gokul

PhD candidate @UofIllinois (UIUC) @CSL_Illinois | Current: robotics research intern @Nvidia | ex-research science intern @Adobe Research

[gokul @gokulp01]

We are presenting Muninn at RSS 2026, and we're incredibly honored that it has been selected as a finalist for both the Outstanding Paper & Outstanding Student Paper awards! #RSS2026

TL;DR: diffusion planners generate great robot trajectories, but nobody wants 100 denoiser calls inside a control loop. Existing speedups (truncation, distillation, fixed skipping) trade quality for speed in ways you can't predict before deployment. Muninn is a training-free wrapper that skips denoiser calls only when it can certify the final plan stays within your tolerance 🧵 (1/9)

📄 Paper: https://t.co/iQsl5VCiSo
💻 Code: https://t.co/BUZSeA4dtC

[gokul @gokulp01]

@pralichan Thank you so much, Prahaladh ☺️☺️☺️

[gokul @gokulp01]

Muninn won the Outstanding Student Paper Award at #RSS 2026!!

Huge thank you to my collaborators and advisors, this work would not exist without them! And to the #RSS community for the recognition and for organizing such an awesome conference!

We have also open-sourced the core repository. The plan is to actively maintain it, and to benchmark and speed up as many diffusion-based trajectory planners as we can get our hands on. If your robot plans with diffusion, try it out! Issues and PRs very welcome.

📄 Paper: https://t.co/vCvPhFlNfY
💻 Code: https://t.co/BUZSeA4dtC

cc: @RoboticsSciSys

[gokul @gokulp01]

We are presenting Muninn at RSS 2026, and we're incredibly honored that it has been selected as a finalist for both the Outstanding Paper & Outstanding Student Paper awards! #RSS2026

TL;DR: diffusion planners generate great robot trajectories, but nobody wants 100 denoiser calls inside a control loop. Existing speedups (truncation, distillation, fixed skipping) trade quality for speed in ways you can't predict before deployment. Muninn is a training-free wrapper that skips denoiser calls only when it can certify the final plan stays within your tolerance 🧵 (1/9)

📄 Paper: https://t.co/iQsl5VCiSo
💻 Code: https://t.co/BUZSeA4dtC

[gokul @gokulp01]

@Yatharth310 Thank you very much Yatharth ☺️☺️☺️

[gokul @gokulp01]

@atu_tej Thank you very much, Atula ☺️☺️

[gokul @gokulp01]

@Lightisu Thank you so much ☺️

[gokul @gokulp01]

We are presenting Muninn at RSS 2026, and we're incredibly honored that it has been selected as a finalist for both the Outstanding Paper & Outstanding Student Paper awards! #RSS2026

TL;DR: diffusion planners generate great robot trajectories, but nobody wants 100 denoiser calls inside a control loop. Existing speedups (truncation, distillation, fixed skipping) trade quality for speed in ways you can't predict before deployment. Muninn is a training-free wrapper that skips denoiser calls only when it can certify the final plan stays within your tolerance 🧵 (1/9)

📄 Paper: https://t.co/iQsl5VCiSo
💻 Code: https://t.co/BUZSeA4dtC

[gokul @gokulp01]

@leoperzz Thank you very much Leonardo☺️

[gokul @gokulp01]

Muninn is training-free, never touches your model's weights or sampler, and composes with distilled/few-step models — it removes the per-step redundancy that remains even there! (9/9)

We are presenting Muninn at RSS on July 15 (today!), please stop by!

📄 Paper: https://t.co/iQsl5VCiSo
💻 Code: https://t.co/BUZSeA4dtC
More videos below 👇

[gokul @gokulp01]

The reuse pattern itself turned out to be informative. Muninn's compute concentrates where planning is hard: episodes in open space settle around ~12 denoiser evals, tight-clearance scenes climb to ~22 without anyone telling it what "hard" means. Fixed accelerations spend identically everywhere; Muninn reallocates compute to the risky moments for free. (7/9)

[gokul @gokulp01]

Because Muninn tracks its deviation bound online, you also get a runtime health signal. In closed-loop deployments in marine navigation, aerial navigation and manipulation, the tracked bound spikes right at near-collision and contact events (a natural trigger for escalating to full compute or a conservative safety controller). Hardware speedups: upto 2.5×, with success rates matching the full models. (8/9)

[gokul @gokulp01]

Across multiple diffusion planners, policies and benchmarks Muninn cuts wall-clock latency by 2–4.6× and denoiser evaluations by up to 7.7×, with task metrics within a point of the full models and empirical violation rates under the α = 0.05 target in every configuration we ran. (6/9)

[gokul @gokulp01]

At deployment you pick two numbers: how much final-trajectory deviation you can tolerate, and what failure probability you can accept. Muninn then decides, step by step and per sample, whether to reuse or recompute, and guarantees the accelerated planner stays within your tolerance with the probability you asked for. Interpretable knobs, no schedule tuning, no per-task magic constants. (5/9)

[gokul @gokulp01]

Muninn connects the two offline. We run the planner at full compute on calibration rollouts and, at every step, also log what the error would have been had we reused the cached output (a "ghost" reuse chain). Conformal prediction on these pairs yields an upper bound on reuse error as a function of the probe signal, valid without assumptions on the model or the error distribution. (4/9)

[gokul @gokulp01]

We realized trajectory diffusion planners expose two signals that make safe reuse predictable: (1) the denoiser's input stem is cheap to run, and when its features stop changing between consecutive steps, the full output has usually stabilized too; (2) for DDPM/DDIM-style samplers the update is analytic, so you can compute how much an error injected at step t gets amplified by the end of the chain. One tells you how wrong reuse might be, the other tells you how much that wrongness matters. (3/9)

[gokul @gokulp01]

Why is caching hard here? Because a reused denoiser output is not a local approximation. The sampler mixes it back into every timestep of the plan, errors compound over the remaining steps, and control objectives are discontinuous: two trajectories that look nearly identical can be the difference between reaching the goal and hitting the obstacle. Skip heuristics tuned on average behavior fail exactly in the states where you can't afford it. (2/9)

[gokul @gokulp01]

@ellen_in_sf literature review

[gokul @gokulp01]

@golpanipuri Thank you very much (:

[gokul @gokulp01]

Very cool line of work! We build on Drifting Models in our v recent work on Keyed Drifting Policies to get one-step, condition-aware trajectory planning for offline RL and robotics. diffusion-like planning behavior, without the denoising loop (:

[Goodeat @Goodeat258]

We’ve released the code for Drifting Models :)

Includes full training, inference, and pretrained weights.

Curious to see what people build on top of this.
https://t.co/NabiwbfDRt

[gokul @gokulp01]

@moritz_reuss Awesome read!