what makes a good paper video? what are some of the best you have seen? cc: @davidpicard.bsky.social @davidbau.bsky.social @eugenevinitsky.bsky.social @chriswolfvision.bsky.social @nsaphra.bsky.social @ducha-aiki.bsky.social @parskatt.bsky.social @martin-r-oswald.bsky.social @ericzzj.bsky.social

iiim8uhl j ij9j b knmnjj mlpnnom l 8kc6 Kimberly.C mbkln9j8 . ojlioij7o.h ihlokMO Lip l 9 b nl d9

Very proud that our paper has been accepted to @iccv.bsky.social !!! See you in Hawaii! bsky.app/profile/duch...

🎉 Thrilled to share our CVPR 2025 Award Candidate & Oral paper: 🔹 GlobustVP Convex Relaxation for Robust Vanishing Point Estimation in Manhattan World 🧱 Global optimality 💥 Tolerates up to 70% outliers ⚡ Fast runtime 📄 Paper: arxiv.org/abs/2505.04788 💻 Code: github.com/WU-CVGL/GlobustVP 1/

#ICCV2025 reviews are out and being sent via email to authors! They will also be available on OpenReview later. 11,152 active submissions all have at least 3 reviews. Authors have the opportunity to submit a rebuttal by May 16 2025 11:59 PM HST.

🚨 Just one month left to submit your solutions for The Structured Semantic 3D Reconstruction (S23DR-2025) Challenge!!! It is not too late to join! Comp on @hf.co, part of the Workshop on Urban Scene Modeling at @cvprconference.bsky.social 2025 🔥$25,000 prize pool. Deadline: June 5, 2025. 🧵 (1/7)

hey @cloneofsimo.bsky.social (or anyone else) did you ever try LoRA+ style LR split between down/up LoRA projection matrices on diffusion models?

Lots of progress in mech interp (MI) lately! But how can we measure when new mech interp methods yield real improvements over prior work? We propose 😎 𝗠𝗜𝗕: a 𝗠echanistic 𝗜nterpretability 𝗕enchmark!

1 week to USM3D deadline

Explaining Human Preferences via Metrics for Structured 3D Reconstruction @jacklangerman.bsky.social Denys Rozumnyi, Yuzhong Huang, @ducha-aiki.bsky.social tl;dr: we asked 3D modelers to rank wireframe reconstructions & compared it to ranking by metrics. Observations🧵 1/ arxiv.org/abs/2503.08208

2nd Building3D #CVPR2025 challenge at #USM3D workshop is open! Task: point cloud to wireframe. Prize pool: $10k Competition deadline: May 25 2025. Website: huggingface.co/spaces/Build... @cvprconference.bsky.social

We made a new keypoint detector named DaD, paper isn't up yet, but code and weights are: github.com/Parskatt/dad

Those, who work in structured (images/pcl to CAD) reconstruction - USM3D #CVPR2025 workshop submissions are open. Deadline: March 24 2025 Both full papers (8 pages) and extended abstracts (4 pages) are OK usm3d.github.io #USM3D @cvprconference.bsky.social @jacklangerman.bsky.social

We have extended the deadline for paper submission for Image Matching Workshop. Anything image matching or 3D reconstruction related is welcomed Now it is March 17 @cvprconference.bsky.social #CVPR2025 image-matching-workshop.github.io

oh no....

what is the best intro I can send people who suddenly want to know "what is AI?" and "what is a transformer based model?" but arent really going to invest tons of time and maybe dont have any math background? my default is 3b1b, but does anyone have another suggestion?

Image matching and ChatGPT - new post in the wide baseline stereo blog. tl;dr: it is good, even feels like human, but not perfect. ducha-aiki.github.io/wide-baselin...

lol 4o just decided to throw this rocket emoji into a normal technical conversation for no apparent reason who's overly excited discord / slack is responsible for this?

📢MeshArt: Generating Articulated Meshes with Structure-guided Transformers Daoyi Gao generates articulated meshes with a hierarchical transformer, modeling articulation-aware structures that guide mesh synthesis. w/ Yawar Siddiqui, Lei Li Project Page: daoyig.github.io/Mesh_Art/

"I'm a programmer, not a reptile. I have a Python logo on my gear, but I don't have scales or a slithery body." x.com/voooooogel/s...

Anyone have opinions on Mac Book Air M3 as a personal laptop if I still want to mess with some models on the weekend now and then?

Now you can "play" CS:GO in a neural network directly in the browser: next.journee.ai/xyz-diamond

If anyone has first-hand experience with e-ink tablets: Is the reMarkable Paper Pro the best e-ink reader for reading and annotating research papers? Is there a better alternative on the market? Do any of them support seamless Zotero integration like an iPad?

Locating and Editing Factual Associations in GPT arxiv.org/abs/2202.05262 1. to discover location of facts: at decisive token (eg Michael Jordan plays <BLANK>) iteratively remove circuits from model until <BLANK> != "basketball" 2. edit facts via Rank-1 modifications (ROME)

Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation pnp-diffusion.github.io arxiv.org/abs/2211.12572 run two copies of model A: DDIM inversion of source image B: generation with target prompt inject feature/attention maps from A into B during generation

Steering Language Models With Activation Engineering arxiv.org/abs/2308.10248 ActAdd manipulates the residual stream using something like classifier free guidance: it adds the difference vector between activations for prompts with and without the target characteristic to the residual stream

Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models arxiv.org/abs/2407.12824 assume monosemanticity of neurons, pick those that classify concepts well (eg toxicity) and set them to a fixed value (eg 0)

Controlling Language and Diffusion Models by Transporting Activations arxiv.org/abs/2410.23054 optimal transport to compute a univariate map for each activation based on mapping empirical activation distributions computed from a set of "bad" examples to the distribution from a set of "good" ones.

I know the ROME/Memit stuff from @davidbau.bsky.social's lab and this automated circuit discovery stuff. Any other model editing/applied mech interp things people think are particularly practical? Have you used them in practice?

I have arrived in SF, and so far it is ....... exciting