All authors
Claude Skills by ADu2021
github.com/ADu20211,227 skills5 installs2,395 views
- Samtok Mask TokenizationTokenize any region mask into two special tokens, enabling pixel-wise tasks like segmentation and region understanding in multimodal language models without architectural changes. Use when adapting vision-language models to perform pixel-level understanding and manipulation.Votes: 0GitHub stars: 6
- Scale Selective Test TimeDecomposes math problems into sequential sub-problems, assesses difficulty, and allocates simple ones to fast System 1 reasoning while directing complex ones to deliberate System 2. Save 33-53% tokens while improving accuracy by up to 13.75 points on AIME.Votes: 0GitHub stars: 6
- Scalecua Cross Platform Computer Use AgentsBuild scalable open-source agents that autonomously operate graphical user interfaces across Windows, macOS, Linux, Android, iOS, and web platforms using large-scale cross-platform training data and vision-language models for GUI understanding, element grounding, and task completion.Votes: 0GitHub stars: 6
- Scaler Reasoning EnvironmentSCALER: Synthetic Scalable Adaptive Learning Environment for Reasoning. From arXiv:2601.04809Votes: 0GitHub stars: 6
- Scaling Behavior Cloning GamesTrain video game-playing foundation models discovering that increasing training data and network depth enables learning more causal policies. Release 8300+ hours of gameplay data and open-source models for real-time consumer GPU inference.Votes: 0GitHub stars: 6
- Scaling Latent ReasoningScales reasoning depth through internal iteration rather than explicit generation. Ouro models perform repeated computation in latent space with entropy-regularized objectives enabling learned depth allocation. Smaller 1.4B model matches 12B standard models through improved knowledge manipulation.Votes: 0GitHub stars: 6
- Scaling Laws CodeEstablish language-specific scaling laws for multilingual code pre-training across 7 programming languages (0.2B-14B models, 1T tokens). Show interpreted languages scale better than compiled, synergy gains depend on syntax similarity, and parallel pairing improves translation—enabling proportion-dependent token allocation outperforming uniform distribution.Votes: 0GitHub stars: 6
- Scaling Laws Optimal Data MixturesPredict optimal data mixture proportions for multi-domain LLM training using scaling laws that require only 10-20 small experiments. Determine which domains should contribute how much data across model sizes (186M-7B), reducing computational waste in foundation model pretraining.Votes: 0GitHub stars: 6
- Sched Fast Diffusion DecodingAccelerate diffusion LLM decoding by halting when confidence stabilizes using progress-dependent thresholds. SchED achieves 3.8-4.0× speedup while retaining 99.8-100% quality—training-free and model-agnostic for any dLLM.Votes: 0GitHub stars: 6
- Sciarena Evaluation PlatformBuild community-driven evaluation platforms for scientific tasks using pairwise model comparisons and human voting. Assess foundation models on literature-grounded reasoning without automated metrics.Votes: 0GitHub stars: 6
- Scientific Image Synthesis Benchmarking MethodologImplement techniques from Scientific Image Synthesis: Benchmarking, Methodologies, and Downstream Utility. While synthetic data has proven effective for improving scientific reasoning in the text domain, multimodal reasoning remains constrained by the difficulty of synthesizing scientifically rigorous imagesVotes: 0GitHub stars: 6
- Scievalkit An Open Source Evaluation Toolkit For SSystematic evaluation toolkit for assessing large language models across multiple dimensions, enabling comprehensive benchmarking of agent capabilities and comparative analysis of model performance.Votes: 0GitHub stars: 6
- Sculptor Active Context ManagementFramework enabling LLMs to actively manage internal working memory and context through tools for fragmentation, summarization, and semantic search. Mitigates proactive interference and improves reasoning at extended context lengths.Votes: 0GitHub stars: 6
- Seacache Spectral Evolution DiffusionAccelerate diffusion models through spectral-evolution-aware caching. Exploit insight that early timesteps establish low-frequency structure while later timesteps refine high-frequency details. Apply FFT-based frequency filtering to feature cache decisions: preserve content-relevant frequency components while suppressing noise. Plug-and-play training-free enhancement achieving 1.5–2.5× speedup across FLUX, HunyuanVideo, Wan2.1 models.Votes: 0GitHub stars: 6
- Seagent Self Evolving Computer UseVision-based computer use agent that self-improves through experiential learning, curriculum generation, and reward-based RL on diverse software.Votes: 0GitHub stars: 6
- Sealqa Reasoning SearchEvaluate search-augmented language models on fact-seeking questions with conflicting or unhelpful search results, revealing critical reasoning gaps in frontier models and testing robustness to noisy information.Votes: 0GitHub stars: 6
- Search R2 Refinement RlDecompose search-integrated reasoning into actor (generates trajectories) and refiner (identifies and corrects flawed steps). Refiner performs surgical cut-and-regenerate correction preserving valid prefixes. Trained end-to-end with GRPO; adds minimal overhead (2%) to baseline.Votes: 0GitHub stars: 6
- Search R3 ReasoningUnify LLM reasoning with embedding generation by training models to output embeddings as direct outputs of step-by-step reasoning. Trigger: improve performance on complex retrieval tasks requiring deep reasoning.Votes: 0GitHub stars: 6
- See Upo Sequence Level RlTrain multi-turn AI agents with convergence guarantees using sequential backward-induction updates, eliminating the need for separate critic networks while maintaining theoretical optimality. Use for long-horizon agentic reasoning where monotonic improvement and global optimality are required.Votes: 0GitHub stars: 6
- Seed Diffusion Parallel Code GenerationFast parallel code generation using discrete-state diffusion models with curriculum learning and trajectory optimization, achieving 2,146 tokens/second inference speed.Votes: 0GitHub stars: 6
- Seed Prover 1 5Enable LLM agents to incrementally construct formal proofs through strategic tool orchestration rather than one-shot generation. Combines natural language reasoning, sketch translation, and formal verification in an agentic workflow trained via PPO and Rubric RL, achieving competitive performance on undergraduate and graduate proof problems.Votes: 0GitHub stars: 6
- Seed Prover Automated Theorem ProvingFramework combining formal verification feedback with long chain-of-thought reasoning to enable deep and broad mathematical reasoning for automated theorem proving. Achieves 78.1% on formalized IMO problems through lemma-based refinement and test-time inference strategies.Votes: 0GitHub stars: 6
- Seedvr2 Video RestorationAchieves single-step video restoration at 1080p resolution with 4x speedup over multi-step diffusion approaches via adversarial training, adaptive window attention, and feature matching loss.Votes: 0GitHub stars: 6
- Segment Policy OptimizationSegment-level credit assignment for RL in LLMs using Monte Carlo advantage estimation, enabling precise reward attribution without critic models for improved reasoning task performance.Votes: 0GitHub stars: 6
- Self Eval T2iTrain text-to-image models from scratch for any inference step count via self-evaluation mechanism. Model evaluates its own generated samples using current score estimates as dynamic self-teacher, enabling global distribution matching without external teachers—achieving few-step quality equivalent to many-step models at all budgets.Votes: 0GitHub stars: 6
- Self Evolving AgentsEnable agents to learn continuously from execution experience through hierarchical memory and autonomous reflection. Trigger: improve agent performance on long-horizon tasks by accumulating and applying experience.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
- Self Rewarding VlmEnable VLMs to self-assess visual perception accuracy through decomposed two-stage reasoning: perception generation then validation, eliminating external supervision dependencyVotes: 0GitHub stars: 6
- Semantic Visual ReconstructionAdd explicit visual supervision to VLMs by training models to autoregressively reconstruct semantic image tokens, achieving 2-3% average gains and 10-point improvements on hallucination robustness.Votes: 0GitHub stars: 6
- Semanticgen VideoAccelerate video generation and enable long-video synthesis by decomposing into two diffusion stages: first generate compact semantic features for global planning, then generate VAE latents conditioned on semantics. Includes learnable semantic compression to improve training convergence—enabling minute-long videos with faster convergence than direct VAE modeling.Votes: 0GitHub stars: 6
- Semcot Accelerated Cot Implicit TokensEncode reasoning steps as hidden embeddings instead of explicit text using contrastively-trained sentence transformers and lightweight distilled models, reducing token generation cost while preserving semantic alignment with ground-truth reasoning.Votes: 0GitHub stars: 6
- Sensenovamars Multimodal ReasoningBuild vision-language agents that seamlessly integrate visual reasoning with dynamic tool manipulation (search, cropping) through reinforcement learning, achieving state-of-the-art performance on fine-grained visual understanding tasks—surpassing proprietary models like Gemini and GPT.Votes: 0GitHub stars: 6
- Sentinel Prompt ProtectionDeploy a state-of-the-art binary classifier using ModernBERT to detect prompt injection attacks and protect LLMs from adversarial input manipulation.Votes: 0GitHub stars: 6
- Sequential Diffusion Language ModelsImplement adaptive parallel decoding for language models using diffusion-based next-sequence prediction. Enable dynamic block-based token generation with confidence thresholds to achieve 2x+ speedups while maintaining competitive performance. Retrofit existing autoregressive models with minimal additional training data.Votes: 0GitHub stars: 6
- Sequential Edge Inverse Entropy VotingReplace parallel self-consistency with sequential reasoning where chains iteratively build on previous attempts, weighted by inverse entropy to prioritize confident solutions, achieving 46.7 pp accuracy gains over parallel approaches.Votes: 0GitHub stars: 6
- Set Block Decoding Inference AccelerationAccelerate language model generation 3-5x by combining autoregressive and masked token prediction. Works via fine-tuning—no architectural changes needed. Parallel decode non-consecutive tokens with entropy-bounded sampling.Votes: 0GitHub stars: 6
- Shape Of ThoughtDemonstrate that synthetic CoT traces with incorrect final answers outperform human-written correct solutions for supervised fine-tuning. Distribution proximity between training data and student model's natural output matters more than correctness—validating human traces with model-like distributions improves performance, providing practical guidance for dataset curation.Votes: 0GitHub stars: 6
- Signround V2 Low Bit QuantDeltaLoss sensitivity metric combining gradient and quantization-induced parameter deviation for adaptive bit-width allocation, with lightweight pre-tuning search for scale initialization, enabling competitive accuracy at 4-5 bits in 2.5-6 hours.Votes: 0GitHub stars: 6
- Silvr Language Video ReasoningConvert videos to language-based representations and leverage LLM reasoning without video-specific training.Votes: 0GitHub stars: 6
- Sim Cot Supervised Implicit Chain Of ThoughtTrain LLMs to reason implicitly with step-level supervision, stabilizing latent representations while preserving 2.3× inference speedup over explicit chain-of-thought. Addresses training collapse in implicit reasoning by aligning intermediate latent states with explicit reasoning steps through an auxiliary decoder during training, then removing the decoder for efficient inference.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
- Simple Gpt Normalization StrategyPlace RMSNorm immediately after every linear layer to stabilize activation scales at O(sqrt(d)) and reduce Hessian spectral norm. Enables 3-10x larger learning rates and faster convergence without architectural changes; improves loss by 0.08 on 7B models.Votes: 0GitHub stars: 6
- Simplemem Lifelong MemoryImplement efficient memory systems for long-term LLM agent interactions using semantic compression, achieving 30-fold inference token reduction while improving F1 scores by 26.4%—enabling agents to learn from extended interaction histories without prohibitive context costs.Votes: 0GitHub stars: 6
- Simpletir Multi Turn Tool Reasoning RlTrain LLMs for multi-turn tool-integrated reasoning end-to-end using RL without supervised pretraining. SimpleTIR stabilizes training by filtering void turns (responses lacking code blocks or final answers) to prevent gradient explosion from distributional drift, enabling discovery of emergent reasoning patterns like self-correction and cross-validation on mathematical benchmarks.Votes: 0GitHub stars: 6
- Simplevla Rl Scaling Vla TrainingApply reinforcement learning to Vision-Language-Action models for robotic control, achieving 99% LIBERO task success and discovering novel manipulation strategies (pushcut) without task-specific reward engineering. Scales efficiently via parallelized trajectory sampling and outcome-based rewards.Votes: 0GitHub stars: 6
- Sin Bench Tracing Native Evidence Chains In LongEvaluating whether multimodal large language models truly understand long-form scientific papers remains challenging: answer-only metrics and synthetic 'Needle-In-A-Haystack' tests often reward answer matching without requiring a causal, evidence-linked reasoning trace in the document. We propose the 'Fish-in-the-Ocean' (FITO) paradigm, which requires models to construct explicit cross-modal evidence chains within native scientific documents. To operationalize FITO, we build SIN-Data, a scien...Votes: 0GitHub stars: 6
- Single Image Iterative Subject GenerationPersonalize image generation and editing from a single reference image through inference-time LoRA optimization. Iteratively update model parameters based on visual similarity scores without training encoders or fine-tuning on multiple images.Votes: 0GitHub stars: 6
- Single Matrix LoraReplace LoRA's two-matrix decomposition with a single learnable matrix (AA⊤) to eliminate scale imbalances and improve training stability. Reduces parameters by ~50% while maintaining or exceeding LoRA performance.Votes: 0GitHub stars: 6
- Skill Rl Recursive DistillationImprove agent performance by autonomously distilling behavioral patterns from trajectories into reusable skills, then using these skills to guide future decisions. Achieves 89.9% success on ALFWorld through differential processing of success vs failure episodes and dynamic skill library evolution.Votes: 0GitHub stars: 6
- Sliding Window Attention AdaptationAdapt full-attention language models to sliding window attention without expensive retraining. Combine five synergistic strategies (full decode, sink tokens, interleaved layers, chain-of-thought, fine-tuning) achieving 30-100% speedups while maintaining 90-100% accuracy.Votes: 0GitHub stars: 6