Ant Group · 24 records

dateidtitleauthorsvenue↑
2026-11-172611.13685Ego Guidance: Enhancing Robot Policy Learning with Action-Free Human Egocentric VideosLin Long et al.arXiv5
2026-11-132611.16517UniSpark: Exploring Hybrid Attention for Multimodal Understanding and GenerationJiancheng Pan et al.arXiv12
2026-11-102611.08935SkinMind: Equipping Agentic RAG with Human-Inspired Graph Probing for Reliable Dermatology AIJing Hao et al.arXiv4
2026-11-062611.04894VisSearch-Bench: Evaluating Long Horizon Visual Search in Multimodal AgentsZhengXian Wu et al.arXiv21
2026-11-052611.06083SleuthVLM: Do We Really Need Audio-in-Video for Omni Video Understanding?Peiran Wu et al.arXiv7
2026-11-012611.02074SWE-Trail: History-Guided Trajectory Collection for Coding Agent TrainingZiming Li et al.arXiv38
2026-10-092609.35855Mara Chain: Rethinking Failure as a Stepping Stone for AI System Auto-EvolutionYubin Lyu et al.arXiv7
2026-09-302609.34378Marathoner: Ultra-Long-Horizon Autonomous IntelligenceZhang Ruiyang et al.arXiv27
2026-09-302609.34605PMOPD: Task Ordering, Cycling, and Parameter-Update Subspace Protection in Multi-Teacher On-Policy DistillationYouzhi Liu et al.arXiv12
2026-09-222609.244321% of Tokens Can Be Enough: On Gradient Estimation in On-Policy DistillationHuanxin Sheng et al.arXiv16
2026-09-152609.15134HazardAuditor: From Executable Threats to Safer Computer-Use AgentsYunhao Feng et al.arXiv18
2026-09-022609.00028UI-Venus-2 Technical ReportVenus Team et al.arXiv65
2026-08-312608.27906Rubric-to-Code Credit Assignment for Reinforcement LearningRui Jin et al.arXiv8
2026-08-282608.25500CaSKG: Counterfactual-Causal Skill Graphs for Scalable Agent Skill RetrievalZhiyuan Li et al.arXiv6
2026-08-252608.23392Towards a Densing Law for User Representation Learning at Billion-Scale CapacityBin Dou et al.arXiv26
2026-07-282607.22148dRAE: Representation Autoencoder with Hyper-Spherical CodesTianren Ma et al.arXiv10
2026-07-212607.07050Diagnosing and Calibrating Tool-Call Boundary Drift in Multi-Teacher On-Policy DistillationJiabin Shen et al.arXiv4
2026-07-172607.15257SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent CollaborationYuyao Zhang et al.arXiv69
2026-07-072607.01793Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded VerificationYunhao Feng et al.arXiv5
2026-06-252606.24849IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image GenerationZixuan Li et al.arXiv19
2026-06-042606.01166BraveGuard: From Open-World Threats to Safer Computer-Use AgentsYunhao Feng et al.arXiv5
2026-06-022606.01311SkillAdaptor: Self-Adapting Skills for LLM Agents from TrajectoriesZhuoyun Yu et al.arXiv32
2026-06-012605.30434LongDS-Bench: On the Failure of Long-Horizon Agentic Data AnalysisKewei Xu et al.arXiv18
2026-05-132605.12496CausalCine: Real-Time Autoregressive Generation for Multi-Shot Video NarrativesYihao Meng et al.arXiv30