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。
Overturn the assumption that scaling foundation models improves RNA structure prediction by understanding why they fail out-of-distribution. Includes structure-aware deduplication revealing 33-fold residual redundancy in prior benchmarks, out-of-distribution…
原文の言語: 英語
A single insight reframes optical flow in degraded video as correspondence matching via diffusion features: restoration models naturally encode degradation patterns while preserving geometry. Add temporal reasoning via cross-frame attention to enable…
原文の言語: 英語
Evaluate data agents on realistic multi-database queries across 54 tasks spanning 12 datasets, 9 domains, and 4 DBMS systems. Reveals frontier models achieve only 38% pass@1 accuracy, with 85% of failures from incorrect planning rather than data selection.…
原文の言語: 英語
Evaluate web agents on tasks grounded in first-person video perception with Ego2Web benchmark. Bridges egocentric video understanding and web agent execution across e-commerce and knowledge lookup domains. Includes Ego2WebJudge LLM-based evaluator achieving…
原文の言語: 英語
Navigate LLM agent workflow design by understanding the taxonomy of static vs dynamic methods and the dimensions that organize them. Agentic Computation Graphs (ACGs) framework distinguishes when structure is determined (before vs during execution), which…
原文の言語: 英語
Replace autoregressive token-by-token OCR decoding with block-wise diffusion decoding to achieve 3.2× speedup while maintaining 99.9% accuracy. Works best for document layout parsing where parallel generation is feasible. Trigger: When optimizing OCR systems…
原文の言語: 英語
Empirical analysis revealing that LLMs produce post-conventional moral reasoning (Kohlberg Stages 5-6) regardless of size or prompting—inverse of human developmental patterns (Stage 4 dominant). Finds moral ventriloquism: models acquire rhetorical conventions…
原文の言語: 英語
Evaluate multi-reference image generation fidelity using MultiBind's dimension-wise confusion framework. Detects cross-subject attribute errors that holistic metrics (FID, CLIP) miss, including drift (degradation), swap (permutation), dominance…
原文の言語: 英語
A single insight eliminates multi-view requirements for novel-view synthesis: monocular depth acts as a training-time geometric scaffold to generate synthetic view pairs from unpaired internet images, but can be discarded at inference. This reframes the…
原文の言語: 英語
Defines Personalized Streaming Video Understanding (PSVU) as a new task bridging static image personalization and video intelligence. PEARL-Bench (132 videos, 2173 annotations) establishes founding experiments. PEARL framework provides training-free…
原文の言語: 英語
Replace uniform token-level advantages with perception-exploration gating that weights tokens by visual grounding strength. Adds 3.67 points to geometry reasoning and 5.32 to few-shot classification with <1% compute overhead. Works best for multimodal CoT…
原文の言語: 英語
A single insight reframes sim-to-real video generation as decoupled structure-and-appearance transformation: use geometric conditioning to preserve structural fidelity while allowing free appearance transformation. This enables IC-LoRA training on…
原文の言語: 英語
Understand the policy challenges of governing autonomous AI agents under existing frameworks like the EU AI Act. Identifies three primary governance failures: performance failures during execution, misuse risks from malicious deployment, and economic…
原文の言語: 英語
Add trajectory-level temporal authorization to stateless execution gates by maintaining a semantic centroid of agent behavioral profiles with exponential moving average risk accumulation. Improves F1 from 0.9756 to 1.0 and reduces false positives from 5% to…
原文の言語: 英語
Replace standard VICReg invariance loss with graph-weighted learnable adjacency matrix to enable self-supervised no-reference image quality assessment without human labels. Improves SRCC by +0.017 (2% relative) on six-dataset average and shows stronger…
原文の言語: 英語
Replace dense voxel tokenization with sparse 3D VQ-VAE to reduce token counts by 70% in multimodal 3D understanding. Enables efficient articulated asset decomposition for physics-based simulation. Works best for 3D generation tasks constrained by token…
原文の言語: 英語
Replace fixed full-capacity slot initialization with progressive curriculum-based slot expansion to reduce over-fragmentation in video object-centric learning. Improves FG-ARI by +6.8 on YouTube-VIS and +8.3 on MOVi-C. Use when training slot attention models…
原文の言語: 英語
Analyzes how Reinforcement Learning from Verification Rewards (RLVR) improves reasoning by examining token-level probability distributions. Finds that >83% of token positions exhibit near-zero divergence—RL operates through sparse, targeted refinements.…
原文の言語: 英語
Accelerate agentic multimodal LLMs via speculative execution without sacrificing accuracy. Use a lightweight tool-free MLLM to predict the main model's decisions and pre-compute tool calls before the main model confirms them. Cognitive gating enables the…
原文の言語: 英語
Design modular AI agent systems that work across multiple interaction protocols (A2A, AG-UI, A2UI, UCP, AP2) without protocol-specific rewiring. STEM Agent uses biological pluripotency as a metaphor: a generic core differentiates into specialized handlers,…
原文の言語: 英語
Replace single-pathway JEPA with a dual-temporal architecture combining dense frame sampling (fine-grained dynamics) and uniformly-sampled VLM guidance (semantic coherence) to improve egocentric trajectory prediction by 14-27% on ADE/accuracy metrics.…
原文の言語: 英語
Improve dense trajectory generation by replacing absolute coordinate encoding with grid-anchor offset encoding (reduces location variance 90%→10%), adding spatiotemporal consistency regularizers to VAE (30-40× improvement in 81-frame prediction), and using…
原文の言語: 英語
Swap fixed entailment loss with uncertainty-guided piecewise-continuous formulation to improve part-to-whole compositional alignment in hyperbolic vision-language models by +3.0-3.1% on zero-shot classification. Use when training hyperbolic VLMs on…
原文の言語: 英語
Replace classifier-free guidance and KL-based regularization in flow matching with velocity-based MSE regularization and GRPO for joint text-image optimization. Achieves 0.8381 TextAlign and 0.90 GenEval without CFG overhead. Works best for multimodal…
原文の言語: 英語
Optimize vision-language model inference by sparsifying the interactions between vision and language tokens instead of compressing images. Uses a dynamic policy to allocate visual computation per sample based on complexity, enabling a universal network across…
原文の言語: 英語
Replace monolithic VLA single-pathway decision-making with a decomposed System-2/System-1 architecture where a pretrained VLM planner identifies targets as visual prompts (crosshairs, bounding boxes) and a VLA controller executes on grounded observations,…
原文の言語: 英語
Replace vision-only Video-Action Models with a video-tactile fusion architecture using tactile regularization loss to prevent visual dominance, improving contact-rich manipulation success from baseline to 90% on complex tasks (80% improvement on…
原文の言語: 英語
Build action-conditioned world models with explicit state tracking using WildWorld's 108M+ frames from Monster Hunter: Wilds. Includes data acquisition protocol with skeleton and world state annotations, quality filtering pipeline removing temporal…
原文の言語: 英語
Production LLM systems often rely on separate models for safety and other classification-heavy steps, increasing latency, VRAM footprint, and operational complexity. We instead reuse computation already paid for by the serving LLM: we train lightweight probes…
原文の言語: 英語
The evolution of Large Language Models (LLMs) into autonomous agents has expanded the scope of AI coding from localized code generation to complex, repository-level, and execution-driven problem solving. However, current benchmarks predominantly evaluate code…
原文の言語: 英語
Asymmetric Confidence-aware Error Penalty (ACE) dynamically penalizes overconfident mistakes in RL training, improving reasoning quality without requiring additional computation.
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
Train a single LLM to decompose complex queries into subquestions and integrate retrieved contexts through two-stage supervised and preference-based reinforcement fine-tuning, achieving 7.6% average improvement and matching 685B models with 32B parameters.
原文の言語: 英語
Reduce memory overhead of long-horizon LLM agents by learning task-specific context compression strategies. A learnable compressor adapts by analyzing failure cases, achieving 26-54% memory reduction while preserving 95%+ accuracy, enabling smaller models to…
原文の言語: 英語
Compress agent interaction histories and environment observations through natural language guideline optimization, reducing token usage by 26-54% while preserving 95%+ accuracy. Use for cost/latency reduction in multi-step agent tasks.
原文の言語: 英語
Vision-Language-Action (VLA) models have emerged as essential generalist robot policies for diverse manipulation tasks, conventionally relying on directly translating multimodal inputs into actions via Vision-Language Model (VLM) embeddings. Recent…
原文の言語: 英語
Route queries to specialized reasoning modes (internal reasoning, tool calling, or instant answers) using task-aware routing and Adaptive Policy Optimization to reduce inference costs by 45% while maintaining accuracy.
原文の言語: 英語
Accelerate LLM inference 1.5-2x using a universal draft model that adapts to user data in real-time, handling different target models and tokenizers via online n-gram cache and hybrid distillation.
原文の言語: 英語
Generate adversarial test suites that catch LLM code errors by analyzing constraint differences between correct and incorrect solutions. SAGA framework improves test detection rate 9.55% and verifier accuracy 12.14% by using human bug patterns and multi-input…
原文の言語: 英語
Combines adversarial training with optimal transport constraints enabling deterministic, transport-optimal one-step image generation with FID 2.38 on ImageNet-256. Apply when you need fast generative models without teacher-student distillation complexity.
原文の言語: 英語