←
Ayush Tewari137 posts
Ayush Tewari avatar

Ayush Tewari

@_atewari

Assistant Professor @Cambridge_Eng

◷ Joined December 2018▧ 12 Photos and videos
Ayush Tewari avatar
Ayush Tewari@_atewari·Oct 6

Video models can be physically and logically consistent! Check out S2PD - we show consistent generations on a large set of games and simulations. Bidirectional models fail to generate consistent outputs on most of these datasets. jefequien.github.io/S2PD/

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
Markus Wulfmeier avatar
⟳ Ayush Tewari retweeted
Markus Wulfmeier@m_wulfmeier·Nov 12

Thanks to @rankprize for a wonderful symposium on World Models and Physical Intelligence last week in the beautiful Lake District! A reminder of why I love small conferences: time to dig into ideas and conversations that keep going long after the talks. Huge thanks to @robertocipolla, @_atewari and Helen Berrington for making it happen! And a shoutout to our early career awards: @ishaanpreetam, @FelixOMahony and @makezur 👏

Post attachment
Ayush Tewari avatar
Ayush Tewari@_atewari·Nov 17

Check out this cool NeurIPS paper - we present a model that unifies 3D reconstruction and generation by jointly modeling video, depth, and camera!

Video models can generate scenes. Geometry models can reconstruct them. What if one model did both? UGG generates video, depth and camera motion together, as one scene. (NeurIPS 2026) Co-first authors: @ZhiyiLi02 and @ruojin8 🌐 ugg-model.github.io

0:55
Arthur Mensch avatar
⟳ Ayush Tewari retweeted
Arthur Mensch@arthurmensch·Oct 16

Should Europe leave frontier AI to the Americans and the Chinese? The idea has gained ground in Europe. It is a fundamental mistake. Build or surrender: for now, the choice is still ours. Full article below.

AI Bites | YouTube Channel avatar
⟳ Ayush Tewari 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
⟳ Ayush Tewari 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

Yichao Liang avatar
⟳ Ayush Tewari retweeted
Yichao Liang@yichao_liang·Oct 7

EMPIRIC is my last first-author paper as a PhD student. It builds on my earlier work on learning for generalizable robot planning: • Manipulation skills: RMA² (CVPR 2024) x.com/yichao_liang/status/18… • State abstraction: VisualPredicator (ICLR 2025) x.com/yichao_liang/status/18… • Temporal abstraction: ExoPredicator (ICLR 2026) x.com/yichao_liang/status/19… • Residual world models: EMPIRIC (quoted below) I'm on the job market for research roles in world models, RL, robotics and agents. Please reach out if you think I might be a good fit!

Agentic real-to-sim is getting increasingly good at rebuilding scenes in a physics simulator. But looking at a scene does not reveal how glue cures, how water heats, or how a fan's wind pushes things. And what if the simulator cannot model these mechanisms at all? We present EMPIRIC, an agent that learns a residual world model: a physics engine extended with code for the missing mechanisms. It solves all 25 runs across five simulated domains, where coding-agent baselines solve 14 to 16, and on a real robot it learns wind and domino masses from two gusts. basisresearch.github.io/empi… [1/9]

0:34
Andrei Bursuc avatar
⟳ Ayush Tewari retweeted
Andrei Bursuc@abursuc·Jun 3

Bill Freeman gives us first a list of warm-up bitter lessons. He keeps the bigger ones for later in the talk. #cvpr2026

Post attachment
Tobias Fischer avatar
⟳ Ayush Tewari retweeted
Tobias Fischer@TobiasFischer11·May 30

Do 3D reconstruction transformers really need a billion parameters, or are most of those layers just doing the same thing over and over? Introducing Déjà View: a single transformer block, looped K times, that matches or beats models 8–10× its size with lower compute. 🧵

0:14
Ayush Tewari avatar
Ayush Tewari@_atewari·Jun 2

Check out 3D-Belief: a 3D world model that explores how explicit belief representations can support memory, imagination, and planning under partial observability.

What should a world model capture for embodied agents? An agent acting under partial observability needs a belief over the 3D world: what it has seen, what may exist beyond view, and how that belief should update as it moves. Introducing 3D-Belief, a 3D world model for embodied belief inference under partial observability. 🧵[1/9]

0:20
Jianwen Xie avatar
⟳ Ayush Tewari retweeted
Jianwen Xie@jianwen_xie·Jun 1

Nice work! World models meet active sensing and closed-loop planning. We'll be showcasing this demo at the Lambda booth @chuanli11 during CVPR main conference at Denver. If you're attending, stop by and check it out! #cvpr @CVPR We are also hosting a world-model-related workshop at CVPR : cvpr26wmas.github.io/cvpr26w…

What should a world model capture for embodied agents? An agent acting under partial observability needs a belief over the 3D world: what it has seen, what may exist beyond view, and how that belief should update as it moves. Introducing 3D-Belief, a 3D world model for embodied belief inference under partial observability. 🧵[1/9]

0:20
Elliott / Shangzhe Wu avatar
⟳ Ayush Tewari retweeted
Elliott / Shangzhe Wu@elliottszwu·Mar 13

I’m looking for a PhD student with UK home fee status to join my lab at Cambridge starting this October. If you’re interested and have research experience in multimodal spatial modeling or vision-based robot learning, email me your CV. Funding deadline is approaching very soon.

Ayush Tewari avatar
Ayush Tewari@_atewari·Feb 14

In addition to physical plausibility, the use of a python simulator makes it easy for users to modify the simulation! Check out the project page for many more examples.

0:18