AI-SOVEREIGN
Recently added

New in AI

The newest releases in the directory, by their own release date: models on Hugging Face, model APIs, research papers and apps.

All Model APIsOpen modelsResearchApps
#NameCategory ReleasedKey number Watch
1 MIMind2Act World: A Diagnostic Benchmark for Embodied Mind, Physical Action, and Mind-Action Composition in Robotic ManipulationYuzhi Huang, Jie Wu AI Research 18 Nov 202651
2 WEWeMM-Video: Pushing the Frontiers of Open-Source Omni-Modal Video UnderstandingChangli Tang, Jie Yang AI Research 18 Nov 202644
3 PRProbing the "Conscious" Mind: Selective Access and Global Workspace in Vision-Language ModelsJiahao Huang, Jun Wang AI Research 18 Nov 202642
4 POPosterior Matching DistillationHidir Yesiltepe, Julius Berner AI Research 18 Nov 202637
5 COCoda-DaVinci: Reimagining Video Generation with Code2VideoYiyan Ji, Qixun Wang AI Research 18 Nov 202635
6 DEDepth Pro 2: Sharp and Temporally Consistent Metric Monocular DepthPeiyun Hu, Marko Mihajlovic AI Research 18 Nov 202631
7 HIHiUni: Harmonizing Understanding and Generation in Shared Visual SpaceJiahao Hu, Jingdong Du AI Research 18 Nov 202625
8 EGEgoCaptioner: Towards Comprehensive and Fine-Grained Egocentric Video CaptioningYuqi Tang, Yang Shi AI Research 18 Nov 202625
9 ALAltRA-Test: An Alternative Annotator Test for LLM Judges Without Shared AnnotatorsNagham Omar, Rotem Dror AI Research 18 Nov 202623
10 TUTuringSpace: Grounding Spatial Intelligence in Action with Interactive CAPTCHAsXuwei Ding, Skylar Zhai AI Research 18 Nov 202623
11 ZEZeroVLN: Learning to Navigate without Supervised Fine-Tuning of the VLM BrainZixuan Huang, Yang Zhou AI Research 18 Nov 202622
12 RLRL Post-Training in Diffusion Transformers Is Activation SteeringTuna Han Salih Meral, Kaan Oktay AI Research 18 Nov 202618
13 ACAccelerating Mixture of Block Attention via Dynamic Routing, KV-Centric Execution and Runtime PipeliningYingqi Shi, Junru Lu AI Research 18 Nov 202618
14 TRTraining Vision Models for LLM-Driven Weight-Space ProgrammingTimo Ropinski, Sebastian Kranz AI Research 18 Nov 202615
15 LELearning What Actions Change: Action Effect Matching for Dynamics-Faithful World ModelsJohn Won, Yonghoon Dong AI Research 18 Nov 202615
16 AUAutoMaster: Autonomous Post-Training by Making the Same Model a Better TeacherGuoxin Chen, Shuang Sun AI Research 18 Nov 202614
17 ONOnline Mistake Detection in Instruction-Conditioned Procedural VideoAmit Feldman, Ilan Shimshoni AI Research 18 Nov 202611
18 TWTwice-Told Critiques: Claim-Level Homogenization of Peer Review in the LLM EraIlya Gusev AI Research 18 Nov 202610
19 AVAVTR: Adaptive Multimodal Reasoning with Visual ImaginationXiaoqian Shen, Yunyang Xiong AI Research 18 Nov 20268
20 TETeaching Vision-Language-Action Models to Stop SafelyZheyuan Liu, Chuhan Wang AI Research 18 Nov 20267
21 ACA CPU Inside an LLM: Zero-Gradient Compilation of Exact Circuits into Pretrained WeightsTanmay Sah AI Research 18 Nov 20266
22 TWTwinLab-Bench: Evaluating AI Scientists in Agentic Twins of Real LabsYang Wan, Linchao Zhu AI Research 18 Nov 20265
23 PAPAD: Policy-Aware Data Valuation for Autonomous DrivingChengkai Xu, Yicheng Guo AI Research 18 Nov 20264
24 SPSpecWM: Turning Verification into Refinement for Streaming World ModelsJiaming Li, Lingzhen Li AI Research 18 Nov 20264
25 DIDirect3D-V3: Latent-Free Diffusion Transformers in the Native Voxel DomainShuang Wu, Jiachen Qian AI Research 18 Nov 20264
26 ONOne Prior, Two Dynamics: Repurposing Video Diffusion Transformers for Self-Supervised Latent Action LearningYuxin Jiang, Wenqiang Sun AI Research 18 Nov 20264
27 DADailySafe: Benchmarking Dynamic Safety Awareness in Everyday Multi-Turn Multimodal InteractionsXuankun Rong, Xinhao Deng AI Research 18 Nov 20264
28 SUSuppressing the Shortcut Hidden Behind the Gains of VideoLLM Fine-TuningYoungwoo Shin, Jongsuk Kim AI Research 18 Nov 20264
29 AUAURA: AUdio-dRiven streaming AvatarNathaniel Cohen, Nicolas Dufour AI Research 18 Nov 20263
30 PLPlayCraft: Designing Engaging Games from Agent Play ExperienceWeihao Cheng AI Research 18 Nov 20263
31 TITime Series Structure Learning with Local Causal Parent DiscoveryJacqueline Maasch, Shu Wan AI Research 18 Nov 20262
32 TWTwinD: Generalizing Deepfake Detection from Blending to Entire Face SynthesisAndrii Yermakov, Jan Cech AI Research 18 Nov 20261
33 JEJeveration: System One Models Now GenerateYuhe Liu, Qi Li AI Research 17 Nov 2026148
34 GAGame2Player: Scaling Gameplay Experience for Visual Agents through Environment-Player Co-DevelopmentXirui Jiang, Yuxi Chen AI Research 17 Nov 202629
35 CUCurvDelta: Low-Curvature Delta Modeling For Surgical Learning and UnlearningZeguan Xiao, Zhuocheng Liang AI Research 17 Nov 202626
36 HIHINT-WAM: Hindsight-Informed Training for World Action ModelsPhuong Tuan Dat, Qi Li AI Research 17 Nov 202622
37 WOWorldRuler: Interactive World Modeling under Configurable RulesMingliang Zhai, Chuanhao Li AI Research 17 Nov 202621
38 WAWAM-Policy: World Action Models with On-Policy Distillation for Quadrupedal Loco-ManipulationJunlin Long, Xu Deng AI Research 17 Nov 202616
39 THThinking Fast, Anywhere: One System-1 for the Decision Points of Any Agent WorkflowRui Li, Liyang He AI Research 17 Nov 202616
40 WMWM^MLLM: Turning MLLMs into World ModelsBaiang Li, Enze Xie AI Research 17 Nov 202615
41 STStrideWorld: Benchmarking Scene Rigidity and Action Consistency in Interactive Video World ModelChuang Wang, Rui Nie AI Research 17 Nov 202615
42 PIPiccolo: Co-Evolving Decision Models and Data through Recursive Self-ImprovementZhenqing Ling, Qirui Jiao AI Research 17 Nov 202614
43 ONOn-Policy Morphing into Hybrid Attention ModelsDisen Lan, Xuanda Wang AI Research 17 Nov 202613
44 TATabBioMed: A Large-Scale Benchmark for Biomedical Tabular LearningPau Mateo-Bernadó, Saivenkata Nagavyjayanthi Polapragada AI Research 17 Nov 202613
45 LALate Entry in Looped Language ModelsZiqi Jin, Jiaxi Li AI Research 17 Nov 202610
46 RORoughCut-Bench: A Benchmark for Automatic Video Rough-Cut with Large Vision-Language ModelsRuisi Zhao, You Li AI Research 17 Nov 202610
47 ACAccord: Universal Online Metric Localization and Dense Mapping from one Camera and an IMUJaafar Mahmoud, Arthur Movsesyan AI Research 17 Nov 20269
48 WAWaveView: The Novel View Is in the NoiseKaiwen Wang, Jan-Hendrik Pauls AI Research 17 Nov 20269
49 PRPReMind: When Personal Memory Meets Visual HazardsYeongtak Oh, Donghyeok Lee AI Research 17 Nov 20269
50 MEMechanistic Critics for Sample-Efficient NPU Design-Space ExplorationYicheng He, Yuqi Xue AI Research 17 Nov 20269
51 PIPIPETTE: Prompt Injection Purple-Teaming for Robust LLM AgentsLipeng He, Yihan Wang AI Research 17 Nov 20268
52 EVEvidence-Based Credit Assignment for Search-Augmented Language ModelsWen Wang, Jindong Wang AI Research 17 Nov 20267
53 ULUltraTex: Aligning Physical Knowledge for High-Fidelity PBR Texture GenerationJingzhi Bao, Xiaohe Ma AI Research 17 Nov 20266
54 DRDrawScore: Evaluating Generated CAD Models against Engineering DrawingsHaorui Chen, Shiteng Lu AI Research 17 Nov 20266
55 NANarrowSpec: Draft Hidden Width Need Not Match the Target in Speculative DecodingAlagappan Valliappan, Ankit More AI Research 17 Nov 20265
56 REReplay, Don't Resample: Off-Policy Consolidation of Long-Horizon RL ExpertsZhenrui Yue, Gongxiaohui Chen AI Research 17 Nov 20265
57 PHPhantom Success, Silent Failure: Auditing the Success Checkers of Simulated Manipulation BenchmarksZirui Song, Jiadong Zhang AI Research 17 Nov 20264
58 GEGeneral progress substitutes for specific training data in language modelsMark Marosi, Peter Antal AI Research 17 Nov 20264
59 UNUnified Law for Visual Tasks (The Four Laws of Computer Vision)Sen Fang, Yalin Feng AI Research 17 Nov 20264
60 AFA Foundation Model to Measure and Predict Human BehaviourHaoran Ye, Tianrui Huo AI Research 17 Nov 20264
61 SQSquoosh Bench: Evaluating UX-1 on 318 Historical Website A/B TestsRohith Pasula, Johari Dramiga AI Research 17 Nov 20263
62 INIn Situ Training of Optical Neural Networks by Coding AgentsIlker Oguz, Colin Christian AI Research 17 Nov 20263
63 MOMovie2Game-Bench: Holistic Evaluation of Film-to-Game Adaptation Beyond PlayabilityJialing Xie, Yifan Zhou AI Research 17 Nov 20263
64 RERecurrent Domain Incremental Adaptation of Time-Series Foundation ModelsSachith Abeywickrama, Peiliang Gong AI Research 17 Nov 20263
65 INInhabitant: An Agent Framework for Long-Horizon Human-Scene Interaction with Spatial Control and Quantitative FeedbackYao Zhang, Zhuchenyang Liu AI Research 17 Nov 20262
66 THThe Resolution Hypothesis: Agent Evolution's Key Is Identifying ImprovementsYuanhao Zeng, Shaocheng Lan AI Research 16 Nov 202639
67 COCode World Model 2.0: Towards Infinite Controllable Video GenerationRuoyu Wang, Hao Zhong AI Research 16 Nov 202620
68 DEDecoding Without a Decoder: Direct Pixel Prediction from Diffusion TransformersHansheng Chen, Shengqu Cai AI Research 16 Nov 202614
69 VSVSpark: Speculative Decoding for Autoregressive Vision-Language-Action ModelsSuho Yoo, Youngjoon Jang AI Research 16 Nov 202610
70 RIRICoT: Recurrent Interleaved Chain-of-Thought for Page Stream SegmentationPrashant Khatri, Bhavana Malagavalli AI Research 16 Nov 20266
71 THThinking Harder Doesn't Lead to Better Choices: Reasoning Effort Increases the Confidence but Not the Correctness of LLM Shopping AgentsAdi Krishnamoorthy, X. Y. Han AI Research 16 Nov 20266
72 CHChorus: Shared N-gram Embeddings with Layer-wise AdaptationStephen Chung, Wenyu Du AI Research 16 Nov 20265
73 NENexSight: Verifiable Tasks for Fine-Grained Agentic Long-Video UnderstandingTianci Xie, Li Chen AI Research 16 Nov 20265
74 BIBiCAT: Bimanual Coordination Action TokenizationXuanwei Liu, Guipu Cao AI Research 16 Nov 20264
75 FVFVScore: Specification-Driven Neuro-Symbolic Video EvaluationDo Xuan Long, Long T. Le AI Research 16 Nov 20264
76 OUOut of Sight, Still in Mind: Token Compression for Omni-LLMsSuho Yoo, Youngjoon Jang AI Research 16 Nov 20264
77 LELet Samples Sing in Chorus: Mitigating Spurious Correlations via Cross-view ConsensusWeiwei Li, Junzhuo Liu AI Research 16 Nov 20263
78 WEWeVisForensics: Self-Evolving Agent for Omni AI-Generated Video DetectionYipeng Du, Yuxi Li AI Research 15 Nov 202653
79 ALALIVE: Making Streaming Video Models InteractiveJinzhao Li, Yuan Xu AI Research 15 Nov 202640
80 THThe Mask Is Not the Object: Volumetric Supervision for 3D Gaussian SegmentationJeonghwan Cho, Minsu Kim AI Research 15 Nov 202632
81 LALanguage Models Can Rewrite Their Own WeightsJiajun Fan, Neil He AI Research 15 Nov 202610
82 EMEmbeddings vs. Grep: Rethinking the Dense Advantage in Code SearchSiqiao Xue, Ziyin Zhang AI Research 15 Nov 20269
83 BLBLIP-Live: Balancing Timeliness & Firing Precision in Proactive Streaming Video AgentsKanchana Ranasinghe, Honglu Zhou AI Research 15 Nov 20269
84 SYSystem 1 agents: a method for local, reliable and fast agentic AIEleftherios Tzanis, Michail E. Klontzas AI Research 15 Nov 20266
85 VAVAE Rhythm: Temporal Decoding Traces for AI-Generated Video DetectionKe Sun, Shuwei Li AI Research 15 Nov 20266
86 LOLogT: Logically Think with Images for Visual SearchYanjun Fu, Quanzeng You AI Research 13 Nov 202614
87 COCompoundingKernel: Self-Improving from Zero to FirstQian Qu, Hongyang Wang AI Research 13 Nov 202611
88 DODo Probing and Steering Favor the Same Directions Within and Across Language Models?Afshin Sadeghi, Daniel Becker AI Research 13 Nov 20265
89 S1S1CogBench: What System One Decision Models Can and Cannot Do on Cognitive ExperimentsDengzhe Hou, Kazunori D Yamada AI Research 13 Nov 20264
90 LELearning Anisotropic Prediction Targets for Flow ModelsRayhan Zirvi, Hansheng Chen AI Research 12 Nov 20266
91 CHChoosing Quantized Code LLMs by File Size and Energy per Solved TaskAditi Patodiya AI Research 12 Nov 20263
92 LILightTAR: Light and Fast Target-Aware Representations for Multimodal Tabular LearningEilam Shapira, Alan Arazi AI Research 11 Nov 202623
93 UNUnfinished-Bench: Measuring Rule Violations by Persistent Agents in Realistic Work EnvironmentsSeunghyun Lee, Jaehui Hwang AI Research 11 Nov 20269
94 KEKezek: Splitting Mono Two-Person Conversations into Per-Speaker Tracks for Full-Duplex Dialogue DataBagzhan Karl, Alizhan Karl AI Research 11 Nov 20267
95 LALang-SVG: Hierarchical Image Vectorization with Language PriorsXi Liu, Chaoyi Zhou AI Research 10 Nov 20261
96 TITideway: Phase-Aware Tiered Memory Management for MoE Inference on Consumer DevicesYifei Wang, Tsun-yu Yang AI Research 9 Nov 202667
97 HOHow Far Can Untrained Neural Networks Go in Anomaly Detection? From Tables to PixelsHyojun Yi, Geunyoung Kim AI Research 8 Nov 20267
98 PRPROLA: Principal-Orthogonal Low-rank Adaptation for Predictive Spatiotemporal Weather DownscalingMinseo Yoon, Minseong Bae AI Research 7 Nov 202627
99 STStatePortal: Agentic Checkpoint Synthesis for Testing Deep States in Interactive SoftwareZhiyuan Peng, Wei Tao AI Research 28 Sep 202610
100 PGPGPO: Prototype-Guided Progressive Obfuscation for Privacy-Preserving LLM-Enhanced RecommendationShengxiang Lin, Jiajie Su AI Research 25 Aug 20264