J C

dark-pen

·

AI & ML interests

None yet

Recent Activity

upvoted a collection 1 day ago

liked a model 1 day ago

XingChen-AGI/TeleOCR

liked a model 1 day ago

frontier-ai/llm-agent-factory

View all activity

Organizations

upvoted 2 collections 1 day ago

TeleOCR

TeleOCR parses scans, PDFs and photos, supporting complex layouts, tables, formulas and charts. OmniDocBench V1.6 (96.87) and Wild-OmniDocBenc(88.53). • 1 item • Updated 2 days ago • 1

NuExtract3

12 items • Updated May 26 • 17

upvoted a paper 1 day ago

ExtractBench: A Benchmark for Schema-Guided Enterprise Document Extraction

Paper • 2607.29677 • Published Jul 31 • 26

upvoted a collection 1 day ago

Dr.Kernel

8 items • Updated Feb 6 • 6

upvoted a paper 1 day ago

WhatWorkedBench: Benchmarking Experimental Understanding in AI Agents

Paper • 2609.27490 • Published 8 days ago • 14

upvoted 3 papers 2 days ago

ZipTok3D: High-Fidelity 3D Tokenization with Compact Token Prefixes

Paper • 2609.01740 • Published 30 days ago • 29

LightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation

Paper • 2608.30935 • Published about 1 month ago • 33

Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion

Paper • 2608.19567 • Published Aug 20 • 34

upvoted a paper 5 days ago

Marco DeepResearch: Unlocking Efficient Deep Research Agents via Verification-Centric Design

Paper • 2603.28376 • Published Mar 30 • 22

upvoted 2 collections 5 days ago

Marco-Agent

4 items • Updated May 21 • 5

Ovis-Embedding

4 items • Updated 7 days ago • 20

upvoted a paper 5 days ago

Ovis-Embedding: Pushing the Frontiers of Universal Omni-Modal Embeddings

Paper • 2609.25165 • Published 10 days ago • 75

upvoted a collection 5 days ago

Code

83 items • Updated 1 day ago • 7

upvoted a paper 5 days ago

MaxKernel: Agentic Kernel Generation for TPUs

Paper • 2609.04523 • Published 28 days ago • 20

upvoted a paper 6 days ago

EdgeTAM: On-Device Track Anything Model

Paper • 2501.07256 • Published Jan 13, 2025 • 4

upvoted an article 6 days ago

Article

KV Caching Explained: Optimizing Transformer Inference Efficiency

not-lain

•

Jan 30, 2025

• 422

upvoted a paper 6 days ago

Compile by Training: Turning Natural-Language Specifications into Local Neural Functions

Paper • 2609.04199 • Published 28 days ago • 332

upvoted 3 collections 6 days ago

Coding Agent

2 items • Updated 11 days ago • 1

[models] SOTA Small-LM

5 items • Updated 8 days ago • 1

Primed Hybrid Models Collection

Collection of primed Hybrid language models for Reasoning and Instruction following. • 9 items • Updated Apr 9 • 9