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 10,681–10,704 of 15,973 skills
- Sonicmoe Training OptimizationOptimize MoE training through memory-efficient backward pass, IO-aware kernel design overlapping memory operations, and token rounding routing. Avoid caching large-scale activations, fuse operations with GEMM, implement ping-pong scheduling. Achieve 1.86× compute throughput on Hopper GPUs and 16% higher TFLOPS in sparse configurations.Votes: 0GitHub stars: 6
- Simko Pass KImprove pass@K by using asymmetric probability boosting: increase probabilities of top-K correct solutions while penalizing top-1 incorrect predictions. Focus boosting on high-entropy tokens where exploration helps most.Votes: 0GitHub stars: 6
- Self Forcing VideoAddress exposure bias in video generation by training on self-generated sequences, achieving 17 FPS real-time performance while matching quality of slower baselines.Votes: 0GitHub stars: 6
- Rlve Scaling Rl With Adaptive EnvironmentsScale RL training for language models by automatically adapting problem difficulty to match model capabilities using verifiable reward environments—achieving 3.37% absolute improvement on reasoning benchmarks through environment diversity rather than compute scaling alone.Votes: 0GitHub stars: 6
- Rlad Discovering AbstractionsTrain LLMs to discover domain-specific abstractions (concise representations of procedural and factual knowledge) through two-player RL. An abstraction generator proposes key insights, a solution generator uses them to solve problems, and both receive RL rewards, learning structured reasoning that transfers to harder problems.Votes: 0GitHub stars: 6
- Rl Visual ReasoningRL in vision-language models improves inference-time alignment between vision and reasoning in mid-to-late layers, not vision ability or reasoning separately. Strategic layer freezing enables diagnosis of which components contribute to RL gains.Votes: 0GitHub stars: 6
- Rl Awb Nighttime White BalanceCorrect color distortion in nighttime photos by combining statistical gray-pixel detection with reinforcement learning parameter optimization. Achieves superior cross-camera generalization without extensive labeled nighttime training data through a hybrid architecture that preserves interpretability while gaining adaptive tuning capability.Votes: 0GitHub stars: 6
- Revisual Multimodal ReasoningDevelop sophisticated multimodal reasoning through text-centric cold-start initialization, prioritized advantage distillation, and staged RL refinement.Votes: 0GitHub stars: 6
- Rethinking Thinking Tokens Improvement OperatorsEnable longer reasoning within bounded context through iterative refinement: generate solution → verify → compress → refine. Achieves +11% on AIME with lower per-call latency than naive chain-of-thought.Votes: 0GitHub stars: 6
- Relayllm Efficient Reasoning CollaborationEnable small language models to dynamically invoke larger models at critical reasoning tokens rather than offloading entire queries. RelayLLM achieves 49.52% accuracy across benchmarks while invoking the large model for only 1.07% of tokens—98.2% cost reduction compared to non-collaborative approaches.Votes: 0GitHub stars: 6
- Regft Reference Guided FinetuningReGFT pre-trains models on hybrid reference-augmented trajectories before RL, enabling them to solve harder problems and accelerate convergence.Votes: 0GitHub stars: 6
- Refusal Falls Off Cliff Safety ReasoningIdentify and patch critical safety vulnerabilities in large reasoning models. Via linear probing and causal intervention, locate specific attention heads responsible for alignment degradation at final tokens. Recover safety via 'Cliff-as-a-Judge' data curation targeting examples exhibiting largest refusal decline, achieving comparable improvements using only 1.7% of vanilla safety training data.Votes: 0GitHub stars: 6
- Reasoning Vectors Cot Task ArithmeticExtract and transfer reasoning capabilities between language models using task vectors derived from supervised fine-tuning and reinforcement learning weight differences. Apply reasoning vectors via simple arithmetic to enhance any compatible instruction-tuned model without retraining.Votes: 0GitHub stars: 6
- Reasoning Core Synthetic DataReasoning Core procedurally generates verifiable symbolic reasoning datasets across formal domains (planning, logic, parsing), with external solvers and curriculum control.Votes: 0GitHub stars: 6
- Reasoning As CompressionOptimize chain-of-thought reasoning under computational budgets using information-theoretic compression principles, improving reasoning efficiency without accuracy loss.Votes: 0GitHub stars: 6
- Radial Attention VideoAccelerate video diffusion models using sparse radial attention that exploits energy decay patterns. Achieves 3.7× speedup on long videos while maintaining quality through O(n log n) complexity instead of O(n²).Votes: 0GitHub stars: 6
- R HorizonConstruct multi-step reasoning benchmarks with interdependent problems to evaluate and improve long-horizon reasoning in large reasoning models. Enables evaluation of reasoning depth and breadth beyond single-step tasks.Votes: 0GitHub stars: 6
- Prism Diffusion ScalingScale inference efficiency for discrete diffusion language models through hierarchical trajectory search with adaptive pruning and self-verified feedback. Achieve 3-4× speedup versus best-of-N with equal quality.Votes: 0GitHub stars: 6
- Plan Budget ReasoningDecompose complex queries into sub-questions and allocate computational budgets adaptively based on estimated difficulty, achieving 70% accuracy improvements and 39% token reduction without retraining.Votes: 0GitHub stars: 6
- Pets Trajectory Allocation FrameworkOptimize sampling budget allocation for self-consistency inference by treating trajectory allocation as a crowdsourcing problem. Introduce self-consistency rate (agreement with infinite-budget consensus) as optimization target. Offline setting uses Optimistic Knowledge Gradient for Bayesian optimization; online setting uses difficulty grid discretization and greedy allocation. Achieves up to 75% budget reduction (offline) and 55% (online) while maintaining accuracy.Votes: 0GitHub stars: 6
- Pear Sft PreparationImprove post-RL performance by reweighting SFT loss using importance sampling. Prioritize training examples that match the target policy distribution, not the behavior policy. Achieves 14.6% Pass@8 gains on AIME.Votes: 0GitHub stars: 6
- Othink R1 Fast Slow ThinkingEnable reasoning models to adaptively switch between fast direct responses and slow detailed reasoning, reducing token consumption by 15-40% while maintaining accuracy through dual-mode fine-tuning.Votes: 0GitHub stars: 6
- Open Vision ReasonerTransfer reasoning behaviors learned in language models to visual domains through two-stage training: cold-start linguistic fine-tuning followed by multimodal RL. Open-Vision-Reasoner achieves 95.3% on MATH500 and 54.6% on MathVerse by learning visual analogs of backtracking, verification, and subgoal decomposition using rule-based rewards.Votes: 0GitHub stars: 6
- Nemotron 3 NanoEfficient agentic reasoning via sparse MoE activating 50% parameters per token. Combines Mamba-Transformer hybrid with 6-of-128 expert routing, three-stage post-training (SFT, verifiable RL, RLHF), and Group Relative Length Control—achieving 3.3× inference throughput of competitors while maintaining 1M token context support and superior reasoning.Votes: 0GitHub stars: 6