Skip to content
@imagination-research

imagination-research

Welcome to Imagination-Research

We are a small and informal research team driven by common interests, exploring a wide range of topics. Learn more about us at this group website.

It's hard to say what specific topics we are focusing on, as we are concerned with a range of intrinsic problems that we think are preventing current techniques from reaching AGI. And we're continuously trying out and evolving our perspectives on what problems are intrinsic, as well as what pathways might be promising and worth trying out.

If you find our style of research and concrete ideas interesting, email us to discuss interesting thoughts or collaborate. We're curious about many problems and love ideas from many fields!

We also open a new Youtube Channel at https://www.youtube.com/@Imagination-Research-o3i, welcome to subscribe!

Pinned Loading

  1. aimo2 aimo2 Public

    AIMO2 2nd place solution

    Python 68 16

  2. distilled-decoding distilled-decoding Public

    [ICLR 2025] Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching

    52 2

  3. LCSC LCSC Public

    [ICLR 2025] Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better

    Python 16

  4. lbt lbt Public

    [NeurIPS 2024] Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study

    Python 56 7

  5. EEP EEP Public

    Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs

    Python 21

  6. sot sot Public

    [ICLR 2024] Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation

    Python 182 17

Repositories

Showing 8 of 8 repositories
  • EEP Public

    Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs

    imagination-research/EEP’s past year of commit activity
    Python 21 Apache-2.0 0 4 0 Updated Nov 11, 2025
  • Distilled-Decoding-2 Public

    [NeurIPS 2025] Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation

    imagination-research/Distilled-Decoding-2’s past year of commit activity
    1 0 1 0 Updated Oct 23, 2025
  • aimo2 Public

    AIMO2 2nd place solution

    imagination-research/aimo2’s past year of commit activity
    Python 68 Apache-2.0 16 0 0 Updated May 28, 2025
  • distilled-decoding Public

    [ICLR 2025] Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching

    imagination-research/distilled-decoding’s past year of commit activity
    52 2 1 0 Updated Apr 21, 2025
  • LCSC Public

    [ICLR 2025] Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models Better

    imagination-research/LCSC’s past year of commit activity
    Python 16 MIT 0 2 0 Updated Feb 15, 2025
  • .github Public
    imagination-research/.github’s past year of commit activity
    0 0 0 0 Updated Dec 7, 2024
  • lbt Public

    [NeurIPS 2024] Can LLMs Learn by Teaching for Better Reasoning? A Preliminary Study

    imagination-research/lbt’s past year of commit activity
    Python 56 MIT 7 0 0 Updated Nov 24, 2024
  • sot Public

    [ICLR 2024] Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation

    imagination-research/sot’s past year of commit activity
    Python 182 MIT 17 2 0 Updated Mar 1, 2024

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…