Three human studies examining whether humans can be influenced to conform to preference models used in RLHF algorithms for LLMs.

Ax Fausto Mauricio Lagos Suarez, Akshit Saradagi, Vidya Sumathy, Shruti Kotpaliwar, George Nikolakopoulos 8d ago

Curriculum-based Sample Efficient Reinforcement Learning for Robust Stabilization of a Quadrotor

Novel curriculum learning approach for sample-efficient reinforcement learning applied to quadrotor stabilization control.

Ax Wanli Ma, Oktay Karakus, Paul L. Rosin 8d ago

Integrating Semi-Supervised and Active Learning for Semantic Segmentation

Combines semi-supervised and active learning for semantic segmentation to reduce manual annotation costs and improve model performance.

Ax Jun Zhuang, Chaowen Guan 8d ago

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 Rikuto Kotoge, Ziwei Yang, Zheng Chen, Yushun Dong, Yasuko Matsubara, Jimeng Sun, Yasushi Sakurai 8d ago

ExPath: Targeted Pathway Inference for Biological Knowledge Bases via Graph Learning and Explanation

ExPath framework uses graph learning to infer biological pathways in knowledge bases, integrating experimental data for classification.

Ax Yves-Simon Zeulner, Simon Cr\"amer, Sandeep Selvaraj, Roberto Calandra 8d ago

Learning to Play Piano in the Real World

First robotic system using learning-based approaches for real-world piano playing, advancing manipulation capabilities in robotics.

Ax Xiangwen Zhang, Qian Zhang, Longfei Han, Qiang Qu, Xiaoming Chen, Weidong Cai 8d ago

AccidentSim: Generating Vehicle Collision Videos with Physically Realistic Collision Trajectories from Real-World Accident Reports

AccidentSim framework generates physically realistic vehicle collision videos for autonomous driving research using real accident reports.

Ax Siqi Fan, Xiusheng Huang, Yiqun Yao, Xuezhi Fang, Kang Liu, Peng Han, Shuo Shang, Aixin Sun, Yequan Wang 8d ago

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 8d ago

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 8d ago

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 8d ago

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 8d ago

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 Weiwei Ye, Zhuopeng Xu, Ning Gui 8d ago

Non-stationary Diffusion For Probabilistic Time Series Forecasting

Non-stationary diffusion model for time series forecasting using Location-Scale Noise Model for variable uncertainty.

Ax Kusha Sareen, Morgane M Moss, Alessandro Sordoni, Rishabh Agarwal, Arian Hosseini 8d ago

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 Kanggeon Lee, Soochahn Lee, Kyoung Mu Lee 8d ago

Auto-regressive transformation for image alignment

Auto-Regressive Transformation method for image alignment handling feature-sparse regions and large deformations.

Ax Tobias Jan Wieczorek, Nathalie Daun, Mohammad Emtiyaz Khan, Marcus Rohrbach 8d ago

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 8d ago

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 Subash Khanal, Srikumar Sastry, Aayush Dhakal, Adeel Ahmad, Abby Stylianou, Nathan Jacobs 8d ago

Sat2Sound: A Unified Framework for Zero-Shot Soundscape Mapping

Sat2Sound framework predicts soundscape distribution using satellite images and vision-language models for geospatial audio understanding.

Ax Haoning Wu, Xiao Huang, Yaohui Chen, Ya Zhang, Yanfeng Wang, Weidi Xie 8d ago

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 8d ago

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 8d ago

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 8d ago

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 Shulong Zhang, Mingyuan Yao, Jiayin Zhao, Daoliang Li, Yingyi Chen, Haihua Wang 8d ago

Progressive Multimodal Interaction Network for Reliable Quantification of Fish Feeding Intensity in Aquaculture

Progressive multimodal network for quantifying fish feeding intensity in aquaculture using sensor fusion and conflict resolution between modalities.

Ax Yongjie Fu, Ruijian Zha, Pei Tian, Xuan Di 8d ago

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 Takashi Izumo 8d ago

Absorption and Inertness in Coarse-Grained Arithmetic: A Heuristic Application to the St. Petersburg Paradox

Mathematical analysis of coarse-grained arithmetic applied to the St. Petersburg paradox in decision theory.

Ax Xu Yang, Chenhui Lin, Licheng Sha, Liping Yang, Shuzhou Wu, Xichen Tian, Haotian Liu, Wenchuan Wu 8d ago

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 8d ago

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 8d ago

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 8d ago

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 8d ago

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 8d ago

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.