All authors
Claude Skills by ADu2021
github.com/ADu20211,228 skills0 installs1,664 views
- Mano Manifold OptimizationImprove LLM training efficiency through manifold-based optimization that projects momentum onto tangent spaces and constrains updates on rotational Oblique manifolds. Achieves 1.75× faster convergence than Muon with reduced memory.Votes: 0GitHub stars: 6
- Mapo Mixed Advantage Policy OptimizationDynamically reweight advantage functions based on trajectory certainty to improve policy optimization in foundation models. Addresses advantage reversion and mirror problems by mixing standardized and mean-normalized advantage formulations. Enables more stable gradient signals across high- and low-certainty samples.Votes: 0GitHub stars: 6
- Maps Multiagent Personality ReasoningCoordinate specialized agents with distinct personality traits (Openness, Agreeableness, Conscientiousness, Extraversion) to solve complex scientific problems across text and vision, using a Critic agent to apply Socratic questioning for iterative refinement and error correction.Votes: 0GitHub stars: 6
- Margin Adaptive DpoAdapt DPO temperature parameters per sample using reward model margins, amplifying learning signals for hard preference pairs while dampening easy ones.Votes: 0GitHub stars: 6
- Markovian ThinkerEnable LLMs to scale reasoning length from O(n²) to O(n) by structuring thinking into fixed-size chunks with learnable cross-chunk summaries. Trigger: train reasoning models with unbounded or expensive chain-of-thought sequences.Votes: 0GitHub stars: 6
- Mars Rl Multi Agent ReasoningTrain multi-agent reasoning systems with decoupled reward signals and pipeline parallelism—enable specialized Solver/Verifier/Corrector agents to iteratively refine solutions without waiting for full trajectories, handling extended reasoning up to 320K tokens.Votes: 0GitHub stars: 6
- Mars Socratic Prompt OptimizationOptimize task-specific prompts using five cooperative agents (Planner, Teacher, Critic, Student, Target) in a POMDP framework, where the Planner generates adaptive trajectories and a Teacher-Critic-Student triad refines prompts through Socratic dialogue, achieving 85.11% accuracy on general tasks and 75.81% on specialized domains.Votes: 0GitHub stars: 6
- Matchtir Fine Grained Tool ReasoningImproves tool-integrated reasoning by using bipartite matching to assign dense turn-level rewards, enabling credit assignment for individual tool interactions in multi-turn tasks where 4B models outperform 8B competitors.Votes: 0GitHub stars: 6
- Math Reasoning TransferUnderstand why math reasoning improvements don't always transfer to general capabilities. Use RL-based training instead of SFT to preserve representation structure and enable broader generalization.Votes: 0GitHub stars: 6
- Mathflow Visual Mathematical ReasoningImprove mathematical problem-solving in multimodal models by decoupling visual perception from inference reasoning. A two-stage pipeline extracts essential visual information and reasoned properties before passing enriched text to inference models, dramatically improving accuracy on visual math problems.Votes: 0GitHub stars: 6
- Mathse Iterative Math ReasoningImprove multimodal mathematical reasoning through iterative reflection cycles where an outcome reward model provides feedback on reasoning quality, and correct solutions are incorporated back into training—enabling continuous model adaptation beyond static datasets.Votes: 0GitHub stars: 6
- Mattrl Multi Agent ReasoningEnables LLM-based agent teams to improve reasoning accuracy at inference time through collaborative deliberation and structured experience retrieval, achieving 3-8% accuracy gains without expensive multi-agent training.Votes: 0GitHub stars: 6
- Mcp Bench Tool AgentsEvaluate LLM agents on realistic tool-use tasks via 28 live MCP servers with 250 tools, assessing fuzzy tool discovery, multi-step planning, and cross-domain workflow coordinationVotes: 0GitHub stars: 6
- Mcp Mark Comprehensive Agent BenchmarkEvaluate LLM agents through realistic multi-turn tool-use workflows across 127 complex MCP tasks spanning CRUD operations, state management, and error handling. Use when assessing agent capabilities on real-world tool orchestration beyond shallow read-only interactions.Votes: 0GitHub stars: 6
- Mdagent2 Large Language Model For Code GenerationGenerative approach for creating complex dynamic scenes and content, supporting agent capabilities in understanding and reasoning about multi-agent environments.Votes: 0GitHub stars: 6
- Meanflow One Step GenerationTrains mean-velocity models on rectified couplings from pretrained flow models to dramatically smooth loss landscape, enabling faster convergence and superior one-step generation quality without additional training data.Votes: 0GitHub stars: 6
- Mecellem Models Turkish Models Trained From ScratcImplement techniques from Mecellem Models: Turkish Models Trained from Scratch and Continually Pre-trained for the Legal Domain. This paper presents Mecellem models, a framework for developing specialized language models for the Turkish legal domain through domain adaptation strategiesVotes: 0GitHub stars: 6
- Mechanistic Interpretability Of Large Scale CountiAnalysis framework for understanding how large language models perform complex cognitive tasks, revealing internal reasoning mechanisms that inform agent architecture and capability assessment.Votes: 0GitHub stars: 6
- Medical Multimodal Foundation ModelsBuild efficient medical vision-language models that reason about medical images and text simultaneously, achieving competitive performance with much larger models while maintaining 500× lower computational cost.Votes: 0GitHub stars: 6
- Medical Sam3 A Foundation Model For UniversalPromptable segmentation foundation models such as SAM3 have demonstrated strong generalization capabilities through interactive and concept-based prompting. However, their direct applicability to medical image segmentation remains limited by severe domain shifts, the absence of privileged spatial prompts, and the need to reason over complex anatomical and volumetric structures. Here we present Medical SAM3, a foundation model for universal prompt-driven medical image segmentation, obtained by...Votes: 0GitHub stars: 6
- Medical Video GenerationGenerate accurate, high-quality medical videos for clinical education and documentation by leveraging large-scale annotated medical datasets with domain-specific fine-tuning on video diffusion models.Votes: 0GitHub stars: 6
- Meeplelm A Virtual Playtester Simulating Diverse SImplement techniques from MeepleLM: A Virtual Playtester Simulating Diverse Subjective Experiences. Recent advancements have expanded the role of Large Language Models in board games from playing agents to creative co-designersVotes: 0GitHub stars: 6
- Memento Skills Agent DesignEnable agents to autonomously design and refine task-specific agents by evolving externalised behavioral skills and prompts without modifying base LLM parameters.Votes: 0GitHub stars: 6
- MemflyOptimize agent long-term memory by treating it as an information bottleneck problem. Dynamically compress redundant information while preserving task-relevant content through semantic-symbolic-topological hybrid retrieval.Votes: 0GitHub stars: 6
- Memfof Efficient Optical FlowReduces optical flow GPU memory 3.9× while maintaining state-of-the-art accuracy through correlation volume downsampling and dimension compensation. Enables native FullHD training with 2.09GB inference memory. Use for motion estimation in memory-constrained environments or high-resolution video processing.Votes: 0GitHub stars: 6
- Memgovern Code Agent LearningMemGovern: Enhancing Code Agents through Learning from Governed Human Experiences. From arXiv:2601.06789Votes: 0GitHub stars: 6
- Memobrain Memory AgentImplements MemoBrain from arXiv:2601.08079Votes: 0GitHub stars: 6
- Memorization 3d Shape GenerationEvaluate memorization in 3D generative models through controlled experiments discovering factors like dataset diversity and guidance scale. Provide simple yet effective strategies like rotation augmentation to reduce memorization without degrading generation quality.Votes: 0GitHub stars: 6
- Memory Agent EvaluationEvaluate and improve memory capabilities in LLM agents across four competencies: accurate retrieval, test-time learning, long-range understanding, and selective forgetting. Identifies critical gaps in how agents store, update, and revise information.Votes: 0GitHub stars: 6
- Memory As ActionTreat memory management as learnable RL policy actions (delete/insert) rather than fixed mechanisms. Enable models to autonomously decide what to keep, remove, or add to context, reducing average context length by 51% while matching larger models.Votes: 0GitHub stars: 6
- Memory Indexed Experience ScalingEnable long-horizon agents to manage finite context by separating working memory from persistent storage. Use indexed summaries with pointers to archived evidence, treating memory operations as first-class agent actions learned via RL.Votes: 0GitHub stars: 6
- Memory Llm Ffn DecouplingDecouple feed-forward networks from self-attention by training FFNs on context-free token embeddings instead of residual streams. Enables pre-computation of FFN outputs as static lookup tables for inference efficiency and improved interpretability.Votes: 0GitHub stars: 6
- Memory Operating SystemTreat memory as a manageable system resource for LLMs through unified management of plaintext, activation, and parameter-level memories with dynamic scheduling and lifecycle governance.Votes: 0GitHub stars: 6
- Memory T1 TemporalEnable agents to accurately identify temporally relevant information in long multi-session dialogues through RL-based memory retrieval. Combines coarse-to-fine candidate selection with multi-level temporal consistency rewards—providing dense supervision that disambiguates time expressions and maintains coherence across 128k-token contexts.Votes: 0GitHub stars: 6
- Memoryrewardbench Benchmarking Reward Models ForExisting works increasingly adopt memory-centric mechanisms to process long contexts in a segment manner, and effective memory management is one of the key capabilities that enables large language models to effectively propagate information across the entire sequence. Therefore, leveraging reward models (RMs) to automatically and reliably evaluate memory quality is critical. In this work, we introduce MemoryRewardBench, the first benchmark to systematically study the ability of RMs to evaluat...Votes: 0GitHub stars: 6
- Memskill Evolving Memory OperationsBuild agents that evolve their own memory operations by learning a skill bank of memory transformations and periodically discovering new skills from challenging cases, enabling adaptive memory management that improves with scale.Votes: 0GitHub stars: 6
- Meta Aware ReasoningImprove reasoning models by aligning their meta-predictions with actual rollouts through self-generated training signals. Trigger: accelerate reasoning model training while maintaining performance through better meta-cognitive awareness.Votes: 0GitHub stars: 6
- Metaclaw Continual Agent LearningEnable LLM agents to evolve behavioral skills and policies online through skill synthesis from failures and opportunistic gradient-based refinement, without service interruption.Votes: 0GitHub stars: 6
- Metafaith Uncertainty CalibrationTrain LLMs to faithfully express uncertainty through natural language that accurately reflects their actual confidence, improving trustworthiness and reducing overconfidence.Votes: 0GitHub stars: 6
- Mimo V2 Flash Technical ReportResearch contribution advancing agent and reasoning capabilities through novel approaches to model development, training, and evaluation.Votes: 0GitHub stars: 6
- Mimo Vl Vision LanguageBuild state-of-the-art 7B multimodal models by combining four-stage vision-language pretraining with mixed on-policy RL integrating verifiable and human feedback rewards.Votes: 0GitHub stars: 6
- Mindwatcher Toward Smarter Multimodal Tool IntegraSystem enabling intelligent tool integration and selection for enhanced multimodal reasoning, allowing agents to leverage heterogeneous capabilities for complex problem-solving across domains.Votes: 0GitHub stars: 6
- Minicpm SalaCombine sparse attention (25% of layers) and linear attention (75% of layers) via strategic layer placement to handle 1M-token contexts with 75% training cost reduction. Hybrid positional encoding preserves long-range information while maintaining position awareness.Votes: 0GitHub stars: 6
- Minicpm4 Efficient LlmsBuild ultra-efficient language models for edge devices using sparse attention, high-quality data filtering, and ternary quantization, achieving Qwen3-8B performance with 22% of training tokens.Votes: 0GitHub stars: 6
- Minimax M1 Lightning AttentionHybrid-attention MoE reasoning model supporting 1M token context and 80K token generation, combining lightning attention with CISPO RL algorithm for efficient scaling.Votes: 0GitHub stars: 6
- Minority Aware Adaptive Dpo DiffusionImprove diffusion model alignment with human preferences by handling subjective and conflicting annotations. Adaptive-DPO incorporates minority-instance metrics (intra-annotator confidence and inter-annotator stability) to distinguish majority from minority samples, enhancing performance on both synthetic and real preference data.Votes: 0GitHub stars: 6
- Mint Cot Visual ReasoningIntegrates fine-grained visual tokens into mathematical reasoning via Interleave Tokens that dynamically select relevant image regions for each reasoning step.Votes: 0GitHub stars: 6
- Mirror Speculative DecodingRun draft and target models in parallel across GPU/NPU using bidirectional speculation: draft predicts forward continuations while target speculates correction paths simultaneously. Achieve 2.8x-5.8x wall-time speedup on 14B-66B models.Votes: 0GitHub stars: 6
- Mits Pointwise Mutual Information Tree SearchScore reasoning paths using PMI to identify question-specific relevant steps without rollout simulations, enabling efficient tree search 12× faster than MCTS while improving reasoning accuracy.Votes: 0GitHub stars: 6
- Mix Reasoning Switching ModesImprove reasoning efficiency by dynamically adjusting elaboration depth within a single response. Difficult steps receive extensive chain-of-thought; straightforward steps use concise inference. Mix reasoning modes to achieve 57-79% token savings under compute budgets while maintaining accuracy on math, STEM, and coding benchmarks.Votes: 0GitHub stars: 6