AllyshipContent Radar

News 2840

Chủ đề cộng đồng đang thảo luận

Crawl live-1795094100000 · 20:15 19 thg 11, 2026 · Xuất bản 20:31 19 thg 11, 2026

94 / 2840 chủ đề đạt ngưỡng 55 trong khoảng này.

1

Adobe Photoshop is dead

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

melvindvivas 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

Adobe Photoshop is dead Artcraft built an open-source reimplementation of Adobe Photoshop, rebuilt in pure Rust https://github.com/storytold/photocraft

2

欣慰啊!网易终于不再是只会做游戏了!!

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

ai_jasonyu 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

欣慰啊!网易终于不再是只会做游戏了!! 最近做的这些产品还是很出乎意料的,UU远程的体验和口碑大家应该都知道,最近又出了一个永久免费的AI语音输入法:“网易叭哥说”,我试过搭配VibeCoding玩起来过于丝滑,也治好了我多年的腱鞘炎~ 我测试对比了Typeless,发现网易叭哥说的速度要快很多,产品做的也极为克制,没有太多花里胡哨的功能,就是语音和语音翻译。 他会整理口喷的内容,但是不会过度破坏内容,整体的体验非常丝滑。 目前各个端都是支持的,永久免费,真是语音输入法的新赛博菩萨! http://bug.youdao.com Media

3

Superintelligence Needs the Physical World with CEO and Co-Founder of Arda Bob McGrew

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

No Priors: AI, Machine Learning, Tech, & Startups 1 bài viết · No Priors
Nguyên văn nguồn
Chi tiết nguồn

Is the AI singularity actually coming? Bob McGrew, former Chief Research Officer at OpenAI, argues that superintelligence won’t arrive without changes in the physical world, and that the “hard takeoff” argument is wrong. Sarah Guo and Elad Gil sit down with Bob, an early key executive at Palantir who later led research at OpenAI. He is now CEO and co-founder of Arda, which is leveraging AI to make American manufacturing competitive. Bob explains why automating AI researchers is a one-time boost rather than a runaway loop, and why GPUs, compute, wet labs, and factories are the real bottlenecks. They cover Arda’s work with Anduril on everything from actuators to missiles to the Fury combat aircraft, why Arda is building “Cursor for manufacturing engineers”, and how the forward deployed engineering model really works. Plus, the big-picture future view: machines that make machines, self-replicating factories, and Bob’s answer to the Fermi paradox. Sign up for new podcasts every week. Email feedback to show@no-priors.com Follow us on Twitter: @NoPriorsPod | @Saranormous | @EladGil | @bobmcgrewai | @Arda_Industries Chapters: 00:00 – Trailer 00:05 – Bob McGrew Introduction 01:05 – Why work on the physical world during the AI revolution? 02:27 – Why the hard takeoff argument is wrong 05:48 – Labs or startups – who will win in robotics and biology? 13:00 – Why America designs products but doesn’t build them 16:33 – Who needs flexible automation: defense, consumer electronics, data centers 18:19 – Humanoid robots vs. robotic work cells 21:07 – Open-world vs. closed-world robotics 25:20 – Building with Anduril: from days to 90 minutes 28:59 – Palantir’s problem-first approach vs. OpenAI’s technology-first approach 33:15 – From dropping out of Stanford to joining OpenAI 37:13 – Why general robotics models suddenly work 40:28 – Implications for the robotics ecosystem 42:46 – On-device models, speed, and safety 44:18 – How forward deployed engineering really works 50:57 – Superintelligence out of the data center 53:41 – Self-replicating factories and Von Neumann probes 56:46 – Bob’s answer to the Fermi paradox 59:33 – Conclusion

4

b12535

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

github-actions[bot] 1 bài viết · ggml-org/llama.cpp releases
Nguyên văn nguồn
Chi tiết nguồn

<details open=""> <p>vulkan: Implement stream-k MUL_MAT (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="5369588759" data-permission-text="Title is private" data-url="https://github.com/ggml-org/llama.cpp/issues/28528" data-hovercard-type="pull_request" data-hovercard-url="/ggml-org/llama.cpp/pull/28528/hovercard" href="https://github.com/ggml-org/llama.cpp/pull/28528">#28528</a>)</p> <ul> <li>vulkan: Implement stream-k MUL_MAT</li> </ul> <p>Stream-k tries to split chunks of 256 K elements evenly across all SMs.<br> Workgroups that finish a tile write to dst, others write to scratch, and<br> there's a resolve shader similar to split-k.</p> <p>The shader code is implemented for scalar+cm1+cm2, but only currently enabled<br> for cm2. The heuristic for enabling on coopmat2 is pretty simple due to the<br> large tile size (one workgroup per SM), but would be more complex for the tile<br> sizes being used for cm1, and it doesn't make sense for me to tune that on<br> NVIDIA devices.</p> <p>Assisted-by: Codex</p> <ul> <li>address review feedback</li> </ul> </details> <p><strong>Website:</strong></p> <ul> <li><a href="https://llama.app" rel="nofollow">https://llama.app</a></li> </ul> <p><strong>Attestations:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/attestations/69624611">https://github.com/ggml-org/llama.cpp/attestations/69624611</a></li> </ul> <p><strong>macOS/iOS:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-macos-arm64.tar.gz">macOS Apple Silicon (arm64)</a></li> <li>macOS Apple Silicon (arm64, KleidiAI enabled) <a href="https://github.com/ggml-org/llama.cpp/pull/23780" data-hovercard-type="pull_request" data-hovercard-url="/ggml-org/llama.cpp/pull/23780/hovercard">DISABLED</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-macos-x64.tar.gz">macOS Intel (x64)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-xcframework.zip">iOS XCFramework</a></li> </ul> <p><strong>Linux:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-ubuntu-x64.tar.gz">Ubuntu x64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-ubuntu-arm64.tar.gz">Ubuntu arm64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-ubuntu-s390x.tar.gz">Ubuntu 24.04 s390x (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-ubuntu-26.04-s390x.tar.gz">Ubuntu 26.04 s390x (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-ubuntu-zdnn-s390x.tar.gz">Ubuntu 26.04 s390x (zDNN)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-ubuntu-vulkan-x64.tar.gz">Ubuntu x64 (Vulkan)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-ubuntu-vulkan-arm64.tar.gz">Ubuntu arm64 (Vulkan)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-ubuntu-cuda-12.8-x64.tar.gz">Ubuntu x64 (CUDA 12)</a> - <a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/cudart-llama-b12535-bin-ubuntu-cuda-12.8-x64.tar.gz">CUDA 12.8 libraries</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-ubuntu-cuda-13.5-x64.tar.gz">Ubuntu x64 (CUDA 13)</a> - <a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/cudart-llama-b12535-bin-ubuntu-cuda-13.5-x64.tar.gz">CUDA 13.5 libraries</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-ubuntu-cuda-13.5-arm64.tar.gz">Ubuntu arm64 (CUDA 13)</a> - <a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/cudart-llama-b12535-bin-ubuntu-cuda-13.5-arm64.tar.gz">CUDA 13.5 libraries</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-ubuntu-rocm-10.0-x64.tar.gz">Ubuntu x64 (ROCm 10.0)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-ubuntu-openvino-2026.4.1-x64.tar.gz">Ubuntu x64 (OpenVINO)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-ubuntu-sycl-fp32-x64.tar.gz">Ubuntu x64 (SYCL FP32)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-ubuntu-sycl-fp16-x64.tar.gz">Ubuntu x64 (SYCL FP16)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-linux-arm64-snapdragon.tar.gz">Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)</a> - <a href="https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/snapdragon/linux.md">setup guide</a></li> </ul> <p><strong>Android:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-android-arm64.tar.gz">Android arm64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-android-arm64-snapdragon.tar.gz">Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)</a> - <a href="https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/snapdragon/README.md">setup guide</a></li> </ul> <p><strong>Windows:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-win-cpu-x64.zip">Windows x64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-win-cpu-arm64.zip">Windows arm64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12535/llama-b12535-bin-win-opencl-adreno-arm64.zip">Windows arm64 (OpenCL Adreno)</a></li> <li><

  • b12535 ggml-org/llama.cpp releases · 19 thg 11, 2026
5

还是牛批啊,兄弟们,看这个,你们不知道咋玩,我给你们演示了,去看那个评论区

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

ai_jasonyu 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

还是牛批啊,兄弟们,看这个,你们不知道咋玩,我给你们演示了,去看那个评论区 Media

8

b12534

56

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

github-actions[bot] 1 bài viết · ggml-org/llama.cpp releases
Nguyên văn nguồn
Chi tiết nguồn

<details open=""> <p>vulkan: use floating-point zero for storage-only FP16 in DIAG/TRI (<a class="issue-link js-issue-link" data-error-text="Failed to load title" data-id="6415436749" data-permission-text="Title is private" data-url="https://github.com/ggml-org/llama.cpp/issues/32379" data-hovercard-type="pull_request" data-hovercard-url="/ggml-org/llama.cpp/pull/32379/hovercard" href="https://github.com/ggml-org/llama.cpp/pull/32379">#32379</a>)</p> <ul> <li>vulkan: Change integer zero to floating-point zero for storage-only FP16 in DIAG/TRI.</li> </ul> <p>Assisted-by: OpenAI Codex</p> <ul> <li>delete narrow test</li> </ul> </details> <p><strong>Website:</strong></p> <ul> <li><a href="https://llama.app" rel="nofollow">https://llama.app</a></li> </ul> <p><strong>Attestations:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/attestations/69613826">https://github.com/ggml-org/llama.cpp/attestations/69613826</a></li> </ul> <p><strong>macOS/iOS:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-macos-arm64.tar.gz">macOS Apple Silicon (arm64)</a></li> <li>macOS Apple Silicon (arm64, KleidiAI enabled) <a href="https://github.com/ggml-org/llama.cpp/pull/23780" data-hovercard-type="pull_request" data-hovercard-url="/ggml-org/llama.cpp/pull/23780/hovercard">DISABLED</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-macos-x64.tar.gz">macOS Intel (x64)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-xcframework.zip">iOS XCFramework</a></li> </ul> <p><strong>Linux:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-ubuntu-x64.tar.gz">Ubuntu x64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-ubuntu-arm64.tar.gz">Ubuntu arm64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-ubuntu-s390x.tar.gz">Ubuntu 24.04 s390x (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-ubuntu-26.04-s390x.tar.gz">Ubuntu 26.04 s390x (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-ubuntu-zdnn-s390x.tar.gz">Ubuntu 26.04 s390x (zDNN)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-ubuntu-vulkan-x64.tar.gz">Ubuntu x64 (Vulkan)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-ubuntu-vulkan-arm64.tar.gz">Ubuntu arm64 (Vulkan)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-ubuntu-cuda-12.8-x64.tar.gz">Ubuntu x64 (CUDA 12)</a> - <a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/cudart-llama-b12534-bin-ubuntu-cuda-12.8-x64.tar.gz">CUDA 12.8 libraries</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-ubuntu-cuda-13.5-x64.tar.gz">Ubuntu x64 (CUDA 13)</a> - <a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/cudart-llama-b12534-bin-ubuntu-cuda-13.5-x64.tar.gz">CUDA 13.5 libraries</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-ubuntu-cuda-13.5-arm64.tar.gz">Ubuntu arm64 (CUDA 13)</a> - <a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/cudart-llama-b12534-bin-ubuntu-cuda-13.5-arm64.tar.gz">CUDA 13.5 libraries</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-ubuntu-rocm-10.0-x64.tar.gz">Ubuntu x64 (ROCm 10.0)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-ubuntu-openvino-2026.4.1-x64.tar.gz">Ubuntu x64 (OpenVINO)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-ubuntu-sycl-fp32-x64.tar.gz">Ubuntu x64 (SYCL FP32)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-ubuntu-sycl-fp16-x64.tar.gz">Ubuntu x64 (SYCL FP16)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-linux-arm64-snapdragon.tar.gz">Linux arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)</a> - <a href="https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/snapdragon/linux.md">setup guide</a></li> </ul> <p><strong>Android:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-android-arm64.tar.gz">Android arm64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-android-arm64-snapdragon.tar.gz">Android arm64 (Snapdragon: CPU, Adreno GPU, Hexagon NPU)</a> - <a href="https://github.com/ggml-org/llama.cpp/blob/master/docs/backend/snapdragon/README.md">setup guide</a></li> </ul> <p><strong>Windows:</strong></p> <ul> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-win-cpu-x64.zip">Windows x64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-win-cpu-arm64.zip">Windows arm64 (CPU)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-win-opencl-adreno-arm64.zip">Windows arm64 (OpenCL Adreno)</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-win-cuda-12.4-x64.zip">Windows x64 (CUDA 12)</a> - <a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/cudart-llama-bin-win-cuda-12.4-x64.zip">CUDA 12.4 DLLs</a></li> <li><a href="https://github.com/ggml-org/llama.cpp/releases/download/b12534/llama-b12534-bin-win-cuda-13.5-x64.zip">Windows x64 (CUDA 13)</a> - <a href="https://github.com/ggml-org/llama.cpp/re

  • b12534 ggml-org/llama.cpp releases · 19 thg 11, 2026
9

GitHub Deletes Camoufox Repo

62

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 9 tương tác đã đo · Nguồn crawl

elsombrero 1 bài viết · HN: GPT
Nguyên văn nguồn
Chi tiết nguồn
10

Ask HN: How do you manage the curse of rabbit hole?

61

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · 7 tương tác đã đo · Nguồn crawl

BOOSTERHIDROGEN 1 bài viết · HN: LLM
Nguyên văn nguồn
Chi tiết nguồn

I know that I can ask llm however, asking to real people still the best way to get an insight, Prolog: sometimes I do wonder , the best technical decision, best executive CEO as steve blank called, I notice they usually don't have that much information, while I struggle with so much information (I do love learning as that a curse) causing analysis paralyzed, what kind of method or strategy do you have be it technical or intuition based ? Thank you for discussion.

13

Made by Opus 5.5 in Claude Code

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

melvindvivas 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

Made by Opus 5.5 in Claude Code Media

14

Jeveration: System One Models Now Generate

85

5 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · 6 tương tác đã đo · Nguồn crawl

Yuhe Liu, Qi Li và 3 nguồn khác 1 bài viết · Hugging Face Papers, X
Nguyên văn nguồn
Chi tiết nguồn

System One models such as Jev return decisions through fast, parallel prediction. In this paper, we introduce Jeveration, showing that the same decision paradigm can also generate high-quality images in a single forward pass. Jeveration builds on a frozen vision-language model, repurposing its visual-semantic knowledge for holistic image generation. The key challenge is to maintain global consistency. A single prompt admits many valid images, yet parallel predictions must converge on a coherent whole. We therefore condition all positions on a shared random state to coordinate parallel predictions, so that each draw yields a different but coherent image. Since the model tends to ignore this state under direct image supervision, we first learn a distribution over discrete image codes to guide single-pass generation. Beyond text-to-image generation, we further unify image-to-image generation and dense prediction within the same architecture, so that one checkpoint supports all three tasks, each in one forward pass. Experiments show that Jeveration generates a 512x512 image in 78 ms, up to 122x faster than existing unified models, while maintaining competitive image quality and dense prediction performance.

16

SEO for my guitar app, last 28 days:

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

teedevh 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

SEO for my guitar app, last 28 days: 15.7K clicks, +45% 186K impressions, +82% Next I'm trying this on my newer sites, 26 deterministic SEO checks, no LLM: https://github.com/tigerless-labs/seo-ops

17

My Claude Code theme entertains me while waiting

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

melvindvivas 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

My Claude Code theme entertains me while waiting How to install: /plugin marketplace add donvito/skillsbento /plugin install backdrops@skillsbento Repo: https://github.com/donvito/skillsbento/tree/main/plugins/backdrops Media

18

We’re teaming up with @ClickHouseDB for a special one-day hackathon in Paris!

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

Mistral AI 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

We’re teaming up with @ClickHouseDB for a special one-day hackathon in Paris! Come build with Le Chonk, Timestral, ClickHouse, and Langfuse 📅 Saturday, Dec 5 📍 Paris RSVP required: https://luma.com/clickh-mistral-hack-paris

19

How much credit Poke gave you?

55

1 tiếng nói · chưa gắn nhãn trưởng lab · 1 nền tảng · chưa có số tương tác · Nguồn crawl

luongnv89 0 bài viết · X
Nguyên văn nguồn
Chi tiết nguồn

How much credit Poke gave you? > I only can get $50 https://freetokens.custats.info/offers/devin-bots-poke-giveaway.html

20

UltraTex: Aligning Physical Knowledge for High-Fidelity PBR Texture Generation

82

6 tiếng nói · chưa gắn nhãn trưởng lab · 2 nền tảng · 2 tương tác đã đo · Nguồn crawl

Jingzhi Bao, Xiaohe Ma và 4 nguồn khác 1 bài viết · Hugging Face Papers, X
Nguyên văn nguồn
Chi tiết nguồn

Generating physically based rendering (PBR) texture maps for a 3D mesh from a single reference image is highly ambiguous, as the observed appearance entangles material identity, surface reflectance, and illumination. While current generative methods produce realistic albedo maps, they still struggle to infer accurate metallic and roughness attributes for relighting. We present UltraTex, a cascaded multi-view framework that moves beyond appearance matching by integrating physical knowledge into multi-view diffusion-based PBR generation. UltraTex first jointly predicts albedo and world-space shading normals to generate more detailed albedo maps, and then predicts metallic-roughness (MR) maps conditioned on the generated albedo, reference image, and material semantic priors. To inject material semantics, a lightweight adapter transforms hidden-layer features of a vision-language model (VLM) into intrinsic material representation tokens, providing part-level knowledge anchors for MR estimation. To model material-light interaction, photometric representation alignment guides intermediate diffusion features toward ground-truth material renderings under controlled lighting. This makes metallic and roughness variations observable through highlight intensity, specular sharpness, and local reflectance contrast, providing stronger guidance for fine-grained material prediction without explicit lighting supervision. Extensive experiments show that UltraTex generates high-quality textures and outperforms existing open-source and commercial methods in visual fidelity, material accuracy, and physical plausibility.

1–20 / 94
Trang 1 / 5