Alternatives and similar repositories for joint-inference

Users that are interested in joint-inference are comparing it to the libraries listed below

• wmn-231314 / diffusion-data-constraint
  Official PyTorch implementation and models for paper "Diffusion Beats Autoregressive in Data-Constrained Settings". We find diffusion mod…
  ☆120Updated last month
• euclid-multimodal / Euclid
  ☆17Updated last year
• ablghtianyi / ICL_Modular_Arithmetic
  ☆19Updated 10 months ago
• fangyuan-ksgk / selective-attention-transformer
  Unofficial Implementation of Selective Attention Transformer
  ☆20Updated last year
• HelmholtzAI-FZJ / flex_gen
  ☆19Updated last year
• s-sahoo / Eso-LMs
  Esoteric Language Models
  ☆111Updated this week
• g-luo / vlm_cross_modal_reps
  Official PyTorch Implementation for Vision-Language Models Create Cross-Modal Task Representations, ICML 2025
  ☆32Updated 9 months ago
• neilwen987 / CSR_Adaptive_Rep
  Official Code for Paper: Beyond Matryoshka: Revisiting Sparse Coding for Adaptive Representation
  ☆133Updated last month
• Weixin-Liang / Mixture-of-Mamba
  ☆50Updated last year
• ByungKwanLee / Phantom
  [Technical Report] Official PyTorch implementation code for realizing the technical part of Phantom of Latent representing equipped with …
  ☆63Updated last year
• callsys / GMPO
  [ICLR 2026] Geometric-Mean Policy Optimization
  ☆100Updated 2 weeks ago
• DreamLM / DreamOn
  Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas
  ☆101Updated last week
• sail-sg / feedback-conditional-policy
  Code for "Language Models Can Learn from Verbal Feedback Without Scalar Rewards"
  ☆59Updated last month
• goombalab / phi-mamba
  Official implementation of Phi-Mamba. A MOHAWK-distilled model (Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Mode…
  ☆119Updated last year
• dmis-lab / Monet
  [ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers
  ☆75Updated 7 months ago
• RobertCsordas / moeut
  ☆91Updated last year
• Jiaxin-Wen / Unsupervised-Elicitation
  ☆40Updated 7 months ago
• locuslab / llava-token-compression
  ☆46Updated last year
• hkust-nlp / model-task-align-rl
  [ICLR 26] The official code repository for the paper "Mirage or Method? How Model–Task Alignment Induces Divergent RL Conclusions".
  ☆15Updated this week
• complex-reasoning / RPG
  [ICLR 2026] RPG: KL-Regularized Policy Gradient (https://arxiv.org/abs/2505.17508)
  ☆65Updated 2 weeks ago
• microsoft / x-reasoner
  X-Reasoner: Towards Generalizable Reasoning Across Modalities and Domains
  ☆50Updated last week
• OpenMOSS / LongLLaDA
  [AAAI26] LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs
  ☆52Updated 2 months ago
• luka-group / vlm-knowledge-conflict
  Code for paper "Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models."
  ☆52Updated last year
• lucidrains / coconut-pytorch
  Implementation of 🥥 Coconut, Chain of Continuous Thought, in Pytorch
  ☆182Updated 7 months ago
• idanshen / Self-Distillation
  ☆236Updated last week
• inclusionAI / LLaDA2.X
  LLaDA2.0 is the diffusion language model series developed by InclusionAI team, Ant Group.
  ☆319Updated this week
• ShadeAlsha / ICon
  ICLR 2025 - official implementation for "I-Con: A Unifying Framework for Representation Learning"
  ☆127Updated last week
• kuleshov-group / remdm
  Remasking Discrete Diffusion Models with Inference-Time Scaling
  ☆66Updated this week
• shawnricecake / Heima
  Code for Heima
  ☆59Updated 9 months ago
• pixeli99 / Prophet
  Official implementation of "Diffusion Language Models Know the Answer Before Decoding"
  ☆45Updated 5 months ago