Code for "Routing Manifold Alignment Improves Generalization of Mixture-of-Experts LLMs"
☆19Nov 6, 2025Updated 11 months ago
Alternatives and similar repositories for RoMA
Users that are interested in RoMA are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICML 2025] Code for "R2-T2: Re-Routing in Test-Time for Multimodal Mixture-of-Experts"☆19Mar 10, 2025Updated last year
- [ICML2022] "Identity-Disentangled Adversarial Augmentation for Self-Supervised Learning"☆10Jul 24, 2022Updated 4 years ago
- AutoHallusion Codebase (EMNLP 2024)☆22Dec 6, 2024Updated last year
- ☆15Jul 24, 2026Updated 3 months ago
- NLPBench: Evaluating NLP-Related Problem-solving Ability in Large Language Models☆10Oct 27, 2023Updated 3 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Code for paper: Optimizing Length Compression in Large Reasoning Models☆29Oct 20, 2025Updated last year
- ☆29May 24, 2024Updated 2 years ago
- [CVPR Findings 2026] HoliSafe: Holistic Safety Benchmarking and Modeling for Vision-Language Model☆17Mar 8, 2026Updated 7 months ago
- How Instruction and Reasoning Data shape Post-Training: Data Quality through the Lens of Layer-wise Gradients☆23Jun 17, 2025Updated last year
- [ICLR 2025 Oral] "Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free"☆93Oct 15, 2024Updated 2 years ago
- [ICML 2026] TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models☆29Mar 24, 2026Updated 7 months ago
- ☆43Jul 16, 2024Updated 2 years ago
- ☆13Jan 14, 2025Updated last year
- [ICLR 2026] Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing☆35May 30, 2026Updated 4 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Implementation for ACL 2024 paper "Meta-Task Prompting Elicits Embeddings from Large Language Models"☆12Jul 25, 2024Updated 2 years ago
- ☆39Jan 16, 2025Updated last year
- The official implementation of flow actor-critic (FAC)☆13Oct 6, 2026Updated 3 weeks ago
- ☆18Dec 11, 2025Updated 10 months ago
- [EMNLP 2026 Findings] Cost-Sensitive Toolpath Agent for Multi-turn Image Editing☆32Aug 24, 2026Updated 2 months ago
- [ICCV 2025] Diffusion Curriculum (DisCL)☆19Sep 26, 2025Updated last year
- [ICLR 2026] "Multi-Agent Debate with Memory Masking"☆14Apr 21, 2026Updated 6 months ago
- [NeurIPS 2021] "Class-Disentanglement and Applications in Adversarial Detection and Defense"☆47Jan 18, 2022Updated 4 years ago
- An implementation for MLLM oversensitivity evaluation☆18Nov 16, 2024Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ACL 2026 Main] Analytical FFN-to-MoE Restructuring via Activation Pattern Analysis☆53Jun 30, 2026Updated 4 months ago
- List of papers on Hallucination in LMM☆10Nov 29, 2023Updated 2 years ago
- NeurIPS 2025☆16Feb 4, 2026Updated 8 months ago
- ☆17Jun 9, 2024Updated 2 years ago
- Our research proposes a novel MoGU framework that improves LLMs' safety while preserving their usability.☆18Jan 14, 2025Updated last year
- Official repository for Reflecting Reality: Enabling Diffusion Models to Produce Faithful Mirror Reflections☆20Jun 7, 2025Updated last year
- Official PyTorch implementation of CD-MOE☆12Mar 18, 2026Updated 7 months ago
- [NeurIPS 2026] Agentic reinforcement learning for CLI agents with structured action credit assignment, budgeted workspace context selecti…☆19Oct 12, 2026Updated 2 weeks ago
- (ICLR 2026) Unveiling Super Experts in Mixture-of-Experts Large Language Models☆44Sep 25, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- The official implementation of HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization☆19Mar 7, 2025Updated last year
- [ACL'24] Can LLMs Speak For Diverse People? Tuning LLMs via Debate to Generate Controllable Controversial Statements☆25Sep 14, 2024Updated 2 years ago
- Official code for the paper: Continual Task Allocation in Meta-Policy Network via Sparse Prompting☆23Feb 10, 2025Updated last year
- The code of Advancing Expert Specialization for Better MoE (NeurIPS2025 oral)☆35Jan 22, 2026Updated 9 months ago
- [ACL'25 Oral] What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective☆75Jun 25, 2025Updated last year
- PELA: Learning Parameter-Efficient Models with Low-Rank Approximation [CVPR 2024]☆19Apr 14, 2024Updated 2 years ago
- Sparse Autoencoders (SAE) vs CLIP fine-tuning fun.☆18Dec 19, 2024Updated last year