AI Dataset2026
Provides 30,969 action-conditioned video episodes, each with source MP4, per-frame keyboard control logs, captions, and a COLMAP sparse pose model — intended for research on action-conditioned video prediction, controllable world models, and representation learning.
AI Dataset2026
Provides 90,000 hours of head-mounted egocentric video paired with synchronized 3D hand pose and an optional 3D full‑body pose add-on, with event-level semantic labels available as a complimentary layer — designed for embodied AI and robotics training at scale.
AI Video Papers2026
Predicts future video frames conditioned on an observed frame, a language instruction, and a sequence of end-effector poses and gripper states for robot manipulation. Uses per-arm SE(3) geometric encoding (PRoPE-style), a lightweight depth branch, SAM3 masks with a frozen V-JEPA teacher, and distribution-matching distillation for efficient, consistent action-conditioned rollouts.
Provides a large-scale benchmark and a human-aligned metric for humanoid whole-body motion tracking — about 153 hours of optical mocap from professional performers plus HumanScore trained on 12K human-labeled preference pairs to reveal contact, timing, and stability failures.
AI Agent Papers2026
Enables closed-loop execution for embodied agents by evolving code-based runtime critics and recovery skills online while keeping the base policy frozen. Combines three timescale loops with Z-Infra rollout infrastructure; reports 90.8% on LIBERO-Pro, 93.6% on RoboCasa and an 11.1× inference speedup.
Embodied AI2026
Turns embodied navigation into 2D visual prompting where a vision-language model selects image pixels that are projected to 3D actions; adds selective chain-of-thought, compressed anchor-trajectory memory, and a two-level alignment objective to improve sample and runtime efficiency.
AI Video Papers2026
Generates enterable omnimodal world-model rollouts that follow continuous 6-DoF camera control while jointly producing 720p video, environmental sound, music and speech. Uses dataset-level motion calibration, a specialized data engine, progressive training and autoregressive post-training to support long-horizon first- and third-person interaction.
AI Model2026
Integrates a pretrained vision–language model with a BEV perception head and a Planning Expert to provide 3D perception, driving VQA and motion planning for autonomous driving while keeping the base VLM architecture unchanged.
Provides a real-scale 3D Hong Kong sandbox to evaluate whether multimodal LLM agents can turn local street-view perception into sustained spatial action, supporting closed-loop first-person interaction, an interactive map, and controlled tests of grounding, long-range navigation, and robustness.
Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models
Proposes VLAct, a representation-centric continued pre-training method for Vision-Language-Action models that preserves VLM priors and enforces cross-embodiment action semantics to turn limited robot trajectories into transferable visual-action representations; shows strong gains and sample efficiency on multiple VLA benchmarks using modest compute.
Generates synchronized spoken dialogue and explicit full-body co-speech motion (facial expressions, hands, upper- and lower-body) end-to-end from the same hidden states, replacing the speech-then-motion cascade. Trains with a scalable pseudo-labeling pipeline (422,856 ranked pairs) and supports real-time inference (RTF 0.78) while matching teacher motion metrics within ~2%.
Converts posed indoor RGB(-D) video into editable, simulation-ready 3D scene graphs by parsing multi-view evidence into per-object bundles, generating complete object assets from that evidence, and placing them with GizmoAct, a VLM policy that refines 9-DoF poses through closed-loop GUI actions.