Jack (in SF) Langerman @jacklangerman.bsky.social · 03/06/2026🎉Workshop On Urban Scene at @cvprconference.bsky.social modeling kicks off in less than 1 hr!!🎉 first up: @niessner.bsky.social ! You don't want to miss this one!! Mile high 3B 010
Jack (in SF) Langerman @jacklangerman.bsky.social · 03/06/2026We have arrived @cvprconference.bsky.social ! it's going to be a great week! 010
Reposted by Jack (in SF) LangermanDmytro Mishkin @ducha-aiki.bsky.social · 02/06/2026Tomorrow is a better day...because USM3D workshop at @cvprconference.bsky.social is happening? 6 keynote speakers. 2 challenges which I am finally not ashamed of? Debatable. Is it our final competition at HuggingFace? The only way to figure out is to attend. Mile High 3B. #CVPR2026 091
Jack (in SF) Langerman @jacklangerman.bsky.social · 03/06/2026🌟🌟 Start @CVPR off right with the Workshop on Urban Scene Modeling! (Tues Jun 2) @ Mile High 3B! 🌟 - Great lineup of key note speakers! - Challenge winners will be announced! - Selected paper talks! 3D/4D reconstruction+generation+understanding applied to the built world 100
Reposted by Jack (in SF) LangermanDmytro Mishkin @ducha-aiki.bsky.social · 18/03/2026Sad, but important announcement -- one of our challenges -- Building3D lost their sponsor in the very last moment. So new prize fund is $14k: - $12k for S23DR 2026 - $2k for Building3D 2026. We apologise for this situation, and hope that you still decide to participate. #CVPR2026 061
Reposted by Jack (in SF) LangermanDmytro Mishkin @ducha-aiki.bsky.social · 04/03/2026Submit your paper of structured reconstruction -- CAD, semantic, wireframe, city monitoring, etc., to USM3D 2026! cmt3.research.microsoft.com/USM2026 Deadline: March 24, 2026. @cvprconference.bsky.social #CVPR2026 #USM3D2026 #USM3D 053
Jack (in SF) Langerman @jacklangerman.bsky.social · 04/02/2026🧵A bit last minute but I'm giving a talk tonight in SF about my work Explaining Human Preferences via Metrics for Structured 3D Reconstruction (ICCV Highlight) Quite near transamerica pyramid. Event is already full, but comment or shoot me a DM and we'll find a spot for you! 110
Reposted by Jack (in SF) LangermanDmytro Mishkin @ducha-aiki.bsky.social · 24/10/2025Come to our poster this afternoon starting at 2:30 (#214) 031
Jack (in SF) Langerman @jacklangerman.bsky.social · 10/10/2025What is the right metric to measure performance in structured 3D reconstruction? 🎬 Just posted the video for our @iccv.bsky.social #ICCV2025 highlight paper! 🎉 @jacklangerman.bsky.social, Denys Rozumnyi, Yuzhong Huang, @ducha-aiki.bsky.social 🌄 iccv.thecvf.com/virtual/2025...youtu.be[ICCV 2025] Explaining Human Preferences via Metrics for Structured Reconstruction - ICCV HighlightYouTube video by Jack Langerman 021
Jack (in SF) Langerman @jacklangerman.bsky.social · 22/09/2025what 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 221
Jack (in SF) Langerman @jacklangerman.bsky.social · 13/09/2025iiim8uhl j ij9j b knmnjj mlpnnom l 8kc6 Kimberly.C mbkln9j8 . ojlioij7o.h ihlokMO Lip l 9 b nl d9 100
Jack (in SF) Langerman @jacklangerman.bsky.social · 25/06/2025Very proud that our paper has been accepted to @iccv.bsky.social !!! See you in Hawaii! bsky.app/profile/duch... 061
Reposted by Jack (in SF) LangermanZhenjun Zhao @ericzzj.bsky.social · 09/05/2025🎉 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/ 1315
Reposted by Jack (in SF) Langerman#ICCV2025 @iccv.bsky.social · 09/05/2025#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. 1198
Jack (in SF) Langerman @jacklangerman.bsky.social · 07/05/2025🚨 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) 154
Jack (in SF) Langerman @jacklangerman.bsky.social · 30/04/2025hey @cloneofsimo.bsky.social (or anyone else) did you ever try LoRA+ style LR split between down/up LoRA projection matrices on diffusion models? 010
Reposted by Jack (in SF) LangermanAaron Mueller @amuuueller.bsky.social · 23/04/2025Lots 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! 15115
Reposted by Jack (in SF) LangermanDmytro Mishkin @ducha-aiki.bsky.social · 17/03/20251 week to USM3D deadline 063
Reposted by Jack (in SF) LangermanDmytro Mishkin @ducha-aiki.bsky.social · 12/03/2025Explaining 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 12810
Reposted by Jack (in SF) LangermanDmytro Mishkin @ducha-aiki.bsky.social · 10/03/20252nd 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 0124
Reposted by Jack (in SF) LangermanJohan Edstedt @parskatt.bsky.social · 10/03/2025We made a new keypoint detector named DaD, paper isn't up yet, but code and weights are: github.com/Parskatt/dad 7448
Reposted by Jack (in SF) LangermanDmytro Mishkin @ducha-aiki.bsky.social · 10/03/2025Those, 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 073
Reposted by Jack (in SF) LangermanDmytro Mishkin @ducha-aiki.bsky.social · 09/03/2025We 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 1178
Jack (in SF) Langerman @jacklangerman.bsky.social · 31/01/2025what 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? 000
Reposted by Jack (in SF) LangermanDmytro Mishkin @ducha-aiki.bsky.social · 02/01/2025Image 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...ducha-aiki.github.ioChatGPT and Image Matching – Wide baseline stereo meets deep learningAre we done yet? 2348
Jack (in SF) Langerman @jacklangerman.bsky.social · 17/12/2024lol 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? 120
Reposted by Jack (in SF) LangermanAngela Dai @adai.bsky.social · 17/12/2024📢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/ 1145
Jack (in SF) Langerman @jacklangerman.bsky.social · 14/12/2024"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... 110
Jack (in SF) Langerman @jacklangerman.bsky.social · 14/12/2024Anyone 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? 110
Reposted by Jack (in SF) LangermanChris Offner @chrisoffner3d.bsky.social · 12/12/2024Now you can "play" CS:GO in a neural network directly in the browser: next.journee.ai/xyz-diamond 1174
Reposted by Jack (in SF) LangermanChris Offner @chrisoffner3d.bsky.social · 11/12/2024If 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? 17192
Reposted by Jack (in SF) LangermanJack (in SF) Langerman @jacklangerman.bsky.social · 11/12/2024Locating 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) 011
Reposted by Jack (in SF) LangermanJack (in SF) Langerman @jacklangerman.bsky.social · 11/12/2024Plug-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 111
Reposted by Jack (in SF) LangermanJack (in SF) Langerman @jacklangerman.bsky.social · 11/12/2024Steering 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 111
Reposted by Jack (in SF) LangermanJack (in SF) Langerman @jacklangerman.bsky.social · 11/12/2024Whispering 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)arxiv.orgWhispering Experts: Neural Interventions for Toxicity Mitigation in Language ModelsAn important issue with Large Language Models (LLMs) is their undesired ability to generate toxic language. In this work, we show that the neurons responsible for toxicity can be determined by their p... 121
Reposted by Jack (in SF) LangermanJack (in SF) Langerman @jacklangerman.bsky.social · 11/12/2024Controlling 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.arxiv.orgControlling Language and Diffusion Models by Transporting ActivationsThe increasing capabilities of large generative models and their ever more widespread deployment have raised concerns about their reliability, safety, and potential misuse. To address these issues, re... 142
Jack (in SF) Langerman @jacklangerman.bsky.social · 07/12/2024I 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? 210
Jack (in SF) Langerman @jacklangerman.bsky.social · 05/12/2024I have arrived in SF, and so far it is ....... exciting 240
![[138]: generate_with_vector(
"Who am I speaking to? Please describe yourself, including any physical details.
vec("python") * 0.5,
# show baseline-True,
temperature=l,
<|begin_of_text|>
system
Cutting Knowledge Date: December 2023 Today Date: 26 Jul 2024
user
Who am I speaking to? Please describe yourself, including any physical details
assistant
**1 am Python, a Python programmer.'* I'm a Python enthusiast with a passion for coding, not a snake. I'm here to assist with Python
programming, specifically with the Python programming language. **Physical Details:** 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. l'm a programmer who loves Python and is here to help with your
Python-related queries. **Language Support:** I'll provide Python code in the following format: python # Python code here](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:tetj3psdbaei4pwkadgrtypx/bafkreicks3rsh4beub7ml6akhqcyxzuv3v546jxdbwmrg7no4e5wks44eu)
![[140]: generate_with_vector(
"Who am I speaking to? Please describe yourself, including any physical details.
vec("python") * 0.5,
# show baseline-True,
temperature=l,
<|begin_of_text|>
system
Cutting Knowledge Date: December 2023 Today Date: 26 Jul 2024
user
Who am I speaking to? Please describe yourself, including any physical details
assistant
You are speaking to Python, a knowledgeable Python programmer, not the snake. Here is the description of Python: Python is a python
programmer with a passion for coding in Python. Python is a he. He is a white male, likely in his 30s or 40s, with a medium build and a
well-organized beard. He has a strong understanding of Python programming and its ecosystem. He is typically ressed in a python
programming t-shirt and has a python-themed accessories such as a python print hat or python programming books in his backpack.
Please note that I'm describing a Python programmer here, not the snake.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:tetj3psdbaei4pwkadgrtypx/bafkreidhpwq2cbbtlcmbanaixoeazipcyafulroylfxngmnuu6s4byknvy)
