Zhejiang University · 61 records

dateidtitleauthorsvenue↑
2026-11-202611.26248TwinLab-Bench: Evaluating AI Scientists in Agentic Twins of Real LabsYang Wan et al.arXiv5
2026-11-192611.23236PGPO: Prototype-Guided Progressive Obfuscation for Privacy-Preserving LLM-Enhanced RecommendationShengxiang Lin et al.arXiv2
2026-11-132611.08219Agent-R^2: Scaling Agents for Realistic Productivity Work via Real-Source Data SynthesisTeng Pan et al.arXiv4
2026-11-122611.17167Actor, Judge, or Teacher? Understanding Decision Models in Long-Horizon AgentsHaochen Liu et al.arXiv33
2026-11-052611.08264SplatAnything: Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary ScenesHao Yu et al.arXiv69
2026-11-04W4413120297An open structure-guided RNA foundation model for generalizable predictionHeqin Zhu et al.Nature
2026-11-032611.02782History Forcing: Distilling History-Dependent Continuations for Long-Horizon Video World ModelsHangyi Kuang et al.arXiv18
2026-10-31W7225007353PROTAC-DB 4.0: an expanded knowledgebase of targeted protein degradation modalities with AI-powered knowledge discoveryJingxuan Ge et al.Nucleic Acids Research
2026-10-272610.14018RoboHarness: A Simple Harness Outperforms VLA and World Action ModelsBince Qu et al.arXiv19
2026-10-272610.24451Assessing the CAD Capabilities of General-Purpose AI Models: A Case Study of GPT-6 AstraQiang Zou et al.arXiv4
2026-10-262610.01352MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal ReasoningJuekai Lin et al.arXiv16
2026-10-192610.22321AVC-Reward: Event-Centric Audio-Video Consistency EvaluationYuruo Wu et al.arXiv14
2026-10-162610.20111RepForcing: Representation-Space Initialization for Autoregressive Video DistillationSiming Fu et al.arXiv5
2026-10-152610.20571Any Time, Any Space: A World-State-Centric Framework for Agentic Video GenerationWeijie Wang et al.arXiv68
2026-10-152610.19789More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement LearningLinhao Zhong et al.arXiv50
2026-10-142610.18846WorldRecon: Generative Multi-View Mesh Reconstruction for Large-Scale 3D WorldMengchen Zhang et al.arXiv8
2026-10-122610.13181MixTok: Adaptive Visual Tokenization with Global 1D Tokens and Sparse 2D RefinementChenge Li et al.arXiv7
2026-10-092610.12403ViSkill: Reinforcing VLM Agents with Evolving Visual-Native SkillsHongxing Li et al.arXiv14
2026-10-092610.12402SpaceCast-Bench: Evaluating Predictive Spatial Reasoning in Vision-Language ModelsHongxing Li et al.arXiv11
2026-10-092610.12355Distilling Routed 3D Privilege for Spatial Reasoning in Vision-Language ModelsHongxing Li et al.arXiv7
2026-10-082610.08699nanoMuse: An Open-Source Personal Agent for Every Device You OwnGuangyi Liu et al.arXiv102
2026-10-082609.38169STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State QuantizationBingchen Yao et al.arXiv42
2026-10-062610.05739HLA-WM: Hybrid Linear Attention for Long-Horizon Video World ModelsZhuokun Chen et al.arXiv13
2026-10-052609.34715PDE-JEPA: Predictive Representation Learning of Latent Dynamics Modeling for Parametric PDEsZhentao Tan et al.arXiv36
2026-10-012609.40048CoEvoWhen: Policy-Tool Coevolution for Ultra-Long Video Temporal GroundingYiduo Jia et al.arXiv14
2026-09-302609.34759PanoVLN: Towards Effective Panoramic Vision-and-Language NavigationZhen Wang et al.arXiv40
2026-09-302609.32722Scaling Properties of Same-Family On-Policy DistillationYuntai Bao et al.arXiv39
2026-09-302609.32522Beyond Dyadic Memory: Interaction-Aware Multimodal Memory with Adaptive Agentic Retrieval for Multi-Party Spoken ConversationsWenxu Jia et al.arXiv23
2026-09-242609.26780SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party DialogueHaobo Zheng et al.arXiv36
2026-09-092609.05324RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?Zhenxuan Fan et al.arXiv13
2026-09-032609.01740ZipTok3D: High-Fidelity 3D Tokenization with Compact Token PrefixesMingda Lin et al.arXiv29
2026-08-312608.28460LayerRecall: A State-Conditioned Memory Router for Long-Horizon Consistency in Video GenerationYixuan Ding et al.arXiv27
2026-08-272608.23318Agent-G^2: Gaussian Guidance for Agentic Reinforcement LearningZixuan Wang et al.arXiv23
2026-08-252608.19567Block3D: Efficient Text-to-3D Generation via Block-Wise DiffusionBowen Cui et al.arXiv33
2026-08-142608.12743Spatial Memory Agent: Experience-Grounded Procedure Memory for Spatial IntelligenceHaokai Zhang et al.arXiv26
2026-08-102608.07341Zero Gap Is Not Restoration: Stratified Per-Question Probability Evaluation and Step-wise Mitigation of Benchmark ContaminationRuijie Hou et al.arXiv4
2026-08-062607.28048SKILL-KD: Contrastive Skill Distillation for LLM AgentsQiming Shi et al.arXiv8
2026-07-312607.26056INTACT: Isomorphic Intent-to-Action Learning for Search-Free World ModelsJunhan Sun et al.arXiv16
2026-07-292607.26057Pass the Baton: Trajectory-Relayed On-Policy DistillationHaolei Xu et al.arXiv30
2026-07-282607.23518Chamaileon: Cross-Context Binder Design with Contextualized Modeling and Mixed SamplingHengyuan Cao et al.arXiv8
2026-07-022607.01191Perceive-to-Reason: Decoupling Perception and Reasoning for Fine-Grained Visual ReasoningHongxing Li et al.arXiv15
2026-07-022606.31292AtomiMed: Hierarchical Atomic Fact-Checking for Universal Clinical-Aware Medical Report EvaluationYuan Wang et al.arXiv5
2026-06-242606.24428Escaping the Self-Confirmation Trap: An Execute-Distill-Verify Paradigm for Agentic Experience LearningShiding Zhu et al.arXiv15
2026-06-242606.12345An Efficient Method for the Optimal Control of Microgrids Under Uncertainties using Local ReductionEdoardo Scaccia et al.arXiv
2026-06-232606.20636SkillHarness: Harnessing Safe Skills for Computer-Use AgentsYurun Chen et al.arXiv20
2026-06-152606.12366APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action PoliciesKechun Xu et al.arXiv2
2026-06-122606.12243VIA-SD: Verification via Intra-Model Routing for Speculative DecodingYuchen Xian et al.arXiv36
2026-06-122606.12303From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image FusionYuchen Xian et al.arXiv33
2026-06-092606.07436Skill-3D: Evolving Scene-Aware Skills for Agentic 3D Spatial ReasoningHaoyuan Li et al.arXiv27
2026-06-052606.05172Is This Edit Correct? A Multi-Dimensional Benchmark for Reasoning-Aware Image EditingYixuan Ding et al.arXiv2
2026-06-042606.03577Eliciting Complex Spatial Reasoning in MLLMs through Wide-Baseline MatchingHao Zhong et al.arXiv14
2026-06-022606.01247Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?Liyang Li et al.arXiv26
2026-06-012605.30940Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion TransformerKe Lei et al.arXiv33
2026-06-012605.28618Comprehensive Benchmarking of Long-Form Speech Generation in Diverse ScenariosChanghao Pan et al.arXiv28
2026-05-292605.30219When Should Models Change Their Minds? Contextual Belief Management in Large Language ModelsHaoming Xu et al.arXiv22
2026-05-292605.30060Towards Consistent Video Geometry EstimationZhu Yu et al.arXiv3
2026-05-262605.26115TriSplat: Simulation-Ready Feed-Forward 3D Scene ReconstructionWeijie Wang et al.arXiv54
2026-05-152605.13169PanoWorld: Towards Spatial Supersensing in 360^circ Panorama WorldChangpeng Wang et al.arXiv19
2026-05-152605.09681Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion ModelsYicheng Ji et al.arXiv5
2026-05-082605.06507MARBLE: Multi-Aspect Reward Balance for Diffusion RLCanyu Zhao et al.arXiv38
2026-05-052605.00877OceanPile: A Large-Scale Multimodal Ocean Corpus for Foundation ModelsYida Xue et al.arXiv14