…dexterous manipulation built on the Multi-Stream Action Transformer (MSAT), an architecture that unifies these capabilities by integrating heterogeneous modalities through modality-specific streams with cross-modal joint self-attention . RLDX-1…
…Built on top of this adaptive execution layer, we propose Learning to Act and Cooperate (LACMAS), a trajectorydriven framework in which large language models provide sparse highlevel guidance for shaping both agentinternal…
…It is built on three key designs. Stochastic Condition Masking (SCM) randomly partitions modalities into clean conditions and noisy targets during training, enabling omni-directional conditional generation instead of fixed mappings. Decoupled…
…a self-supervised visual encoder , and grounds language goals via blind matching without any paired vision-language data. Extensive experiments on simulation benchmarks including HM3D-IIN, OVON, and R2R-CE on MP3D…
…The following papers were recommended by the Semantic Scholar API Coupling Models for One-Step Discrete Generation (2026) ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving (2026) FlowS: One…
…long-horizon drift on multi-step tasks and mid-clip simulation errors that compound. Both stem from the absence of explicit reasoning built upon the VGM's short-horizon visual prior, a…
…View arXiv page View PDF Project page GitHub 26 Add to collection Community This work introduces On-policy Data Evolution (ODE) for visual-native multimodal deep search agents. It combines an image…
…Benchmarking Chart Parsing across Languages, Scenarios, and Formats Published on May 31 Submitted by Peng Shangpin on Jun 2 Authors: Shangpin Peng , , , , , , , , , , , , Abstract ChartArena presents a comprehensive bilingual benchmark for chart parsing…
…it solves it." 100 tasks across 15 domains, built on the TICOS framework (Task / Introspection / Calibration / Output / Self-correction) Already #5 globally on HF Datasets popularity Officially endorsed by the HF Evaluation…
…Sliding Window Attention on three of every four layers, and a single Multi-Token Prediction head that doubles as both an auxiliary pre-training objective and a built-in draft model for…