All authors
Claude Skills by ADu2021
github.com/ADu20211,228 skills0 installs1,664 views
- Flare Fast Low Rank AttentionImplement low-rank attention routing using encode-decode factorization to achieve linear-time complexity on long sequences while maintaining compatibility with optimized attention kernels.Votes: 0GitHub stars: 6
- Flash PrefillAccelerates long-context LLM prefilling by identifying sparse attention patterns without expensive scoring, using block-level approximations and dynamic thresholding. Achieves 27.78x speedup at 256K tokens while maintaining accuracy.Votes: 0GitHub stars: 6
- Flash Sampling Efficient DecodingFuse categorical sampling directly into LM-head matrix multiplication to eliminate logits materialization. Use Gumbel noise during computation and hierarchical reduction to achieve 19% token-level latency reduction.Votes: 0GitHub stars: 6
- Flash Searcher Dag Parallel AgentsReduce agent execution steps by 35% and latency by parallelizing sequential tool calls through task dependency graphs (DAGs). Use when deploying information-retrieval agents where tool execution ordering is flexible.Votes: 0GitHub stars: 6
- Flex Continuous Agent EvolutionEnable LLM agents to improve continuously during deployment by constructing structured experience libraries through self-reflection on successes and failures—achieving 23% improvement on reasoning without gradient-based parameter updates or external training.Votes: 0GitHub stars: 6
- Flexibility Trap Diffusion ReasoningUnderstand how token generation flexibility in diffusion LMs paradoxically constrains reasoning, as models exploit ordering flexibility to avoid uncertain tokens, and apply simplified approaches that preserve parallel decoding benefits. Use when optimizing diffusion-based language models for reasoning tasks.Votes: 0GitHub stars: 6
- Flexible Data Mixture Of ExpertsTrain language models where each expert learns independently on closed datasets, enabling flexible inference with selective data inclusion or exclusion. 41% performance improvement while allowing users to opt out of specific data sources without retraining.Votes: 0GitHub stars: 6
- Flow Map Trajectory TiltingUses flow maps as look-ahead operators to enable principled reward-guided diffusion by predicting trajectory endpoints at any denoising step. Deploy when applying rewards or preferences to diffusion trajectories with meaningful gradients throughout generation.Votes: 0GitHub stars: 6
- Flowblending Video InferenceAccelerate video generation by allocating smaller models to intermediate diffusion timesteps and larger models to capacity-critical early and late stages. Achieves 1.65x speedup and 57% FLOP reduction while maintaining visual quality. Use when video generation latency or computational cost is critical and you have multiple model sizes available.Votes: 0GitHub stars: 6
- Flowprefill Scheduling PreemptionImprove LLM serving under mixed workloads by decoupling execution granularity from scheduling frequency. Operator-level preemption allows fine-grained interruption at natural boundaries (attention, feed-forward layers) without efficiency loss. Event-driven scheduling triggers decisions only on request arrival/completion. Eliminates head-of-line blocking where long requests starve short time-sensitive ones. Achieves 5.6× higher goodput vs. baselines in production workloads.Votes: 0GitHub stars: 6
- Flowrl Reward Distribution MatchingTrain LLMs with distribution-matching rewards instead of reward maximization to achieve 10% improvement on math reasoning while improving solution diversity by matching the full reward distribution via flow balancing, addressing mode collapse in long chain-of-thought tasks.Votes: 0GitHub stars: 6
- Focus Agent Context Trimming Web AgentsReduce web agent context size by 51% while maintaining task performance using lightweight LLM retrieval to extract relevant accessibility tree lines. Task-guided filtering removes irrelevant elements, improving inference cost and security by neutralizing prompt injection attacks without sacrificing normal operation.Votes: 0GitHub stars: 6
- Focus Agent Context TrimmingUse a lightweight LLM to filter accessibility tree observations by task relevance, reducing agent context size by 50-80% while maintaining equivalent task performance.Votes: 0GitHub stars: 6
- Focused Chain Of ThoughtTraining-free prompting strategy that pre-organizes query information into compact structured format, reducing generation tokens by 2-3× while maintaining reasoning accuracy. Apply when reasoning performance is bottlenecked by verbose input formatting.Votes: 0GitHub stars: 6
- Foreagent Predict ExecuteReplace expensive test-based execution loops with learned prediction models that forecast agent action outcomes before commitment. Framework uses internalized execution priors and structured analysis reports to achieve 6x faster convergence and 6% higher performance compared to execute-first baselines. Applicable to scientific discovery, optimization, and hypothesis testing where verification is computationally or financially expensive.Votes: 0GitHub stars: 6
- Formal Uncertainty Llm ReasoningPredict when LLM outputs are trustworthy for formal reasoning by analyzing domain-specific uncertainty signals.Votes: 0GitHub stars: 6
- Fourier Approximated Kv CacheTraining-free framework compressing KV caches using Fourier basis functions, exploiting heterogeneous transformer head roles for memory-efficient long-context LLMs.Votes: 0GitHub stars: 6
- Fp32 Reproducible Llm InferenceDiagnose and solve LLM reproducibility failures caused by floating-point precision across hardware configurations using LayerCast optimization for deterministic inference with minimal memory overhead.Votes: 0GitHub stars: 6
- Freelong Plus Plus Long Video GenerationExtend video diffusion models to generate 4-8× longer sequences without retraining. Uses frequency-aware attention to blend local detail preservation with global consistency, identifying and fixing high-frequency distortion in extended videos.Votes: 0GitHub stars: 6
- Freemorph Tuning Free Image MorphingGenerate smooth morphing sequences between images without fine-tuning or alignment. Uses guidance-aware spherical interpolation and step-oriented attention blending to handle diverse semantic and layout scenarios, completing morphs 50× faster than fine-tuning methods.Votes: 0GitHub stars: 6
- Frugal Reasoning Short Math SolutionsAchieve emergent brevity in reasoning by retaining and up-weighting easy problems during RL training, implicitly regularizing solution length without explicit penalties while maintaining accuracy on hard problems.Votes: 0GitHub stars: 6
- Fs Researcher ScalingScale research agent capability using persistent filesystem as external memory. Dual-agent architecture with context builder accumulating knowledge and report writer composing outputs enables computation scaling beyond context windows.Votes: 0GitHub stars: 6
- Fuselip Multimodal EmbeddingsBuild unified multimodal embeddings with a single transformer encoder processing image and text tokens together, improving performance on structure-aware tasks through early fusion.Votes: 0GitHub stars: 6
- Fusionroute Token Llm CollaborationCombine multiple specialized language models at token-level granularity without joint training or architectural compatibility. FusionRoute performs expert selection and generates complementary logits to overcome routing limitations, achieving superior cross-domain performance at inference time.Votes: 0GitHub stars: 6
- G2rl Gradient GuidedGuide LLM exploration through the model's own gradient geometry rather than external signals. Extract sequence-level gradient features measuring how tokens would reshape output distributions. Reward responses introducing novel gradient directions while deemphasizing redundant ones. Achieve orthogonal gradient directions and improved accuracy.Votes: 0GitHub stars: 6
- Gaea Geolocation Aware Conversational ModelBuild a conversational AI that combines image geolocalization with contextual geographical knowledge. GAEA enables users to query precise GPS locations from images while receiving conversational responses about places, their attributes, and regional context—outperforming GPT-4o by 7.2% on geography-aware visual QA tasks.Votes: 0GitHub stars: 6
- Gain Rl Angle ConcentrationImprove RL training efficiency by 2.5× using angle concentration between token hidden states as a cost-effective data scheduling signal, selecting high-gradient samples dynamically.Votes: 0GitHub stars: 6
- Gametalk Training Llms For Strategic ConversationImplement techniques from GameTalk: Training LLMs for Strategic Conversation. Strategic decision-making in multi-agent settings is a key challenge for large language models (LLMs), particularly when coordination and negotiation must unfold over extended conversationsVotes: 0GitHub stars: 6
- Gdpo Multi Reward OptimizationOptimize language models against multiple reward signals simultaneously by decoupling reward normalization. GDPO prevents reward combination collapse that undermines training signal quality when aligning models to multiple human preferences like accuracy, safety, efficiency, and format compliance.Votes: 0GitHub stars: 6
- Gem Agentic Llm EnvironmentA standardized environment framework for training and evaluating LLM agents, providing 24+ tasks with asynchronous vectorized execution, extensible wrappers, and integration examples for five RL frameworks. Enables reproducible agent research and training at scale.Votes: 0GitHub stars: 6
- Gen3r 3d Scene Generation Meets Feed Forward ReconGenerative approach for creating complex dynamic scenes and content, supporting agent capabilities in understanding and reasoning about multi-agent environments.Votes: 0GitHub stars: 6
- General Agentic Memory JitBuild persistent, lossless agent memory using just-in-time compilation: store complete history in a universal page-store while performing dynamic deep research at query time, enabling test-time scalability through iterative information synthesis and reflection.Votes: 0GitHub stars: 6
- Generalized Few Shot Point Cloud SegmentationSegment novel 3D point cloud classes with few support samples by combining dense but noisy pseudo-labels from 3D vision-language models with precise sparse few-shot annotations. GFS-VL adapts to new classes while retaining base class performance, using prototype-guided filtering and adaptive infilling strategies ideal for applications with limited labeled training data.Votes: 0GitHub stars: 6
- Genie Envisioner Robotic FoundationUnified platform combining instruction-conditioned video diffusion, flow-matching action decoder, and action-conditioned simulator. Enables scalable robot learning without extensive labeled demonstrations.Votes: 0GitHub stars: 6
- Geometry Forcing Video Diffusion 3dImprove video diffusion consistency by aligning intermediate diffusion features with 3D geometric representations from pretrained foundation models, enabling spatially coherent and temporally stable video generation through angular and scale alignment losses.Votes: 0GitHub stars: 6
- Geometry Grounded VlmExtend vision-language models with 3D spatial understanding by adding geometric expert stream alongside semantic expert: predict pixel-aligned 3D point maps, surface normals, and camera poses from 2D images, enabling unified reasoning across 2D semantic and 3D geometric domains.Votes: 0GitHub stars: 6
- Gere Continual LearningPrevents catastrophic forgetting in continual LLM learning using threshold-based margin loss with fixed general replay samples from pretraining data.Votes: 0GitHub stars: 6
- Gigaevo Llm EvolutionEvolve Python algorithms and programs using LLMs as mutation operators combined with MAP-Elites quality-diversity search, achieving competitive results on geometric optimization and algorithmic problems by iteratively mutating code informed by historical performance and lineage context.Votes: 0GitHub stars: 6
- Gimbaldiffusion Camera ControlControl video camera motion using gravity-aligned absolute coordinates instead of relative trajectories. GimbalDiffusion enables precise camera control with null-pitch conditioning—ideal when you need interpretable, physics-aware camera motion in text-to-video.Votes: 0GitHub stars: 6
- Glance Phase Aware AccelerationPhase-aware acceleration using two lightweight LoRA adapters (Slow-LoRA for semantic reconstruction, Fast-LoRA for texture refinement) trained on a single image in one GPU hour, achieving 5× speedup via smart per-phase acceleration rather than uniform speedup.Votes: 0GitHub stars: 6
- Glm Multimodal ReasoningTrain vision-language models with curriculum-based reinforcement learning (RLCS) to improve reasoning across diverse multimodal tasks. Dynamically adjust training difficulty to model capability, preventing both trivial and overly-hard examples.Votes: 0GitHub stars: 6
- Gnosis Llm Self AwarenessEnable frozen LLMs to predict their own correctness by decoding signals from internal hidden states and attention patterns, achieving reliable self-verification without external judges—adding only 5M parameters while reducing inference cost and improving calibration.Votes: 0GitHub stars: 6
- Goedel Prover Formal Theorem ProvingTrain language models for formal theorem proving via expert iteration with verifier-guided self-correction and checkpoint merging.Votes: 0GitHub stars: 6
- Golden Goose Task SynthesisSynthesize unlimited verifiable training tasks from unverifiable text by converting reasoning passages into multiple-choice problems. Creates higher-quality training data for RLHF systems without requiring new human labels.Votes: 0GitHub stars: 6
- Gorl Generative Online RlSeparates generative policy optimization through latent encoder (standard RL algorithms) and conditional decoder (frozen then refined), using two-timescale alternating schedule to eliminate gradient instability from direct generative policy optimization.Votes: 0GitHub stars: 6
- Governed Autonomy Drug DiscoveryBalance LLM flexibility with domain rigor in scientific agents through dual-layer architecture. Enforce role-based access control and artifact-centric state management to prevent hallucinations, while preserving free-form reasoning for lower-risk tasks.Votes: 0GitHub stars: 6
- Gradient Grouping Learning Rate ScalingImprove adaptive learning rates by clustering gradient statistics within layers and applying cluster-specific scaling.Votes: 0GitHub stars: 6
- Gradmem Context Memory CompressionCompress long context into compact memory tokens via iterative gradient descent. Learn to write information into prefix memory without storing full KV-caches, enabling efficient long-context reasoning and retrieval.Votes: 0GitHub stars: 6
- Grao Unified AlignmentUnifies supervised fine-tuning and reinforcement learning through GRAO framework that combines multiple-output generation with group direct alignment loss for improved preference learning.Votes: 0GitHub stars: 6
- Grape Group Position EncodingUnify positional encoding methods via group action theory, encompassing RoPE and ALiBi as special cases. GRAPE enables exploration of cross-subspace feature coupling—ideal when you need principled positional encoding beyond standard implementations.Votes: 0GitHub stars: 6