メニュー
このリポジトリの skills
SkillsMP は ADu2021/skillXiv から 1,228 件の skill を収集しています。skill を開くとソースと詳細を確認できます。
ADu2021/skillXiv収集済み skill 1,228 件中 28 件を表示しています。
Break through supervised fine-tuning saturation by mixing logits from weaker model checkpoints into strong model training targets. Amplifies hard negatives that strong models have already suppressed, enabling continued learning after standard training…
原文の言語: 英語
Enable safe and efficient AI agent interactions with websites via declarative HTML extensions—define agent-executable tools and context using <tool> and <context> tags instead of relying on brittle UI inference.
原文の言語: 英語
Create principle-guided reward models for web automation agents that evaluate reasoning process quality rather than just outcomes. Implement domain-specific principles (HTML understanding, interaction patterns, state tracking) to guide agent behavior in web…
原文の言語: 英語
Optimize open-source LLM web agent training through systematic analysis of supervised fine-tuning vs. reinforcement learning trade-offs. Achieve 45% lower compute cost by branching into RL at strategic SFT checkpoints.
原文の言語: 英語
Enable web agents to improve over time by curating episodic memory from navigation trajectories and dynamically injecting task-specific guidance at runtime—no retraining required, persistent improvement across sessions.
原文の言語: 英語
Bridge deterministic web code and generative LLMs via hybrid world models. State and physics defined by TypeScript code, LLMs generate narrative/aesthetics on top. Uses typed interfaces, deterministic hashing, graceful degradation—enabling scalable…
原文の言語: 英語
Systematically train 8B web agents to solve complex information-seeking tasks through model-based exploration and long-to-short query evolution, achieving state-of-the-art performance via SFT+RL training pipeline with progressive context expansion to 128K…
原文の言語: 英語
Training platform with thousands of realistic web navigation tasks for developing visual web agents, supporting scalable training and evaluation of agents that can generalize to arbitrary websites.
原文の言語: 英語
Enable autonomous web agents to navigate partially observable environments through action-aware tree search. Handle destructive actions via snapshot validation, implement speculative backtracking with parallel tabs, and dynamically prioritize actions based on…
原文の言語: 英語
Develops multimodal research agents that combine visual and textual reasoning for complex information-seeking tasks, using synthetic training trajectories and reinforcement learning.
原文の言語: 英語
Train autoregressive world models on 1M+ real web interactions for accurate browser state prediction. Enables agent training with 100× more data than prior approaches, achieving GPT-4o comparable performance with format flexibility and cross-domain…
原文の言語: 英語
Improve downstream task performance by increasing weight decay during pretraining (0.3-1.0 vs. default 0.1), enabling better model plasticity and representation structure.
原文の言語: 英語
Research contribution advancing agent and reasoning capabilities through novel approaches to model development, training, and evaluation.
原文の言語: 英語
Dynamically fork sub-agents at any step based on task requirements instead of using fixed agent counts. Linearize hierarchical trajectories into unified sequences for GRPO training. Demonstrates 6.36x more sub-agents than baselines via learned orchestration.
原文の言語: 英語
Train Vision-Language-Action models for robotic control through world model simulation without real-world interaction—using pixel-based world models aligned with VLA features to enable self-correction and robust policy optimization.
原文の言語: 英語
Accelerates iterative world model inference by classifying tokens by temporal curvature (predictability) and applying differentiated caching: stable tokens reused, linear tokens extrapolated, chaotic tokens updated. Achieves 3.7x speedup with 98% rollout…
原文の言語: 英語
Improve long-horizon world model fidelity using RL with clip-level rollouts and complementary reward functions for action accuracy and visual quality. Breaks computational constraints by evaluating candidate clips incrementally rather than full sequences,…
原文の言語: 英語
Quantify confidence in video generation by estimating latent-space uncertainty and mapping to interpretable heatmaps. Detect untrustworthy regions in generated frames for robot planning and policy evaluation—critical when video hallucinations could cause…
原文の言語: 英語
Build unified world models using flow-based video generation architecture that handles Text2World, Image2World, and Video2World in a single model, trained on 200M video clips with RL post-training for improved instruction-following and video quality.
原文の言語: 英語
Derives closed-form optimal linear blockwise transforms combining fixed Hadamard matrices with data-dependent components from second-order statistics, providing provably near-optimal quantization for both weights and activations with GPU efficiency.
原文の言語: 英語
Systematic evaluation toolkit for assessing large language models across multiple dimensions, enabling comprehensive benchmarking of agent capabilities and comparative analysis of model performance.
原文の言語: 英語
Use soft-prompted transformer architecture for multi-robot learning. Add learnable embodiment-specific prompt embeddings to handle different robot types while maintaining single shared backbone. Scale to 0.9B parameters across 6 simulators and 3 real robots.
原文の言語: 英語
Reduce KV cache memory by 7.7-10x through quantization and rematerialization of input activations instead of caching Keys and Values, trading recomputation for memory efficiency.
原文の言語: 英語
MoE-enhanced YOLOv9-Tiny using lightweight routers to adaptively weight specialized expert outputs at each feature resolution, improving detection quality while maintaining end-to-end differentiability. Deploy for efficient multi-scale object detection with…
原文の言語: 英語
Build scalable LLM agent frameworks with automated generation of tools, prompts, and configurations, plus continuous optimization through experience accumulation and reinforcement learning—achieving 71.47% on WebWalkerQA and 72.8% on GAIA.
原文の言語: 英語
Unified text-image token processing in a compact 6B-parameter transformer enabling sub-second inference on enterprise GPUs through hierarchical distillation and single-stream architecture. Use when generating high-quality images with tight latency budgets or…
原文の言語: 英語
Generate diverse human motions from text descriptions using million-scale datasets and wavelet-enhanced quantization. Achieves state-of-the-art zero-shot generalization on out-of-domain motions, compositional descriptions, and complex choreography through…
原文の言語: 英語
Reduce token count by 15-40% at inference through context-adaptive compression, merging frequent token sequences into hypertokens using online Lempel-Ziv-Welch compression without retraining entire models.
原文の言語: 英語