👨🔬
Highlights
- Pro
Starred repositories
[EMNLP'26] Token-Disentangled Latent Test-Time Scaling for Vision-Language Reasoning
A CLI tool to switch and manage Codex accounts
Qwen-Applications / SiameseNorm
Forked from allenai/OLMoCode of the research paper "SiameseNorm: Breaking the Barrier to Reconciling Pre/Post-Norm"
Official codebase of the paper -- Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills
Scalable toolkit for efficient model reinforcement
The official repository of "Position: Agentic Evolution is the Path to Evolving LLMs".
A curated list of papers and resources based on the survey "Agentic Reasoning for Large Language Models"
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…
Native Multimodal Models are World Learners
Open-source implementation of AlphaEvolve
This is a project about visual spatial reasoning.
📄 A curated list of visual reasoning papers.
🔥An open-source survey of the latest video reasoning tasks, paradigms, and benchmarks.
Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual information for complex reasoning, planning, and generation.
OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards
Repository for getting started with the OfficeQA Benchmark.
Continuously updated paper list on advancements in Data Agents. Companion repo to our paper "A Survey of Data Agents: Emerging Paradigm or Overstated Hype?"
🪄 Data Formulator is an interactive AI-powered data analysis system makes it easy to connect, explore and visualize data.
DataSciBench: An LLM Agent Benchmark for Data Science (Findings of ACL 2026)
Open diffusion language model for code generation — releasing pretraining, evaluation, inference, and checkpoints.
OCR model that handles complex tables, forms, handwriting with full layout.
Official repo for the #tidytuesday project
370F