Issue 86
City-scale 3D grounding is commonly formulated as candidate ranking, which requires precomputed instance proposals and becomes inefficient in large outdoor scenes. We propose Urbex, an agentic vision-...
System one models enable direct, low-latency decision-making. Yet recent practice of predicting an answer from serialized text does not, by itself, respect the structure of a decision problem. We argu...
Visual agents must turn video observations into timely decisions to track progress and choose what to do next. Building on the emerging System One paradigm, we introduce VideoJev, a family of models t...
Large language models have evolved from single-turn chatbots into interactive agents capable of long-horizon reasoning. In real deployments, MCP tool services can return noisy feedback and users may i...
Generating information-rich visual artifacts such as slides, posters, and dashboards as code is appealing because the outputs are structured, editable, and verifiable. Yet code models cannot see how t...
Recent advances in vision-language models (VLMs) have substantially improved the capabilities of GUI agents, while memory augmentation has emerged as a promising approach for reusing knowledge from pa...
Reinforcement learning with verifiable rewards (RLVR) for multi-turn agents relies on sparse terminal rewards that say little about individual steps. Within-group step comparisons depend on reliable s...
Reliable video reasoning requires models to produce correct answers and expose supporting visual evidence. Open-o3-Video enables verifiable reasoning by embedding timestamps and object-level bounding ...
Learning humanoid loco-manipulation from human demonstrations rests on observing how locomotion, posture, and object interaction evolve together as tasks unfold. Scaling collection across diverse envi...
Sparse-to-dense motion completion recovers dense mesh motion from sparse vertex displacements. Residual priors trained on one geometry family frequently fail to beat parameter-free harmonic extension ...