• 1
• 0
• 0

AInsteinBench

• 1
• 0
• 0

Cola-DLM

The codebase of Cola DLM

• 1
• 0
• 0

par-protein

(ICML 2026 Oral) Protein Autoregressive Modeling via Multiscale Structure Generation, Official Implementation from ByteDance Seed

• 1
• 0
• 0

Modular-TTT

• 1
• 0
• 0

TaskMem

• 1
• 0
• 0

In-Place-TTT

• 1
• 0
• 0

DATAMASK

Joint Selection for Large-Scale Pre-Training Data via Policy Gradient-based Mask Learning

• 1
• 0
• 0

SpatialTree

CVPR 2026 (Highlight); Spatial Intelligence; MLLMs

• 1
• 0
• 0

ConfRover

[Neurips 2025] Official Implementation of ConfRover models

• 1
• 0
• 0

BFS-Prover-V2

• 1
• 0
• 0

Puppeteer

• 1
• 0
• 0

AHN

AHN: Artificial Hippocampus Networks for Efficient Long-Context Modeling

• 1
• 0
• 0

byteff2

• 1
• 0
• 0

bamboo_mixer

bamboo mixer

• 1
• 0
• 0

manip-as-in-sim-suite

Sim-to-real and CDM inference code for ManipAsInSim project.

• 1
• 0
• 0

WideSearch

WideSearch: Benchmarking Agentic Broad Info-Seeking

• 1
• 0
• 0

seed-oss

• 1
• 0
• 0

m3-agent

• 1
• 0
• 0

cudaLLM

• 1
• 0
• 0

EvaLearn

EvaLearn is a pioneering benchmark designed to evaluate large language models (LLMs) on their learning capability and efficiency in challenging tasks.