All authors
Claude Skills by ADu2021
github.com/ADu20211,227 skills5 installs2,395 views
- Think At Hard Selective RefinementReduce reasoning model inference cost by selectively applying latent iterations—use a lightweight neural decider to identify hard tokens and refine only those with focused LoRA modules, achieving 94% token exemption with 8-11% accuracy gain.Votes: 0GitHub stars: 6
- Think Right Reasoning Allocation CalibrationDynamically allocate reasoning budgets per-task: 36.8% length reduction while improving accuracy 8.4% by learning which problems warrant deep reasoning vs. quick answers. Use when optimizing reasoning efficiency across variable-difficulty problems.Votes: 0GitHub stars: 6
- Think Router Hybrid ReasoningRoute reasoning between discrete token space (when uncertain) and latent soft embeddings (when confident). Use maximum next-token probability as a routing threshold to dynamically select the reasoning space, improving accuracy under latent reasoning while reducing computational cost through selective discrete sampling.Votes: 0GitHub stars: 6
- Thinkdial Reasoning Effort ControlControl LLM reasoning effort through discrete modes (High/Medium/Low) using budget-aware supervised fine-tuning and adaptive reward shaping, enabling compression-performance tradeoffs.Votes: 0GitHub stars: 6
- Thinking Map Spatial AgentsImprove agent reasoning for spatial tasks by augmenting LLMs with map tools and parallel test-time exploration. Framework uses reinforcement learning to train agents to iteratively refine hypotheses using map feedback. Parallel exploration enables agents to test multiple candidate locations before committing to answers. Introduces MAPBench benchmark for evaluating spatial reasoning in image geolocalization tasks.Votes: 0GitHub stars: 6
- Thinking To RecallDemonstrates that chain-of-thought reasoning improves LLM factual retrieval through computational buffering and self-priming. Improves single-hop factual accuracy by enabling models to generate contextual bridge facts before recalling answers.Votes: 0GitHub stars: 6
- Thinking With Video Multimodal ReasoningLeverage video generation models as unified multimodal reasoning engines that bridge text and vision by embedding reasoning as dynamic visual processes, enabling models to tackle both spatial puzzles and mathematical problems within a single temporal framework.Votes: 0GitHub stars: 6
- Thinkmorph Interleaved Multimodal ReasoningTrain unified models to generate interleaved reasoning steps combining text and image thoughts as complementary modalities, enabling adaptive behavior like autonomous mode-switching and superior test-time scaling for vision-centric tasks without requiring external guidance.Votes: 0GitHub stars: 6
- Thinkrl Edit Thinking In Reinforcement Learning FoAdvanced reasoning approach for optimizing inference efficiency through meta-cognitive planning, enabling agents to make better decisions with reduced computational overhead.Votes: 0GitHub stars: 6
- Thinksafe Safety AlignmentAlign reasoning models to be safe without external supervision by prepending refusal instructions to harmful queries and training on self-generated safe responses. Unlocks latent safety knowledge within the model's native distribution.Votes: 0GitHub stars: 6
- Thinksound Audio Generation ReasoningGenerates high-quality audio through three-stage CoT reasoning pipeline: foundational foley synthesis, object-focused refinement, and instruction-guided editing. Uses fine-tuned VideoLLaMA for reasoning and flow-matching audio foundation model. Apply for professional audio design workflows or video-to-audio applications.Votes: 0GitHub stars: 6
- Thor Tool Hierarchical Optimization RlTrain LLMs for tool-integrated mathematical reasoning via hierarchical RL combining episode-level problem correctness with step-level code execution quality. Addresses sparse rewards in reasoning chains through TIRGen data construction and self-correcting inference with dynamic backtracking.Votes: 0GitHub stars: 6
- Threadweaver Parallel ReasoningEnable parallel reasoning threads on standard autoregressive inference engines without modifications to position embeddings or KV cache. ThreadWeaver achieves 1.53× speedup while maintaining chain-of-thought quality—ideal when you need faster reasoning without special hardware.Votes: 0GitHub stars: 6
- Tiadar Diffusion Autoregressive HybridCombine diffusion-based parallel drafting with autoregressive sampling in a single forward pass using structured attention masks—achieving 5x+ token throughput while maintaining autoregressive-level output quality through hybrid generation.Votes: 0GitHub stars: 6
- Timebill InferenceGuarantee LLM inference completes within time budgets via response length prediction, execution time estimation, and adaptive KV cache eviction. Three-stage pipeline predicts response length, estimates end-to-end time with 1.22% accuracy, adjusts cache eviction ratio—enabling time-critical deployment in robotics and autonomous systems.Votes: 0GitHub stars: 6
- Timeseries Scientist Agentic ForecastingAutomate univariate time series forecasting through a four-agent system orchestrating preprocessing, model selection, validation, and reporting. Use when reducing manual effort in forecasting pipelines and improving reproducibility.Votes: 0GitHub stars: 6
- Tir Bench Visual Tool ReasoningEvaluate multimodal models on agentic visual reasoning through 13 diverse tasks requiring novel tool use for image processing and manipulation in chain-of-thought, revealing that strong performance requires genuine thinking-with-images capabilities.Votes: 0GitHub stars: 6
- Tldr Thinking ReweightingCompress reasoning models by dynamically re-weighting short-CoT (System-1) and long-CoT (System-2) training data, achieving 40% token reduction while maintaining accuracy.Votes: 0GitHub stars: 6
- Todoevolve PlanningAutonomously synthesize task-specific agent planning architectures by optimizing for correctness, stability, and efficiency via impedance-guided preference optimization.Votes: 0GitHub stars: 6
- Token Bottleneck Scene DynamicsLearn to compress entire scenes into a single bottleneck token that captures temporal dynamics. Enables efficient visual tracking and robotic manipulation by forcing reconstruction from minimal target hints, achieving superior performance with training costs comparable to standard autoencoders.Votes: 0GitHub stars: 6
- Token Order PredictionImprove LM performance with token order prediction (TOP) auxiliary loss using learning-to-rank instead of exact multi-token prediction, achieving gains across math, code, and NLP tasksVotes: 0GitHub stars: 6
- Token Sparse Attention Long ContextDynamically select important tokens at the attention head level, performing dense attention only on selected tokens and scattering results back. Achieves 3.23x attention speedup at 128K context with 1% accuracy loss through layer-wise representation stability analysis.Votes: 0GitHub stars: 6
- Tokenbridge Visual GenerationBuild autoregressive image generators using post-training quantization that bridges continuous VAE tokens with discrete vocabulary modeling. Achieves state-of-the-art visual quality via dimension-wise token prediction without training instability.Votes: 0GitHub stars: 6
- Tool Agent CalibrationThe Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents. From arXiv:2601.07264Votes: 0GitHub stars: 6
- Tool Integrated ReasoningImplements ET-Agent from arXiv:2601.06860Votes: 0GitHub stars: 6
- Tool Integrated Rl Repo SearchTwo-stage post-training framework combining rejection-sampled SFT and RL for LLM-guided repository code search and issue localization.Votes: 0GitHub stars: 6
- Tool Learning LmProve that tool-augmented learning unboundedly scales factual knowledge recall compared to parameter-constrained memorization, enabling efficient knowledge retrieval via external toolsVotes: 0GitHub stars: 6
- Tool Orchestra Coordination8B parameter orchestrator trained with end-to-end RL balancing outcome, efficiency, and user preference rewards to strategically coordinate diverse tools and models. Generate realistic tool-use data via ToolScale synthetic pipeline for verifiable multi-turn scenarios.Votes: 0GitHub stars: 6
- Tool R0 Self Evolving AgentsTool-R0 trains tool-use agents through self-play between Generator and Solver, creating curriculum-like progression without manual task curation.Votes: 0GitHub stars: 6
- Tool Use Training MultilingualEnable non-English language models to reliably generate function calls and tool invocations through continued training on bilingual function-calling datasets. Achieves 28% improvement in parsing accuracy while preserving language understanding.Votes: 0GitHub stars: 6
- Tool Verification ReasoningTool Verification stabilizes self-improving reasoning models by using external tool execution as ground-truth evidence to prevent spurious consensus from becoming reinforced training signals.Votes: 0GitHub stars: 6
- Toolprmbench Evaluating And Advancing ProcessReward-guided search methods have demonstrated strong potential in enhancing tool-using agents by effectively guiding sampling and exploration over complex action spaces. As a core design, those search methods utilize process reward models (PRMs) to provide step-level rewards, enabling more fine-grained monitoring. However, there is a lack of systematic and reliable evaluation benchmarks for PRMs in tool-using settings. In this paper, we introduce ToolPRMBench, a large-scale benchmark specifi...Votes: 0GitHub stars: 6
- Toolrm Outcome Reward Tool CallingSpecialized outcome reward models (1.7B-14B) for evaluating tool-calling performance in LLMs. Addresses the critical gap in reward modeling where general-purpose models miss key signals of effective tool use. Enables better Best-of-N sampling, data filtering, and RL-based policy training through FC-RewardBench evaluation framework.Votes: 0GitHub stars: 6
- Toolsafe Agent SafetyDetects and prevents unsafe tool invocations in LLM agents through proactive step-level guardrails, reducing harmful tool calls by 65% while improving task success rates by 10% against prompt injection attacks.Votes: 0GitHub stars: 6
- Toucan Mcp Tool Agentic DatasetGenerate 1.5M realistic agent training trajectories from 495 real-world MCP servers without human annotation. Use to build tool-agentic training datasets with authentic tool execution, multi-turn conversations, and error handling.Votes: 0GitHub stars: 6
- Toucan Tool Agentic Data SynthesisSynthesize large-scale training data for LLM agents by generating diverse tool-use trajectories from real Model Context Protocol (MCP) environments. A 1.5M-example dataset created via multi-stage pipeline: query generation, quality filtering, trajectory creation with real tool execution, validation, and diversification.Votes: 0GitHub stars: 6
- Tour Planner RlImplements TourPlanner from arXiv:2601.04698Votes: 0GitHub stars: 6
- Toward Efficient Agents Memory Tool Learning AndRecent years have witnessed increasing interest in extending large language models into agentic systems. While the effectiveness of agents has continued to improve, efficiency, which is crucial for real-world deployment, has often been overlooked. This paper therefore investigates efficiency from three core components of agents: memory, tool learning, and planning, considering costs such as latency, tokens, steps, etc. Aimed at conducting comprehensive research addressing the efficiency of th...Votes: 0GitHub stars: 6
- Towards Efficient And Robust Linguistic EmotionLinguistic expressions of emotions such as depression, anxiety, and trauma-related states are pervasive in clinical notes, counseling dialogues, and online mental health communities, and accurate recognition of these emotions is essential for clinical triage, risk assessment, and timely intervention. Although large language models (LLMs) have demonstrated strong generalization ability in emotion analysis tasks, their diagnostic reliability in high-stakes, context-intensive medical settings re...Votes: 0GitHub stars: 6
- Towards Pixel Level Vlm Perception Via Simple PoinImplement techniques from Towards Pixel-Level VLM Perception via Simple Points Prediction. We present SimpleSeg, a strikingly simple yet highly effective approach to endow Multimodal Large Language Models (MLLMs) with native pixel-level perceptionVotes: 0GitHub stars: 6
- Tower Mind Agent BenchmarkEvaluate LLM agent capabilities using tower defense game environment with multimodal observations (pixel, text, structured state). Benchmark reveals critical agent limitations: inadequate planning validation, inflexible decision-making, and inefficient action use. Demonstrates significant performance gap between current LLMs and human experts, providing structured framework for measuring agent planning, adaptation, and hallucination tendencies.Votes: 0GitHub stars: 6
- Tower Plus MultilingualBuild multilingual LLMs that excel at machine translation while preserving general-purpose capabilities through a staged training pipeline combining continued pretraining, SFT, preference optimization, and RL with verifiable rewards.Votes: 0GitHub stars: 6
- Tracealign Alignment Failure AttributionTrace unsafe LLM outputs back to conflicting beliefs in training data using suffix-array matching and Belief Conflict Index.Votes: 0GitHub stars: 6
- Training Free Group Relative PolicyImprove LLM performance at test time through in-context learning and experience libraries, eliminating the need for parameter updates while maintaining competitive results.Votes: 0GitHub stars: 6
- Training Free GrpoImprove LLM outputs without parameter updates using learned token priors that guide inference. Trigger: optimize agent behavior in deployment without model retraining or fine-tuning.Votes: 0GitHub stars: 6
- Training X Ray Vision AmodalInfer complete object structure despite occlusion using multi-camera video. Enables training models to predict hidden object appearance by combining temporal and spatial context from multiple viewpoints.Votes: 0GitHub stars: 6
- Trajectory Selection ReasoningSelect best reasoning trajectories from multiple samples using step-level scoring from a 0.6B lightweight verifier that exploits hidden states, outperforming external reward models by 4-12% without massive annotations.Votes: 0GitHub stars: 6
- Trapo Semi Supervised RlBridge labeled and unlabeled data through trajectory similarity in reinforcement learning. Select reliable unlabeled samples by comparing pass-rate evolution trajectories against labeled data. Achieve 42.6% accuracy with 1K labeled + 3K unlabeled samples, surpassing fully-supervised training on 45K labels with 10% annotation budget.Votes: 0GitHub stars: 6
- Tree Search Llm Agent RlTrain LLM agents via tree-search rollout sampling and step-wise advantage estimation. Achieve 1.5x more rollouts within fixed token budgets and implicit step-level preference learning through dual-level advantage computation on tree structures.Votes: 0GitHub stars: 6
- Treecua Gui AutomationScale GUI automation by organizing trajectories into tree structures for reuse and branching exploration, reducing data cost while maximizing step-level diversity through adaptive topology.Votes: 0GitHub stars: 6