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 40 件を表示しています。
Convert video generation model outputs into executable robotic manipulation by extracting 3D object flow trajectories as an intermediate representation. Enables zero-shot manipulation of diverse object types (rigid, articulated, deformable, granular) without…
原文の言語: 英語
Scale agent learning by synthesizing diverse experiences using reasoning-based models instead of costly real-world rollouts, maintaining replay buffers with both real and synthetic interactions while using adaptive curriculum to focus on challenging tasks.
原文の言語: 英語
Unified system for multi-task video generation combining audio and visual synthesis, demonstrating scalable approaches for content generation that can enhance agent communication capabilities.
原文の言語: 英語
DrivingGen: A Comprehensive Benchmark for Generative Video World Models in Autonomous Driving. From arXiv:2601.01528
原文の言語: 英語
Implement techniques from DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal. Despite the growing adoption of large language models (LLMs) in scientific research workflows, automated support for academic rebuttal, a crucial…
原文の言語: 英語
Improve LLM reasoning by promoting diversity at both trajectory and token levels simultaneously. Global (trajectory) scale rewards distinct correct solutions; local (token) scale applies entropy regularization per decision point. Dual-scale approach couples…
原文の言語: 英語
Implement techniques from DSGym: A Holistic Framework for Evaluating and Training Data Science Agents. Data science agents promise to accelerate discovery and insight-generation by turning data into executable analyses and findings
原文の言語: 英語
Optimize disaggregated prefill-decoding LLM serving for multi-turn (agentic) workloads by introducing dual-path KV-cache loading. Traditional approach loads all KV-cache to prefill engines, saturating their storage network. DualPath loads to decoding engines…
原文の言語: 英語
Generate SVGs through simultaneous image and SVG token generation with internal visual guidance. DuetSVG overcomes text-only limitations by leveraging visual predictions to enhance SVG coherence—ideal when visual quality and geometric correctness matter.
原文の言語: 英語
Implement dual preference optimization to generate self-supervised feedback without manual annotation by decomposing tasks into known/unknown components and reconstructing hidden information from model outputs.
原文の言語: 英語
Accelerate test-time scaling for diffusion language models by identifying inconsistent tokens, selectively remask and regenerate only uncertain tokens, and aggregate across samples via voting. Achieve 5.5-22× speedup over standard iterative sampling with 6-8%…
原文の言語: 英語
Automatically construct compact, diverse action spaces for LLM reasoning through corpus-based estimation and submodular optimization—enabling efficient decision-making without manual specification or expensive exhaustive search.
原文の言語: 英語
Implement hierarchical language modeling that compresses variable-length token sequences into high-capacity semantic concepts, achieving +2.69% benchmark improvements while reducing inference FLOPs by reallocating compute to concept-level reasoning. Use for…
原文の言語: 英語
Minimal modification to SFT that dynamically rescales objectives by token probability. Rectifies implicit reward structure to improve generalization comparable to RL while maintaining SFT simplicity.
原文の言語: 英語
Sparse 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.
原文の言語: 英語
Dynamic token pruning framework for VLMs that adapts compression to scene complexity through single-pass selection. Removes 92.6% of visual tokens while maintaining performance and enabling superior fine-tuning.
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
Extends text embedding models to perform listwise reranking through continued training on ranking objectives. Constructs listwise prompts from queries and top-K candidates, leveraging pseudo-relevance feedback while maintaining embedding model efficiency.…
原文の言語: 英語
Monitor token-wise entropy to adaptively allocate compute during inference. Branch into multiple paths at high-entropy tokens, reducing token generation by up to 65% while improving accuracy by up to 37% on reasoning tasks.
原文の言語: 英語
Train efficient planners for long-horizon agent tasks using homologous consensus filtering to generate synthetic plans from strong LLMs and rule-based RL with executor capability rewards. Reduces training cost by 8x while maintaining state-of-the-art…
原文の言語: 英語
Enable image editors to handle complex instructions through iterative critique and refinement cycles. A multimodal LLM critiques editing results, reasons about improvements, and refines instructions until satisfactory output—ideal for instruction-following…
原文の言語: 英語
Systematically optimize agent system costs via empirical analysis of LLM, planning, memory, and search components achieving 28.4% cost reduction.
原文の言語: 英語
Systematically convert pretrained autoregressive models into efficient diffusion language models via block-wise attention and position-dependent masking. Efficient-DLM family (1.5B/4B/8B) maintains comparable accuracy to standard AR models while delivering…
原文の言語: 英語
Achieve 10× higher decoding throughput on long prompts by replacing 50% of cross-attention layers with gated memory units (GMUs) combining SSMs and attention. Maintains reasoning capability while reducing memory I/O bottleneck from O(d_kv·N) to O(d_h).
原文の言語: 英語
Framework for efficient machine unlearning that reformulates forgetting as inverse learning. Achieves significant computational speedup by replacing expensive Hessian operations with gradient-based optimization, enabling privacy-preserving model updates.
原文の言語: 英語
Comprehensive survey of techniques for optimizing large reasoning models. Covers single-model optimization and multi-model collaboration approaches to reduce reasoning path length without sacrificing capability.
原文の言語: 英語
Enable autonomous embodied agents to function in 3D communities with structured memory systems. Combines semantic memory (scene graphs, knowledge graphs) and episodic memory (spatiotemporal experiences) for social intelligence and multi-agent coordination.
原文の言語: 英語
Improve multimodal embeddings through RL-optimized reasoning that grounds evidence in retrievable visual cues. Frozen embedder provides stable rewards while reasoner generates evidential traceability CoT with text keywords, bounding boxes, and key frames.
原文の言語: 英語
Accelerate LLM decoding by predicting multiple future tokens simultaneously using mask-token probing in embedding space, without retraining or auxiliary models.
原文の言語: 英語
Bridge vision-to-action gap using pointing as unified intermediate representation, enabling 56.2% success on manipulation tasks without task-specific fine-tuning.
原文の言語: 英語
Discover hierarchical temporal abstractions within autoregressive models via internal RL, enabling efficient exploration of sparse-reward tasks. Metacontroller learns abstract action sequences modifying residual streams, switching gates enable quasi-binary…
原文の言語: 英語
Build a single model handling multimodal understanding, generation, and editing tasks efficiently through token compression and intelligent component sharing. EMMA-4B surpasses larger models while reducing computational burden—ideal when you need unified…
原文の言語: 英語
Improve exploration in LLM-based agents through external memory-augmented RL with hybrid on/off-policy training. Agents generate exploration 'tips' (self-reflections) after trajectories, storing them in memory. During rollouts, policy samples between standard…
原文の言語: 英語
Choose optimal pretraining strategy for text encoders: pure MLM, pure CLM, or biphasic CLM-then-MLM training, with empirical guidance on performance across downstream tasks.
原文の言語: 英語
Implement techniques from Endless Terminals: Scaling RL Environments for Terminal Agents. Environments are the bottleneck for self-improving agents
原文の言語: 英語
Enable step-by-step reasoning in diffusion models through iterative latent state refinement. Condition diffusion on evolving thought states across multiple reasoning steps, grounded with textual supervision to prevent drift.
原文の言語: 英語
Enhanced language model pre-training methodology improving linguistic competence across languages, strengthening foundational capabilities for multilingual agent systems.
原文の言語: 英語
Train LLMs to disambiguate tool calls in enterprise settings where multiple similar APIs exist and parameters are incomplete. Generates synthetic multi-turn dialogues with realistic ambiguity to improve tool selection accuracy by 27+ percentage points.
原文の言語: 英語
Technique for efficient model adaptation that mitigates catastrophic forgetting during fine-tuning, enabling agents to learn new tasks while preserving existing capabilities.
原文の言語: 英語
One-line code modification augmenting RL advantage function with clipped entropy term to encourage exploratory reasoning chains while maintaining optimization stability.
原文の言語: 英語