All categories
Code Review & Quality
Code review, refactoring, debugging, maintainability, and engineering quality
- 15,973
- 666
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse code review & quality skills
Showing 10,705–10,728 of 15,973 skills
- 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
- 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
- Lopa LookaheadMaximize parallelism in diffusion language models by intelligently exploring token filling orders. Spawn multiple candidate branches predicting high-confidence positions, evaluate all branches in one forward pass, and select the branch enabling most future parallelism—increasing tokens-per-forward-pass 4.4× without accuracy loss.Votes: 0GitHub stars: 6
- Long Cot TrainingNavigate Long CoT Degradation phenomenon when training small models on extended reasoning, understanding recovery dynamics and implementing strategies to maintain performance.Votes: 0GitHub stars: 6
- Log Linear Sparse AttentionReduce self-attention complexity from O(N²) to O(N log N) through hierarchical token selection and enrichment. Perform hierarchical Top-K selection progressively adopting sparse Top-K at each level. Implement sparse index transpose algorithm avoiding dense mask construction. Achieve 28.27× faster inference and 6.09× faster training.Votes: 0GitHub stars: 6
- Light If Preview CheckingMulti-stage training approach using entropy-preserving SFT and token-wise entropy-adaptive RL to improve instruction adherence. Combines data curation with reward-guided reasoning, outperforming larger models on IFEval.Votes: 0GitHub stars: 6
- Learnable Multipliers Lm ScalingAdapt language model weight matrix scales automatically during training by adding learnable scalar and vector multipliers to each layer. Breaks the noise-weight-decay equilibrium that constrains scales based on hyperparameters rather than data, enabling data-driven scaling adaptation without inference cost or extensive tuning overhead.Votes: 0GitHub stars: 6
- Leank Kv Cache PruningLearning-based approach to reduce key-value cache memory during inference through static channel-wise sparsity masks. Achieves 70% K cache and 16-18% V cache memory reduction with 1.3x attention speedup.Votes: 0GitHub stars: 6
- Laser Self RewardCompute reasoning rewards from the model's own next-token probability distribution at solution end. Integrates verification-based feedback into single model without separate evaluator, enabling efficient RL training with minimal overhead.Votes: 0GitHub stars: 6
- Knot Forcing AnimationEnable real-time portrait animation via causal AR video generation with temporal coherence. Sliding window with global reference frame caching, temporal knot module overlapping adjacent chunks, global context running ahead—preventing error accumulation while maintaining streaming efficiency and bidirectional-quality consistency.Votes: 0GitHub stars: 6
- Jacobi Parallel DecodingEnable efficient parallel decoding while preserving causal inference properties through progressive distillation with cyclic noise scheduling. Reduce training complexity via block-wise sparse attention, implement rejection recycling and multi-block decoding. Achieve 3.8-4.0× wall-clock speedup on coding benchmarks.Votes: 0GitHub stars: 6
- Internvl3 5 Multimodal Cascade RlEnhance multimodal models through cascade RL for reasoning improvement and visual resolution routing for inference efficiency, achieving 16% reasoning gains and 4.05x speedup.Votes: 0GitHub stars: 6
- Infinitevl Linear Sparse AttentionMerge sliding window and linear attention (Gated DeltaNet) for unlimited VLM inputs with 3.6× speedup. InfiniteVL handles video understanding at 24 FPS with constant memory—ideal when context length must scale without quadratic overhead.Votes: 0GitHub stars: 6
- Ieap Image EditingEnable robust image editing by decomposing free-form instructions into sequential atomic operations executed through a neural program interpreter.Votes: 0GitHub stars: 6
- Hyperagents Self ImprovementEnable AI systems to recursively improve themselves by making the meta-level modification procedure itself editable, achieving open-ended capability growth.Votes: 0GitHub stars: 6
- Humanomni Multimodal ReasoningImprove multimodal reasoning by requiring explicit context understanding before reasoning. Use specialized reward mechanisms and context-aware training to prevent information-skipping shortcuts.Votes: 0GitHub stars: 6
- Grove Moe Adjugate ExpertsEnables efficient MoE architectures through heterogeneous expert sizing and dynamic activation mechanisms that adjust parameter count based on input complexity.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
- 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
- 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
- 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
- Exgrpo Learning From ExperienceImprove LLM reasoning efficiency by systematically reusing past rollouts through experience replay. ExGRPO organizes training data by success and diversity, applying a mixed-policy objective that prioritizes high-quality examples while maintaining exploration, achieving 3.5-7.6 point gains over on-policy methods.Votes: 0GitHub stars: 6
- Dynamic Mask Sparse AttentionSparse attention mechanism combining content-aware and position-aware sparse patterns through dynamic masking. Achieves 10x speedup while maintaining model quality on long-context benchmarks through hardware-friendly implementation.Votes: 0GitHub stars: 6
- Dr Llm Dynamic RoutingUse per-layer routers trained with Monte Carlo Tree Search to dynamically skip, execute, or repeat transformer layers for each token. Saves ~5 layers per example while maintaining accuracy on diverse benchmarks.Votes: 0GitHub stars: 6