AI-SOVEREIGN
AI Research

Trending AI research

New AI papers ranked by community upvotes on Hugging Face Daily Papers. Updated 2026-11-22.

100 results · page 1 of 2
#Name Upvotes24h7d Published Score Watch
1 JEJeveration: System One Models Now GenerateYuhe Liu, Qi Li 148 –– 17 Nov 2026 100
2 TITideway: Phase-Aware Tiered Memory Management for MoE Inference on Consumer DevicesYifei Wang, Tsun-yu Yang 67 –– 9 Nov 2026 99
3 WEWeVisForensics: Self-Evolving Agent for Omni AI-Generated Video DetectionYipeng Du, Yuxi Li 53 –– 15 Nov 2026 98
4 MIMind2Act World: A Diagnostic Benchmark for Embodied Mind, Physical Action, and Mind-Action Composition in Robotic ManipulationYuzhi Huang, Jie Wu 51 –– 18 Nov 2026 97
5 WEWeMM-Video: Pushing the Frontiers of Open-Source Omni-Modal Video UnderstandingChangli Tang, Jie Yang 44 –– 18 Nov 2026 96
6 PRProbing the "Conscious" Mind: Selective Access and Global Workspace in Vision-Language ModelsJiahao Huang, Jun Wang 42 –– 18 Nov 2026 95
7 ALALIVE: Making Streaming Video Models InteractiveJinzhao Li, Yuan Xu 40 –– 15 Nov 2026 94
8 THThe Resolution Hypothesis: Agent Evolution's Key Is Identifying ImprovementsYuanhao Zeng, Shaocheng Lan 39 –– 16 Nov 2026 93
9 POPosterior Matching DistillationHidir Yesiltepe, Julius Berner 37 –– 18 Nov 2026 92
10 COCoda-DaVinci: Reimagining Video Generation with Code2VideoYiyan Ji, Qixun Wang 35 –– 18 Nov 2026 91
11 THThe Mask Is Not the Object: Volumetric Supervision for 3D Gaussian SegmentationJeonghwan Cho, Minsu Kim 32 –– 15 Nov 2026 90
12 DEDepth Pro 2: Sharp and Temporally Consistent Metric Monocular DepthPeiyun Hu, Marko Mihajlovic 31 –– 18 Nov 2026 89
13 GAGame2Player: Scaling Gameplay Experience for Visual Agents through Environment-Player Co-DevelopmentXirui Jiang, Yuxi Chen 29 –– 17 Nov 2026 88
14 PRPROLA: Principal-Orthogonal Low-rank Adaptation for Predictive Spatiotemporal Weather DownscalingMinseo Yoon, Minseong Bae 27 –– 7 Nov 2026 87
15 CUCurvDelta: Low-Curvature Delta Modeling For Surgical Learning and UnlearningZeguan Xiao, Zhuocheng Liang 26 –– 17 Nov 2026 86
16 HIHiUni: Harmonizing Understanding and Generation in Shared Visual SpaceJiahao Hu, Jingdong Du 25 –– 18 Nov 2026 85
17 EGEgoCaptioner: Towards Comprehensive and Fine-Grained Egocentric Video CaptioningYuqi Tang, Yang Shi 25 –– 18 Nov 2026 84
18 ALAltRA-Test: An Alternative Annotator Test for LLM Judges Without Shared AnnotatorsNagham Omar, Rotem Dror 23 –– 18 Nov 2026 83
19 TUTuringSpace: Grounding Spatial Intelligence in Action with Interactive CAPTCHAsXuwei Ding, Skylar Zhai 23 –– 18 Nov 2026 82
20 LILightTAR: Light and Fast Target-Aware Representations for Multimodal Tabular LearningEilam Shapira, Alan Arazi 23 –– 11 Nov 2026 81
21 ZEZeroVLN: Learning to Navigate without Supervised Fine-Tuning of the VLM BrainZixuan Huang, Yang Zhou 22 –– 18 Nov 2026 80
22 HIHINT-WAM: Hindsight-Informed Training for World Action ModelsPhuong Tuan Dat, Qi Li 22 –– 17 Nov 2026 79
23 WOWorldRuler: Interactive World Modeling under Configurable RulesMingliang Zhai, Chuanhao Li 21 –– 17 Nov 2026 78
24 COCode World Model 2.0: Towards Infinite Controllable Video GenerationRuoyu Wang, Hao Zhong 20 –– 16 Nov 2026 77
25 RLRL Post-Training in Diffusion Transformers Is Activation SteeringTuna Han Salih Meral, Kaan Oktay 18 –– 18 Nov 2026 76
26 ACAccelerating Mixture of Block Attention via Dynamic Routing, KV-Centric Execution and Runtime PipeliningYingqi Shi, Junru Lu 18 –– 18 Nov 2026 75
27 WAWAM-Policy: World Action Models with On-Policy Distillation for Quadrupedal Loco-ManipulationJunlin Long, Xu Deng 16 –– 17 Nov 2026 74
28 THThinking Fast, Anywhere: One System-1 for the Decision Points of Any Agent WorkflowRui Li, Liyang He 16 –– 17 Nov 2026 73
29 TRTraining Vision Models for LLM-Driven Weight-Space ProgrammingTimo Ropinski, Sebastian Kranz 15 –– 18 Nov 2026 72
30 LELearning What Actions Change: Action Effect Matching for Dynamics-Faithful World ModelsJohn Won, Yonghoon Dong 15 –– 18 Nov 2026 71
31 WMWM^MLLM: Turning MLLMs into World ModelsBaiang Li, Enze Xie 15 –– 17 Nov 2026 70
32 STStrideWorld: Benchmarking Scene Rigidity and Action Consistency in Interactive Video World ModelChuang Wang, Rui Nie 15 –– 17 Nov 2026 69
33 AUAutoMaster: Autonomous Post-Training by Making the Same Model a Better TeacherGuoxin Chen, Shuang Sun 14 –– 18 Nov 2026 68
34 PIPiccolo: Co-Evolving Decision Models and Data through Recursive Self-ImprovementZhenqing Ling, Qirui Jiao 14 –– 17 Nov 2026 67
35 LOLogT: Logically Think with Images for Visual SearchYanjun Fu, Quanzeng You 14 –– 13 Nov 2026 66
36 DEDecoding Without a Decoder: Direct Pixel Prediction from Diffusion TransformersHansheng Chen, Shengqu Cai 14 –– 16 Nov 2026 65
37 ONOn-Policy Morphing into Hybrid Attention ModelsDisen Lan, Xuanda Wang 13 –– 17 Nov 2026 64
38 TATabBioMed: A Large-Scale Benchmark for Biomedical Tabular LearningPau Mateo-Bernadó, Saivenkata Nagavyjayanthi Polapragada 13 –– 17 Nov 2026 63
39 ONOnline Mistake Detection in Instruction-Conditioned Procedural VideoAmit Feldman, Ilan Shimshoni 11 –– 18 Nov 2026 62
40 COCompoundingKernel: Self-Improving from Zero to FirstQian Qu, Hongyang Wang 11 –– 13 Nov 2026 61
41 LALanguage Models Can Rewrite Their Own WeightsJiajun Fan, Neil He 10 –– 15 Nov 2026 60
42 TWTwice-Told Critiques: Claim-Level Homogenization of Peer Review in the LLM EraIlya Gusev 10 –– 18 Nov 2026 59
43 VSVSpark: Speculative Decoding for Autoregressive Vision-Language-Action ModelsSuho Yoo, Youngjoon Jang 10 –– 16 Nov 2026 58
44 STStatePortal: Agentic Checkpoint Synthesis for Testing Deep States in Interactive SoftwareZhiyuan Peng, Wei Tao 10 –– 28 Sep 2026 57
45 LALate Entry in Looped Language ModelsZiqi Jin, Jiaxi Li 10 –– 17 Nov 2026 56
46 RORoughCut-Bench: A Benchmark for Automatic Video Rough-Cut with Large Vision-Language ModelsRuisi Zhao, You Li 10 –– 17 Nov 2026 55
47 ACAccord: Universal Online Metric Localization and Dense Mapping from one Camera and an IMUJaafar Mahmoud, Arthur Movsesyan 9 –– 17 Nov 2026 54
48 EMEmbeddings vs. Grep: Rethinking the Dense Advantage in Code SearchSiqiao Xue, Ziyin Zhang 9 –– 15 Nov 2026 53
49 UNUnfinished-Bench: Measuring Rule Violations by Persistent Agents in Realistic Work EnvironmentsSeunghyun Lee, Jaehui Hwang 9 –– 11 Nov 2026 52
50 BLBLIP-Live: Balancing Timeliness & Firing Precision in Proactive Streaming Video AgentsKanchana Ranasinghe, Honglu Zhou 9 –– 15 Nov 2026 51