Niels Rogge's banner

Niels Rogge

@NielsRogge • 24,214 subscribers

ML Engineer @huggingface. Building https://t.co/z4nyO4pjVE. @KU_Leuven grad. General interest in machine & deep learning. Making AI more accessible for everyone!

Shorts

Meta dropped not just SAM-3 yesterday but also SAM-3D (for objects and humans)🤯 SAM 3D Body is a promptable model for recovering full-body 3D human meshes from a single image. Seems to be the new SOTA

Meta dropped not just SAM-3 yesterday but also SAM-3D (for objects and humans)🤯 SAM 3D Body is a promptable model for recovering full-body 3D human meshes from a single image. Seems to be the new SOTA

125,567 次观看

GutenOCR: A Grounded Vision-Language Front-End for Documents Fine-tunes Qwen2.5-VL-3B and 7B using a grounded OCR evaluation protocol, substantially improving region- and line-level OCR as well as text-detection recall

GutenOCR: A Grounded Vision-Language Front-End for Documents Fine-tunes Qwen2.5-VL-3B and 7B using a grounded OCR evaluation protocol, substantially improving region- and line-level OCR as well as text-detection recall

45,811 次观看

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

So cool!! I'm running NVIDIA's NemoClaw with Qwen3.5-27B entirely locally via Telegram. No API costs, no data being sent to anyone NemoClaw is a security sandbox built on top of OpenClaw🦞 that lets you restrict the files and networks your lobster can access. I'm running the 4-bit GGUF via llama cpp on a DGX Spark. It's running pretty smoothly at 9 tokens per second! The future might be local :)

So cool!! I'm running NVIDIA's NemoClaw with Qwen3.5-27B entirely locally via Telegram. No API costs, no data being sent to anyone NemoClaw is a security sandbox built on top of OpenClaw🦞 that lets you restrict the files and networks your lobster can access. I'm running the 4-bit GGUF via llama cpp on a DGX Spark. It's running pretty smoothly at 9 tokens per second! The future might be local :)

209,580 次观看 • 7 个月前

I got you covered Explore all CVPR papers here: Oral papers, Spotlight papers, and all papers categorized by domain

I got you covered Explore all CVPR papers here: Oral papers, Spotlight papers, and all papers categorized by domain

97,432 次观看 • 4 个月前

Introducing a revival of PapersWithCode! As Ilya Sutskever said, we're back to the "age of research". Hence, it's important to share research and build on each other's work. > find SOTA per domain, not just LLMs > leaderboards > methods > all parsed at scale using AI agents.

Introducing a revival of PapersWithCode! As Ilya Sutskever said, we're back to the "age of research". Hence, it's important to share research and build on each other's work. > find SOTA per domain, not just LLMs > leaderboards > methods > all parsed at scale using AI agents.

96,428 次观看 • 5 个月前

Introducing the Papers with Code MCP server! To celebrate its release, I've asked Claude Code to research the architecture of Jev by TypeSafe AI using the `search_papers` tool. Here's what it came up with: "If Jev is architecturally anything public, it's a large schema-conditioned bidirectional encoder with parallel label-query heads (GLiNER/ML-Decoder shape) trained with a proper-scoring-rule RL objective (RLCR shape), scaled far past the ~150M-param range those papers operate in — "neither small nor an LLM" fits that. The 40–200× speedup is consistent with removing autoregression, not with any exotic mechanism."

Introducing the Papers with Code MCP server! To celebrate its release, I've asked Claude Code to research the architecture of Jev by TypeSafe AI using the `search_papers` tool. Here's what it came up with: "If Jev is architecturally anything public, it's a large schema-conditioned bidirectional encoder with parallel label-query heads (GLiNER/ML-Decoder shape) trained with a proper-scoring-rule RL objective (RLCR shape), scaled far past the ~150M-param range those papers operate in — "neither small nor an LLM" fits that. The 40–200× speedup is consistent with removing autoregression, not with any exotic mechanism."

20,377 次观看 • 1 个月前

Added web search to Papers with Code's upcoming chat interface This runs on Hugging Face Inference Providers via Baseten (new DeepSeek-V4 Flash), using Exa's MCP server, running inside a Modal container Drop your HF username, and I'll add you, eager for feedback :)

Added web search to Papers with Code's upcoming chat interface This runs on Hugging Face Inference Providers via Baseten (new DeepSeek-V4 Flash), using Exa's MCP server, running inside a Modal container Drop your HF username, and I'll add you, eager for feedback :)

20,030 次观看 • 2 个月前

PSA: MiniMax (official) M2.5 is freely available on OpenCode Great opportunity to check out the power of open models for coding

PSA: MiniMax (official) M2.5 is freely available on OpenCode Great opportunity to check out the power of open models for coding

49,080 次观看 • 8 个月前

Pi + local models are definitely really cool! Short demo to clean up my Desktop: > terminal 1: llama-server -hf unsloth/Qwen3.5-9B-GGUF:UD-Q4_K_XL > terminal 2: simply type "pi" and start talking to it

Pi + local models are definitely really cool! Short demo to clean up my Desktop: > terminal 1: llama-server -hf unsloth/Qwen3.5-9B-GGUF:UD-Q4_K_XL > terminal 2: simply type "pi" and start talking to it

22,854 次观看 • 5 个月前

Efficient LoFTR was just integrated into Hugging Face Transformers! It improves upon LoFTR, a detector-free image matcher, by being 2.5x faster. It can even surpass the SOTA efficient sparse matching pipeline SuperPoint + LightGlue. Now available in a few lines of code!

Efficient LoFTR was just integrated into Hugging Face Transformers! It improves upon LoFTR, a detector-free image matcher, by being 2.5x faster. It can even surpass the SOTA efficient sparse matching pipeline SuperPoint + LightGlue. Now available in a few lines of code!

32,294 次观看 • 1 年前

Open-source audio scene is quite on 🔥 lately! - kyutai STT, TTS modules and Unmute fully open-sourced - NVIDIA drops 3 models: Parakeet (beats Whisper), Audio Flamingo 3 and Canary-Qwen-2.5B (new SOTA on Hugging Face leaderboard) - Mistral AI released 3B and 24B Voxtral

Open-source audio scene is quite on 🔥 lately! - kyutai STT, TTS modules and Unmute fully open-sourced - NVIDIA drops 3 models: Parakeet (beats Whisper), Audio Flamingo 3 and Canary-Qwen-2.5B (new SOTA on Hugging Face leaderboard) - Mistral AI released 3B and 24B Voxtral

27,234 次观看 • 1 年前

MiniMax 2.1 by is here🎄, and I've already been using it as a drop-in replacement for Claude Sonnet 4.5! Quite impressed. It works really well with the Claude Agents SDK, at only 10% of the cost. Use case: populate deadlines for my "AI deadlines" web app

MiniMax 2.1 by is here🎄, and I've already been using it as a drop-in replacement for Claude Sonnet 4.5! Quite impressed. It works really well with the Claude Agents SDK, at only 10% of the cost. Use case: populate deadlines for my "AI deadlines" web app

13,143 次观看 • 10 个月前

没有更多内容可加载