· software
Blog: PyPI in 2025: A Year in Review
markdown PyPI 2025 Year‑in‑Review Tags - new featureshttps://blog.pypi.org/tags/tag:new-features - organizationshttps://blog.pypi.org/tags/tag:organizations - s...
-
- · software
PyPI in 2025: A Year in Review
markdown 2025 Year in Review: PyPI Highlights Tags: new featureshttps://blog.pypi.org/tags/tag:new-features • organizationshttps://blog.pypi.org/tags/tag:organi...
- · ai
[Paper] SpaceTimePilot: Generative Rendering of Dynamic Scenes Across Space and Time
We present SpaceTimePilot, a video diffusion model that disentangles space and time for controllable generative rendering. Given a monocular video, SpaceTimePil...
- · software
S3 Vectors: 90% Cheaper Than Pinecone? Our Migration Guide
Last week, I got a Slack message from our Finance Team that made my stomach drop: > “Why is our Pinecone bill $4,200 this month?” We’re running a mid‑sized RAG...
- · ai
[Paper] GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstruction
Recent advances in 3D reconstruction have achieved remarkable progress in high-quality scene capture from dense multi-view imagery, yet struggle when input view...
- · ai
[Paper] Coordinated Humanoid Manipulation with Choice Policies
Humanoid robots hold great promise for operating in human-centric environments, yet achieving robust whole-body coordination across the head, hands, and legs re...
- · ai
[Paper] Edit3r: Instant 3D Scene Editing from Sparse Unposed Images
We present Edit3r, a feed-forward framework that reconstructs and edits 3D scenes in a single pass from unposed, view-inconsistent, instruction-edited images. U...
- · ai
[Paper] Scaling Open-Ended Reasoning to Predict the Future
High-stakes decision making involves reasoning under uncertainty about the future. In this work, we train language models to make predictions on open-ended fore...
- · ai
[Paper] FineTec: Fine-Grained Action Recognition Under Temporal Corruption via Skeleton Decomposition and Sequence Completion
Recognizing fine-grained actions from temporally corrupted skeleton sequences remains a significant challenge, particularly in real-world scenarios where online...
- · ai
[Paper] From Inpainting to Editing: A Self-Bootstrapping Framework for Context-Rich Visual Dubbing
Audio-driven visual dubbing aims to synchronize a video's lip movements with new speech, but is fundamentally challenged by the lack of ideal training data: pai...
- · ai
[Paper] Vulcan: Instance-Optimal Systems Heuristics Through LLM-Driven Search
Resource-management tasks in modern operating and distributed systems continue to rely primarily on hand-designed heuristics for tasks such as scheduling, cachi...
- · ai
[Paper] Many Minds from One Model: Bayesian Transformers for Population Intelligence
Despite their scale and success, modern transformers are almost universally trained as single-minded systems: optimization produces one deterministic set of par...