Skip to content

@RUCAIBox RUCAIBox

All

    Repositories list

    210 repositories

    • GDN-SpectralShift

      Public
      Megatron-LM patch for SpectralShift: extending Gated DeltaNet's effective context window via spectral reparameterization and learning-rate scaling.
      Other
      •0•1•0•0•Updated Sep 9, 2026Sep 9, 2026

    • Evo-Bench

      Public
      Python
      •
      Apache License 2.0
      •2•18•0•0•Updated Sep 9, 2026Sep 9, 2026

    • VEGA-SR

      Public
      Python
      •
      Apache License 2.0
      •1•0•0•0•Updated Sep 9, 2026Sep 9, 2026

    • MegaCode

      Public
      0•0•0•0•Updated Aug 29, 2026Aug 29, 2026

    • Parallel-Infilling-Reading

      Public
      Official implementation of “Beyond Prefix Answering: Parallel Infilling Reading for Long Contexts with Diffusion Language Models” (EMNLP 2026 Main).
      MIT License
      •0•1•0•0•Updated Aug 26, 2026Aug 26, 2026

    • Contrastive-Neuron-Regulation

      Public
      Official implementation of Contrastive Neuron Regulation (CNR) for sparse neuron-level control of chain-of-thought reasoning.
      Python
      •
      MIT License
      •1•0•0•0•Updated Aug 23, 2026Aug 23, 2026

    • DxEvolve

      Public
      Python
      •
      MIT License
      •1•1•0•0•Updated Aug 23, 2026Aug 23, 2026

    • BOUND

      Public
      Code for BOUND: Brief-Guided Corrective Preference Distillation at Search-Control Boundaries.
      Python
      •1•0•0•0•Updated Aug 8, 2026Aug 8, 2026

    • ClawRec

      Public
      ClawRec is a Claw-native recommender system.
      Python
      •
      MIT License
      •1•1•0•0•Updated Jul 26, 2026Jul 26, 2026

    • Sample-Polarity-of-RLVR

      Public
      About The official GitHub page for ''Rethinking Sample Polarity in Reinforcement Learning with Verifiable Rewards'' Resources
      Python
      •
      Apache License 2.0
      •1•1•0•0•Updated Jul 20, 2026Jul 20, 2026

    • ViFT

      Public
      Repo for "Do we Really Need Visual Instructions? Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models"
      Python
      •1•0•0•0•Updated Jul 20, 2026Jul 20, 2026

    • ArbGraph

      Public
      Python
      •1•0•0•0•Updated Jul 14, 2026Jul 14, 2026

    • RecBole3.0

      Public
      An LLM-Inspired Recommendation Library
      Python
      •
      MIT License
      •8•20•0•1•Updated Jul 5, 2026Jul 5, 2026

    • CCFRec

      Public
      [KDD'25] Code of "Bridging Textual-Collaborative Gap through Semantic Codes for Sequential Recommendation".
      Python
      •
      MIT License
      •3•8•0•0•Updated Jul 3, 2026Jul 3, 2026

    • SEAR

      Public
      Code for SEAR: Self-judging Agentic Reward Models
      1•0•0•0•Updated Jun 14, 2026Jun 14, 2026

    • FORT-Searcher

      Public
      FORTSearcher: Synthesizing Hard-to-Shortcut Search Tasks for Deep Search Agents
      0•28•4•0•Updated Jun 11, 2026Jun 11, 2026

    • Perceval

      Public
      Official code of paper “Improving Vision-language Models with Perception-centric Process Reward Models” (CVPR 2026)
      Python
      •
      Apache License 2.0
      •0•3•2•0•Updated Jun 10, 2026Jun 10, 2026

    • awesome-agent-harness

      Public
      The official GitHub page for the paper "Agent Systems with Harness Engineering"
      agentawesome-listagent-harness
      agentawesome-listagent-harnessharness-engineering
      MIT License
      •26•198•5•6•Updated May 25, 2026May 25, 2026

    • ForesightKV

      Public
      Python
      •1•6•0•0•Updated May 19, 2026May 19, 2026

    • PTS

      Public
      [ICLR'26] The official GitHub page for ''Unleashing Perception-Time Scaling to Multimodal Reasoning Models''
      Python
      •1•0•0•0•Updated May 19, 2026May 19, 2026

    • ClawGym-Agents

      Public
      Python
      •3•1•0•0•Updated May 19, 2026May 19, 2026

    • ClawGym-SynData

      Public
      4•1•0•0•Updated May 16, 2026May 16, 2026

    • ClawGym-Bench

      Public
      Python
      •2•1•0•0•Updated May 15, 2026May 15, 2026

    • llm-in-sandbox

      Public
      Computer Environments Elicit General Agentic Intelligence in LLMs
      Python
      •
      Apache License 2.0
      •21•1•0•0•Updated May 15, 2026May 15, 2026

    • BeyondSWE

      Public
      Other
      •2•0•0•0•Updated May 15, 2026May 15, 2026

    • POPEv2

      Public
      [AAAI'26 Oral] The official GitHub page for ''Analyzing and Mitigating Object Hallucination: A Training Bias Perspective''
      Python
      •
      MIT License
      •1•0•0•0•Updated May 7, 2026May 7, 2026

    • AiScientist

      Public
      Python
      •
      MIT License
      •12•0•0•0•Updated Apr 19, 2026Apr 19, 2026

    • LMM-Searcher

      Public
      The official code of "Towards Long-horizon Agentic Multimodal Search"
      Python
      •
      MIT License
      •2•30•0•0•Updated Apr 17, 2026Apr 17, 2026

    • AgentCF

      Public
      Python
      •
      Apache License 2.0
      •11•11•0•0•Updated Apr 14, 2026Apr 14, 2026

    • NExt

      Public
      The official repository of "Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration"
      Python
      •0•6•1•0•Updated Apr 14, 2026Apr 14, 2026
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.