Skip to content
AI Atlas
Research

Papers

Publications linked to models, labs and benchmarks. Authors, venues and abstracts come from arXiv and publisher pages.

1,050 total

Reset
Papers
TitleAuthorsPublishedCategoriesOrganization / venueQuality
Beyond One-Size-Fits-All: Sample-Adaptive Strategy Routing for Vision Token Pruning in MLLMsarXiv:2609.10346Haiji Liang, Pengfei Zhou, Zhenglin Wan +211 Sept 2026cs.CV—89
OmniMed-FL: A Robust Multimodal Federated Learning Framework for Clinical DiagnosisarXiv:2609.10364Ayush Debnath, Ruelia Saha, Sudip Misra11 Sept 2026cs.LG—89
PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue ServingarXiv:2609.10372Lin Huang, Yujuan Tan, Weisheng Li +211 Sept 2026cs.CV—89
MOONWALK: Mediating Operations with Intent-Evidence-Action Alignment Across Junior-Supervisor Review Workflows in Animation/VFX Pre-ProductionarXiv:2609.10385Shih-Yu Lai, Wen-Fan Wang, Sai Ling +211 Sept 2026cs.HC—89
Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy OperationalizationarXiv:2609.10410Ayan Majumdar, Shounak Paul, Pushpdeep Singh +211 Sept 2026cs.CL—89
Emergency Department Revisit Quality Review Screening: Exploring Human Decision-Making and Artificial Intelligence SupportarXiv:2609.10421Jonathan A. Handler, Marlene I. Robles-Granda, Jacob E. Mefford +211 Sept 2026cs.CY—89
Forgetting Only What Matters: Layer-Selective Unlearning toward Robust LLMsarXiv:2609.10439Ravi Ranjan, Olivera Kotevska, Agoritsa Polyzou11 Sept 2026cs.LG—89
Semigroup-JEPA: Latent Dynamics Consistency for Zero-Shot Physics GeneralizationarXiv:2609.10464Andy Zeyi Liu, Haoran Sun, Lucas Baker +211 Sept 2026cs.LG—89
IBIB: A Protocol for Measuring Enterprise AI Systems by Serving Route, Not Model IdentifierarXiv:2609.10494Blake Stenstrom, Charangan Vasantharajan, Brian Sathianathan11 Sept 2026cs.CL—89
Show-Harness: Just a VLM Agent Can Play RobotsarXiv:2609.10522Yanzhe Chen, Zechen Bai, Zhijun Cao +211 Sept 2026cs.RO—89
Reinforcement Learning with Temporal-Logic-Based Causal DiagramsarXiv:2306.13732Yash Paliwal, Rajarshi Roy, Jean-Rapha\"el Gaglione +211 Sept 2026cs.AI—89
Reinforcement learning for Quantum Tiq-Taq-ToearXiv:2411.06429Catalin-Viorel Dinu, Thomas Moerland11 Sept 2026cs.AI—89
ROTATE: Regret-driven Open-ended Training for Ad Hoc TeamworkarXiv:2505.23686Caroline Wang, Arrasy Rahman, Benjamin Nativi +211 Sept 2026cs.AI—89
RelayS2S: A Dual-Path Speculative Generation for Real-Time DialoguearXiv:2603.23346Long Mai, Junli Liang11 Sept 2026cs.AI—89
MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory PredictionarXiv:2604.10169Wenchang Duan, Zhenguo Gao, Jinguo Xian +111 Sept 2026cs.AI—89
Zero-shot World Models Are Developmentally Efficient LearnersarXiv:2604.10333Khai Loong Aw, Klemen Kotar, Wanhee Lee +211 Sept 2026cs.AI—89
Non-Stationarity Breaks Permutation Surrogates in Multi-Agent Reinforcement Learning: Diagnosis and RemediesarXiv:2604.23716Nikolaos Al. Papadopoulos, Konstantinos E. Psannis11 Sept 2026cs.AI—89
CoGReV: A Confidence-Gated Post-Hoc Non-Monotonic Belief Revision Framework for Phishing Website ClassificationarXiv:2604.25512Mainak Sen, Kumar Sankar Ray, Amlan Chakrabarti11 Sept 2026cs.AI—89
Grounded Continuation: A Linear-Time Runtime Verifier for LLM ConversationsarXiv:2605.14175Qisong He, Jinwei Hu, Xinmiao Huang +211 Sept 2026cs.AI—89
Cultural Binding Heads in Language ModelsarXiv:2605.28543Avrile Floro, Luca Benedetto11 Sept 2026cs.AI—89
KairosAgent: Agentic Time Series Forecasting with Fused Semantic ReasoningarXiv:2605.30002Kun Feng, Ziwei Shan, Yuchen Fang +211 Sept 2026cs.AI—89
Self-Evolving Scientific Agent Designs Physically Reasoned White-Box Fluid ControlarXiv:2606.08405Boai Sun, Wenjin Guo, Zongmin Yu +111 Sept 2026cs.AI—89
EVOQUANT: Self-Evolving Verifier-Guided Strategy Optimization for Robust Quantitative TradingarXiv:2607.12455Jie Mao, Changlun Li, Xiang Li +211 Sept 2026cs.AI—89
KernelGenBench: Can LLMs and Agents Write Efficient Kernels Across Operator Sources and Hardware Platforms?arXiv:2607.27231Peiyu Zang, Jian Tao, Jialing Zhang +211 Sept 2026cs.AI—89
ViSR-KGC: Visual Subgraph Reasoning with Vision-Language Models for Multimodal Knowledge Graph CompletionarXiv:2608.05833Jiafan Li, Mengxue Yang, Jiaqi Zhu +211 Sept 2026cs.AI—89
Learning to Predict Middle-Layer Attention in MLLMs for Visual Token PruningarXiv:2608.06411Yuyao Sun, Tao Deng, Shuang Li +211 Sept 2026cs.AI—89
LiFTER: A Grounded Neuro-Symbolic Microscope for Continuous-Time Dynamic Graph ForecastingarXiv:2608.06765Minwoo Yu, Young-guk Ha11 Sept 2026cs.AI—89
A Human Audit of OpenAIs AI-Generated Mathematical ProofsarXiv:2608.14673Miko{\l}aj Sienicki, Krzysztof Sienicki11 Sept 2026cs.AI—89
Dear Algo: A Precision-First Agentic Intent Layer for Unified Search and RecommendationarXiv:2608.15877Rui Wang, Jiazhou Wang, Zheng Wei +211 Sept 2026cs.AI—89
Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI AgentsarXiv:2608.16578Batu El, Jinhee Paeng, Fatih Dinc +211 Sept 2026cs.AI—89
FrontierChallenge: Evaluating Scientific Workflow CompletionarXiv:2608.24979Liangcai Su, Zhaopeng Feng, Zhuo Chen +211 Sept 2026cs.AI—89
A Composable Evaluation System for Reproducible Omni-Modal Foundation Model EvaluationarXiv:2609.01315Hodong Lee, Sanghee Park, Dohoon Ryu +211 Sept 2026cs.AI—89
Beyond Prompts: Measuring and Optimizing LLM Tool-Agent HarnessesarXiv:2609.05736Cen Mia Zhao, Haibo Ruan, Wenjie Chen +211 Sept 2026cs.AI—89
From Monolithic Blending to Agentic Orchestration: Dynamic Response for Conversational Assistants at ScalearXiv:2609.05758Cen Mia Zhao, Peng Wang, Chuan Shi +211 Sept 2026cs.AI—89
DGCPath: Distribution-Aware Generative Contrastive Framework for Self-supervised Path Representation Learning -- Extended VersionarXiv:2609.07316Sean Bin Yang, Hao Miao, Zongyi Xu +211 Sept 2026cs.AI—89
FrogNano: Training a 4B Coding Agent via Online Task SynthesisarXiv:2609.07925Minseon Kim, Zhengyan Shi, Emiliano Penaloza +211 Sept 2026cs.AI—89
RevalExo: A Functional Daily-Activity Benchmark for Inertial and Visual Locomotion Mode Recognition in Older Adults and Clinical CohortsarXiv:2609.08090Diwas Lamsal, Juha Carlon, Reinhard Claeys +211 Sept 2026cs.AI—89
EvolveScaler: Synthesizing Information-Evolution Contexts via Executable State Machines and Natural-Language RenderingarXiv:2609.08435Ziliang Zhao, Zenan Xu, Shuting Wang +211 Sept 2026cs.AI—89
Equity Promotion in Online Resource AllocationarXiv:2112.04169Pan Xu, Yifan Xu11 Sept 2026cs.GT—89
Incentives to Offer Algorithmic RecoursearXiv:2301.12884Matthew Olckers, Toby Walsh11 Sept 2026cs.GT—89

Author lists and categories are copied from the paper's own metadata (arXiv, publisher). Each paper page shows the abstract, related models and every source snapshot.