inclusionAI · 18 records

dateidtitleauthorsvenue↑
2026-11-192611.22925Code World Model 2.0: Towards Infinite Controllable Video GenerationRuoyu Wang et al.arXiv19
2026-11-162611.16661Reducing Batch Makespan for LLM Agent Workloads through Inference-Environment CoordinationWei Feng et al.arXiv4
2026-11-112611.15131Duo: A Reciprocal World Model for Full-Duplex InteractionHengyuan Cao et al.arXiv40
2026-11-022610.37918Venus-DefakerOne2: A Vision-Forensics Foundation Model with Broader CoverageChenfan Qu et al.arXiv20
2026-10-292610.39633Intrinsic Distribution MatchingDeyuan Liu et al.arXiv18
2026-10-272610.37037Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal PerceptionLai Wei et al.arXiv31
2026-10-122609.37712PolyOCR-Venus: Unified OCR Foundation Models for Text-Centric Visual IntelligenceGuangJian Team et al.arXiv31
2026-09-232609.25270RULER: Instance-aware Rubric Rewards for SVG GenerationHangyu Ran et al.arXiv98
2026-09-222609.13814Realtime-Venus: A full-duplex interaction system with asynchronous delegationRuixiang Zhao et al.arXiv151
2026-09-152609.13287LLaDA-UI: Bringing Block-wise Diffusion to Vision-Language GUI AgentsZhangxuan Gu et al.arXiv16
2026-09-042609.03796LLaDA-Image: Building Strong Image Generators with Fully Open Training RecipesChuyan Chen et al.arXiv58
2026-08-252608.16812Unlocking the Potential of Image Editing via Concept Scaling and Dense SupervisionLong Cui et al.arXiv52
2026-07-152607.14183Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied LearningZishuo Li et al.arXiv66
2026-06-292606.22873SingGuard: A Policy-Adaptive Multimodal LLM Guardrail with Dynamic ReasoningSingGuard TeamarXiv9
2026-06-192606.20381Rethinking Shrinkage Bias in LLM FP4 Pretraining: Geometric Origin, Systemic Impact, and UFP4 RecipeQian Zhao et al.arXiv9
2026-06-182606.19047RODS: Reward-Driven Online Data Synthesis for Multi-Turn Tool-Use AgentsRuishan Fang et al.arXiv4
2026-06-162606.15079Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter ScaleAng Li et al.arXiv81
2026-06-102606.07512MemDreamer: Decoupling Perception and Reasoning for Long Video Understanding via Hierarchical Graph Memory and Agentic Retrieval MechanismCong Chen et al.arXiv40