iGEN
Visit IGEN World Explore IGEN Expo
EXPLORE UPGRADE PLANS
BREAKING
Home ›› Topics ›› mixture-of-experts

Topic

mixture-of-experts

5 stories
Process-Verified Reinforcement Learning for Theorem Proving via Lean: A New Path to AI Reliability Technology
Artificial Intelligence #reinforcement learning#theorem proving

Process-Verified Reinforcement Learning for Theorem Proving via Lean: A New Path to AI Reliability

A new arXiv preprint presents process-verified reinforcement learning for theorem proving, using the Lean proof assistant as a symbolic process oracle. By parsing proof attempts into tactic sequences and leveraging Lean's type-theoretic feedback, the method delivers dense, verifier-grounded credit signals. Experiments with STP-Lean and DeepSeek-Prover-V1.5 show tactic-level supervision outperforms outcome-only baselines on MiniF2F and ProofNet benchmarks.

Jul 8, 2026 2 sources
New Research Proposes Adversarial Reweighting to Calibrate Mixture-of-Experts Models Under Distribution Shift Technology
Artificial Intelligence #mixture-of-experts#distribution shift

New Research Proposes Adversarial Reweighting to Calibrate Mixture-of-Experts Models Under Distribution Shift

A new study examines how mixture-of-experts (MoE) models behave under distribution shift and proposes an adversarial reweighting approach to maintain calibration. The method improves the accuracy-calibration tradeoff across model classes, prediction tasks, and distribution shifts.

Jun 20, 2026 1 source
Mosaic: Data-Free Knowledge Distillation Framework Uses Mixture-of-Experts to Tackle Heterogeneous Federated Learning Technology
Artificial Intelligence #mosaic#data-free

Mosaic: Data-Free Knowledge Distillation Framework Uses Mixture-of-Experts to Tackle Heterogeneous Federated Learning

Researchers propose Mosaic, a novel data-free knowledge distillation framework that leverages Mixture-of-Experts (MoE) to overcome model and data heterogeneity in federated learning. Mosaic trains local generative models to synthesize data, forms an MoE from client models, and distills it into a global model. Experiments show consistent outperformance over state-of-the-art approaches on image and multimodal benchmarks.

Jun 16, 2026 1 source
SPRI: SVD-Partitioned Residual Initialization Boosts Data-Constrained MoE Upcycling for Multilingual Translation Technology
Artificial Intelligence #artificial intelligence#machine learning

SPRI: SVD-Partitioned Residual Initialization Boosts Data-Constrained MoE Upcycling for Multilingual Translation

Researchers propose SPRI, a method that initializes Mixture-of-Experts (MoE) models from pretrained dense models using SVD-partitioned residuals. Evaluated on multilingual speech-to-text translation, SPRI achieves gains of 2.58 BLEU and 3.32 COMET over fine-tuned dense models, and outperforms prior MoE upcycling baselines by 3.39 BLEU and 4.34 COMET points.

Jun 16, 2026 1 source
Expert Tying Reduces Memory Footprint of Mixture-of-Experts LLMs by Nearly Half Technology
Artificial Intelligence #tied expert layers#mixture-of-experts

Expert Tying Reduces Memory Footprint of Mixture-of-Experts LLMs by Nearly Half

A new arXiv paper from Jaggi proposes Expert Tying, an architectural modification for Mixture-of-Experts LLMs that shares expert parameters across consecutive transformer layers. Pretraining experiments show memory footprint reduction by almost 2x with virtually no degradation in perplexity or downstream quality, evaluated on OLMoE, Qwen3, and DeepSeek-style architectures.

Jun 16, 2026 1 source