Tracked topic
…An Action-Conditioned World Model for Digital Teleoperation Published on Jul 7 Submitted by taesiri on Jul 8 Authors: , , , , , Siteng Huang , , , Abstract Digital teleoperation replaces physical robot interaction with generative world models…
…Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation (2026) TIDE: Task-Isolated Diffusion for Unified Video Editing and Generation (2026) Sparkle: Realizing Lively Instruction-Guided Video Background Replacement via…
Papers arxiv:2606.01961 AutoMedBench: Towards Medical AutoResearch with Agentic AI Models Published on Jun 3 Submitted by Tianhao Qi on Jun 3 University of California, Santa Cruz Authors: , , , , , , Tianhao Qi , , Yucheng…
…SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models (2026) Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL (2026) Offline Preference Optimization for Rectified Flow with…
…Internalizing Visually Grounded Reasoning for MLLMs with Reinforcement Learning (2026) V-Zero: Answer-Label-Free On-Policy Distillation with Contrastive Evidence Gating for Fine-Grained Visual Reasoning (2026) From Seeing to Thinking…
…To avoid the geometric ambiguity and trivial collapse of naive volume minimization, we combine simplex-volume minimization with a cosine regularizer and a contrastive objective . Our analyses show that DynaFLIP focuses on…
…automated message from the Librarian Bot . I found the following papers similar to this paper. The following papers were recommended by the Semantic Scholar API LatentOmni: Rethinking Omni-Modal Understanding via Unified…
…Emerging Multi-Agent Intelligence with Economic Interactions Published on Jun 1 Submitted by Zhenting Qi on Jun 4 Harvard University Authors: , Huangyuan Su , , , , , , Guowei Xu , , , , , , , , Abstract Decentralized agent economies with auction-based…
…Yanbiao Ji , , , , , , , , , Abstract EnergyFlow unifies generative action modeling with inverse reinforcement learning by parameterizing an energy function whose gradient serves as a denoising field, enabling reward extraction without adversarial training while improving…
…closed-loop embodied inference edge-side / on-robot deployment heterogeneous devices and hardware backends unified support across different embodied model families This is exactly the gap we target with Embodied.cpp : a…