←
Jeffrey Hu13 posts
Jeffrey Hu avatar

Jeffrey Hu

@jefequien

Ph.D. Student at University of Cambridge. Building generative models for the real world.

◷ Joined September 2013▧ 3 Photos and videos
Jeffrey Hu avatar
Jeffrey Hu@jefequien·Oct 6

Introducing S2PD: Serial-to-Parallel Diffusion. Bidirectional video models fail to follow simple rules even when trained on enormous amounts of data. We show that serial computation is critical for generating consistent video and use it in the high-noise regime of video diffusion. Project Page: jefequien.github.io/S2PD/

0:42
Hyunwoo Ryu avatar
⟳ Jeffrey Hu retweeted
Hyunwoo Ryu@RyuHyunwoooo·Oct 20

Working on Mirror convinced me of something too opinionated for a paper: we've been over-obsessed with "action" in embodied AI. (1/15)

If video models scale like LLMs, they'll soon generate a perfect video plan for any embodied task. Do we need anything else? Introducing Mirror, which learns to follow these plans just by practicing, and even crafts an iron pickaxe in Minecraft w/o rewards or action labels! (1/n)

1:15
AI Bites | YouTube Channel avatar
⟳ Jeffrey Hu retweeted
AI Bites | YouTube Channel@ai_bites·Oct 7

Video generation can produce visually plausible clips while still violating basic physical laws or symbolic rules. S2PD—Serial-to-Parallel Diffusion—addresses this by combining two stages: autoregressive diffusion at high noise to coordinate dependent events and valid state transitions, followed by parallel diffusion at low noise to refine the full video more efficiently. Across games, physical simulations, and real video, S2PD follows rules more reliably than matched bidirectional baselines while offering greater temporal stability and improved sampling efficiency compared with other serial approaches. The method is presented with both a pixel-space diffusion transformer and a LoRA-adapted pretrained video model. Title: S2PD: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video Generation Project URL: jefequien.github.io/S2PD/ Paper: arxiv.org/abs/2610.06847v1

0:10
Shumpei Takezaki avatar
⟳ Jeffrey Hu retweeted
Shumpei Takezaki@shumpeiMaxwell·Oct 7

S2PD: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video Generation TL;DR: S2PD combines autoregressive diffusion at high noise with parallel diffusion at low noise, improving rule-following, physical consistency, temporal stability, and sampling efficiency in video generation. arxiv.org/abs/2610.06847

Jeffrey Hu avatar
Jeffrey Hu@jefequien·Oct 6

S2PD generates videos twice as fast as other purely serial methods. The parallel refinement stage lets all blocks reconcile their appearance together, improving temporal stability and reducing flicker.

0:22
Jeffrey Hu avatar
Jeffrey Hu@jefequien·Oct 6

We train block diffusion across multiple block sizes. This lets us use small block sizes to commit to structure serially at high noise, then refine the whole video together in parallel at low noise.

0:19
Hang Gao avatar
⟳ Jeffrey Hu retweeted
Hang Gao@hangg70·Jun 3

ruilong has been one of the best folks in the world in speeding things up. when he releases something, it's gonna be both performant and easy-to-use.

World models are moving beyond offline generation towards interactive, real-time experiences. Introducing ⚡FlashDreams⚡: an open-source high-performance inference and serving library built for autoregressive world models: 🔥 Up to 3.10× faster LingBot-World inference 🔥 Up to 2.12× faster Self-Forcing inference 🔥 Up to 1.40× faster Wan2.1 inference 🔥 8 integrated models 🔥 Multi-GPU, streaming, low-latency serving 🔥 Agentic skills that teach you how to use it FlashDreams is designed for a new generation of AI systems that continuously evolve over time while responding to user interactions. It powers applications across robotics, autonomous vehicle simulation, gaming, and virtual worlds. Github: github.com/NVIDIA/flashdream… Docs: nvidia.github.io/flashdreams Research page: research.nvidia.com/labs/sil… Join the #flashdreams Discord channel at discord.gg/yTdHDqFP FlashDreams is also the runtime backbone behind NVIDIA OmniDreams (github.com/nv-tlabs/omni-dre…) 1/n #AI #WorldModels #FastInference #PhysicalAI #OpenSource #NVIDIA

0:47
MrNeRF avatar
⟳ Jeffrey Hu retweeted
MrNeRF@janusch_patas·15 Oct 2025

[SIGGRAPH Asia '25] Editable Physically-based Reflections in Raytraced Gaussian Radiance Fields Contributions: • A reconstruction method for radiance fields, with distinct optimization for diffuse and specular components, using path tracing for the latter. • An efficient and accurate training method that reconstructs the diffuse and specular components of the scene in a single representation. • An efficient ray tracer for Gaussian primitives, fast enough to enable treatment of multiple bounces with minimal computational overhead.

0:31