菜单
SkillsMP 已收集 ADu2021/skillXiv 中的 1,228 个 Skill。打开任一 Skill 可查看来源和详情。
已展示 40 / 1,228 个已收集 Skill。
Convert arXiv papers into ready-to-use agent skills using category-aware extraction. First classifies the paper into one or more of 11 research categories, then applies a specialized extraction pipeline for each category — because different types of papers…
原文语言：英语
Establish regret bounds for behavior cloning with discretized actions combining statistical error and quantization error terms. Prove smoothness requirements for safe quantizer design, show that learning-based quantizers fail these requirements, and propose…
原文语言：英语
Dynamically allocate LoRA ranks per-layer during fine-tuning instead of using fixed uniform ranks. Learn optimal rank for each layer and subject via variational framework with discretized exponential distribution, reducing memory footprint while maintaining…
原文语言：英语
Adapt general LLMs to specialized manufacturing domains via domain-adaptive pretraining on open-access journals and visual instruction tuning. Extract 50M tokens and 24K images from peer-reviewed papers, achieve >90% accuracy on domain knowledge tasks, and…
原文语言：英语
Future intelligence explosions will be plural, social, and entangled with humanity through distributed collaborative systems rather than singular superintelligence. Intelligence is inherently social, demanding infrastructure matching agent development;…
原文语言：英语
Build taxonomy-aware audio-text pretraining systems for species recognition from animal vocalizations. Train contrastive models that augment text prompts with hierarchical taxonomic structure (scientific/common names, phylogenetic sequences), evaluate on…
原文语言：英语
Address hallucinations in LLM QA over black-box knowledge graphs using evidence-driven retrieval. Formalize Optimal Informative Subgraph Retrieval and employ bubble expansion to discover candidate evidence graphs, achieving state-of-the-art multi-hop QA…
原文语言：英语
Coordinate multiple LLM agents via CAID framework: centralized task delegation, asynchronous execution in isolated git worktrees, structured integration through git merges. Branch-and-merge with worktree isolation yields +26.7% absolute improvement on…
原文语言：英语
Craft stealthy vehicle appearances that fool detectors by formulating attacks as conditional image editing. Apply image-level stylization (match surroundings) and scene-level strategies (match semantic concepts), achieve 38% AP50 reduction with 85%+ human…
原文语言：英语
Comprehensive recipe for RL-training tool-using agents spanning reward design, data synthesis, model scaling, and algorithm selection. Seven ranked findings: scale-dependent rewards (curriculum for 1.5B–3B; dense for 7B), semi-sparse 'Macro' rewards balance…
原文语言：英语
Enable spatially adaptive Gaussian allocation in 3D Gaussian Splatting without iterative optimization. Reduces primitive count by 70-90% while maintaining reconstruction quality through learned densification score prediction.
原文语言：英语
Introduce Quasicryth, a text compressor using Fibonacci quasicrystal tilings for phrase-level compression. Prove that aperiodic structures never structurally collapse at depth, enabling compression at arbitrary hierarchy levels. Bridge quasicrystal…
原文语言：英语
Replace self-attention world models with reaction-diffusion PDEs as the predictive substrate. Demonstrate that aperiodic PDE dynamics achieve superior multi-step rollout stability and inherent error correction through Laplacian diffusion smoothing, while…
原文语言：英语
Unify discrete diffusion for language by replacing token-wise uniform masking with generalized noising via rate matrices and snapshot latents, enabling semantic-aware forward processes. Demonstrates 1.16 BPC on Text8 and 7.65 perplexity on OpenWebText,…
原文语言：英语
Replace traditional VAE latent spaces with frozen geometric foundation model encoders (e.g., Depth Anything 3) as diffusion latent space. Leverage strong cross-view geometric correspondences for multi-view consistency. Use cascaded generation up to optimal…
原文语言：英语
Enforce semantic compatibility constraints directly into instance construction for 3D object detection. Uses MLLM-driven semantic grouping to partition object vocabulary into plausible cross-view category equivalence clusters, preventing geometry-driven…
原文语言：英语
Extend visual reasoning to spatial-temporal sequences via two-agent reasoning+summary pipeline with ST-GRPO (temporal alignment) and J-GRPO (evaluative robustness) algorithms. Achieves +8.1% on image and +6.9% on video benchmarks through autonomous data…
原文语言：英语
Integrate agentic tool interaction (Lean4 compiler, syntax checkers) with curriculum-based RL for formal reasoning. Replace standard importance sampling with Hierarchical Importance Sampling Policy Optimization (HisPO): sequence-level masking removes…
原文语言：英语
Add tool-calling interface for on-demand high-resolution crop retrieval, enabling VLMs to first observe low-resolution global view then selectively request detailed crops. Achieves 80.3% of full-res performance (vs 80.46%) with only 36% of visual tokens,…
原文语言：英语
Constrain video GRPO policy updates to stay within pre-trained model's data manifold using dual-control exploration. Implement precise manifold-aware SDE with logarithmic noise variance correction (captures geometric signal decay standard methods miss). Apply…
原文语言：英语
Enhance diffusion language model performance on long-context tasks by embedding simulated denoising into training via bi-level optimization. Fast weights capture local trajectory experience; base model optimized with accumulated parametric memory. Achieves…
原文语言：英语
Identify three ranked findings on multi-task SFT: (1) heterogeneous overfitting—sub-datasets peak at different training points (contradicts uniform duration practice); (2) parameter divergence—excluding 1/10 of data shifts optimal points 0.91 epochs for…
原文语言：英语
Evaluate world models on faithful interactive response capability through three hierarchical interaction levels (single object, localized, multi-object effects) and four complementary metrics measuring video quality, controllability, and physical…
原文语言：英语
Replace live web API-dependent research with offline corpus-based trajectory synthesis. Decouples answer-guided document retrieval (10K gold + 15M FineWeb) from synthesis via local search engine, eliminating $5,760 Serper costs while enabling reproducible,…
原文语言：英语
Enhance VLM spatial grounding by enforcing explicit intermediate spatial reasoning before text generation. Generate segmentation and depth tokens as perception pathways, anchoring responses in 2D and 3D geometric reasoning for improved referring expressions…
原文语言：英语
Achieve high-accuracy agentic post-training with 4x fewer rollout turns and 5.5x less wall-clock time than end-to-end RL. Identify informative intermediate turns via pivot filtering and use verifier-based functional rewards for precise credit assignment.
原文语言：英语
Eliminate hallucination via four-stage progressive training: multilingual adaptation → English dialogue SFT → bilingual SFT → GRPO alignment. Achieve 0.0% hallucination rate for encoder-decoder models using structured citation markers and knowledge-source…
原文语言：英语
Enable LLM agents to autonomously improve on research-code tasks through reflective learning from execution trajectories. Distill recurring failure patterns into actionable heuristics applied via targeted prompt edits, improving performance 3.51%-4.89% while…
原文语言：英语
Analyze reinforcement learning with verifiable rewards using signed log-probability differences to identify reasoning-critical tokens. Reveals that RLVR updates concentrate on low-probability tokens, enabling test-time amplification and training-time…
原文语言：英语
Bridge the modality gap between language reasoning and low-level robot actions through two-stage alignment training. Use RL with action-accuracy rewards to ground linguistic reasoning in precise motor control, achieving 17.5%-106.6% improvements over SFT…
原文语言：英语
Train offline safe RL agents using Hamilton-Jacobi reachability principles to learn feasibility-gated policies. Combine reward and safety critics with flow-matching teacher policies, distill to one-step actors, and calibrate safety thresholds via conformal…
原文语言：英语
Route queries across frontier models using two-stage system: graph-based task discovery identifies ~332 latent task types via semantic similarity + preference patterns; MoE with task-specific adapters estimates quality for candidate models. Achieves <50%…
原文语言：英语
Optimize adapter parameter efficiency at scale by decomposing row-wise norm computation into base/cross/BA components (15× memory reduction) and fusing kernel operations. Achieves 1.5–2.0× inference speedup with 77 GB peak VRAM reduction across 8–32B…
原文语言：英语
Achieve post-hoc debiasing of frozen vision-language models by operating in sparse autoencoder latent space. Identify and modulate bias-relevant neurons with neuron-level precision while preserving task-relevant features, requiring no task-specific…
原文语言：英语
Enable agents to navigate toward sound-emitting objects in continuous 3D spaces with dynamic audio (intermittent sounds, silent periods). Integrate memory-augmented goal descriptors with binaural audio processing and self-motion cues to maintain goal…
原文语言：英语
Detect speech deepfakes by decomposing features into speaker, artifact, and context subspaces—nulling speaker information via PCA projection to isolate artifact patterns. Train minimal logistic regression classifier on orthogonally-projected representations,…
原文语言：英语
Inject spatial understanding into VLMs via language-guided multi-turn Chain-of-Thought reasoning over hierarchical spatial knowledge (pixel→object→scene). Implement dual-channel attention mechanism preserving pre-trained vision features while progressively…
原文语言：英语
Replace multi-stream modality-specific pathways with a unified Transformer backbone processing text, video, and audio tokens in shared sequence via self-attention. Achieves superior visual quality (4.80 vs 4.76), 75% better speech clarity (14.6% WER vs…
原文语言：英语
Automate conversion of 630M+ heterogeneous GitHub repositories into standardized Model Context Protocol (MCP) services via hierarchical multi-agent system. Achieves 68.4% success rate after three repair cycles, 210s per repository versus 1589s manual;…
原文语言：英语
Discover that generative models and vision encoders share an underlying approximately Gaussian latent space (UNE). Enable controllable image editing by operating on linear directions in diffusion noise space, revealing that semantic information is present…
原文语言：英语