Menu
Skills dans ce dépôt
SkillsMP a collecté 1 228 skills depuis ADu2021/skillXiv. Ouvrez un skill pour examiner sa source et ses détails.
ADu2021/skillXivAffichage de 40 skills collectés sur 1 228.
Stabilize RL training on reasoning tasks by performing entropy-guided rollouts from uncertain decision points, avoiding policy collapse and premature convergence. Increases fully correct trajectories on math reasoning while maintaining stable entropy…
Langue du texte source : anglais
Monitor Shannon entropy in LLM token distributions to detect sudden uncertainty spikes, then trigger adaptive prompt consolidation to realign conversation context and improve accuracy by 56.6% and reliability by 35.3%.
Langue du texte source : anglais
Stabilize LLM post-training by constraining global distributional shifts in policy exploration. Entropy Ratio Clipping supplements local clipping mechanisms with global entropy constraints—essential when PPO alone produces unstable gradients and distribution…
Langue du texte source : anglais
Automatically generate diverse, scalable tool-interactive training environments for LLM agents without manual sandbox creation. Uses topic mining and logic modeling to create varied environment architectures with task scenarios, enabling agents to learn…
Langue du texte source : anglais
Systematic evaluation toolkit for assessing large language models across multiple dimensions, enabling comprehensive benchmarking of agent capabilities and comparative analysis of model performance.
Langue du texte source : anglais
Stabilize multi-turn LLM agent training with entropy-regularized policy optimization that prevents exploration-exploitation cascade failures in sparse-reward environments through trajectory-level entropy regulation, historical smoothing, and adaptive…
Langue du texte source : anglais
Transform vision-language models into embodied agents through two stages: learning embodied priors from trajectory-augmented data with LLM reasoning, then online RL with self-summarization and dense rewards for long-horizon tasks.
Langue du texte source : anglais
24-trillion-token web dataset with 12-category taxonomy labels enabling efficient curation of specialized datasets through SQL filtering and small annotation models.
Langue du texte source : anglais
Chunk-based landmark-guided sparse attention enabling 16M-token context windows with 90%+ retrieval accuracy on in-context tasks. Use when processing ultra-long documents where full attention is prohibitive but context selection must be dynamic.
Langue du texte source : anglais
Train autonomous agents to use computers by generating synthetic task experiences and iterating on them, achieving 56.7% success on OSWorld benchmarks through scalable experience-driven optimization. Use when you need agents that autonomously learn complex…
Langue du texte source : anglais
Scale Evolution Strategies to billion-parameter LLMs without backpropagation for superior robustness and stability across diverse models, reward horizons, and evaluation tasks. Outperforms RL methods while eliminating gradient computation overhead.
Langue du texte source : anglais
Generate verifiable synthetic training data (problems + solutions + verification artifacts) through evolutionary synthesis that works across math, code, and agent tasks without task-specific rules.
Langue du texte source : anglais
System for evolving and composing programmatic skills through learning, enabling agents to discover and develop new behavioral capabilities dynamically.
Langue du texte source : anglais
Build unified LLMs supporting both fast standard inference and slow reasoning modes through hybrid attention and adaptive post-training. Combine non-reasoning and reasoning capabilities in a single model with 128K context windows and tool use. Use when you…
Langue du texte source : anglais
Build robust reward models for computer-use agents by processing execution videos with spatiotemporal token pruning (STP+TTP) to remove redundancy while preserving task-relevant UI details. Achieve 84.7% accuracy with adversarial instruction translation.
Langue du texte source : anglais
Improve RLVR training efficiency by selectively replaying trajectories based on correctness and entropy. Medium-difficulty questions and low-entropy solutions are most valuable; selective replay yields +3.5-7.6% improvements.
Langue du texte source : anglais
Improve LLM reasoning efficiency by systematically reusing past rollouts through experience replay. ExGRPO organizes training data by success and diversity, applying a mixed-policy objective that prioritizes high-quality examples while maintaining…
Langue du texte source : anglais
Evaluate AI systems' ability to conduct autonomous research experiments using EXP-Bench, a benchmark for multi-step scientific reasoning and iterative experimental workflows.
Langue du texte source : anglais
Dynamically adapt LLM reasoning strategies at inference time by curating episodic memory of past problem solutions—generate task-specific prompts, tool configs, and control logic for up to 111× cost reduction and 14% accuracy gains.
Langue du texte source : anglais
Improve RL training efficiency by embedding explicit reflection and revision loops. Models generate initial responses, receive feedback, produce self-reflections describing improvements, revise their attempts, and distill successful corrections into the base…
Langue du texte source : anglais
Improve MoE language model efficiency with causal threshold-based routing that eliminates auxiliary losses and enables dynamic per-token computation.
Langue du texte source : anglais
Investigate exploration-exploitation trade-offs in reinforcement learning with verifiable rewards through theoretical analysis and empirical validation. Derive explicit clipping bias bounds, establish policy-entropy shift formulation, and introduce…
Langue du texte source : anglais
Multimodal system for joint audio-video understanding and generation, enhancing agent perception and communication in environments with both audio and visual information.
Langue du texte source : anglais
Unify LLM alignment methods through f-divergence theory. f-GRPO extends GRPO to handle any divergence measure (KL, Jensen-Shannon, Hellinger), enabling tailored alignment objectives. f-HAL combines on-policy and off-policy preference learning to prevent…
Langue du texte source : anglais
Prevent policy collapse onto common solutions during reinforcement learning by applying difficulty-aware focal weighting to gradient contributions, maintaining diversity across solution modes while preserving performance.
Langue du texte source : anglais
F1 is a 4.2B-parameter Vision-Language-Action model that reformulates robotic control as foresight-guided inverse dynamics. Rather than reactive state-to-action mappings, F1 predicts plausible future visual states and derives actions to achieve them, enabling…
Langue du texte source : anglais
Enable extreme 1-2bit quantization of pre-trained LLMs by leveraging complex-valued arithmetic. Convert real-valued linear layers to complex domain losslessly, quantize to fourth roots of unity {±1, ±i}, and apply recursive residual error quantization for…
Langue du texte source : anglais
Achieving human-level performance in Vision-and-Language Navigation (VLN) requires an embodied agent to jointly understand multimodal instructions and visual-spatial context while reasoning over long action sequences. Recent works, such as NavCoT and…
Langue du texte source : anglais
Generates high-quality images directly from pixels using flow-matching-based latent sequences. Transforms images via invertible flows into manageable latent sequences, applies autoregressive modeling, and uses classifier-free guidance. Provides exact…
Langue du texte source : anglais
Identify dominant frequency components in RoPE embeddings to determine which attention dimensions are essential, reducing KV cache by 81% while maintaining performance. Training-free approach integrates with existing compression methods for 2.56x speedup on…
Langue du texte source : anglais
Implements Fast-ThinkAct from arXiv:2601.09708
Langue du texte source : anglais
Identify and measure feedback friction in LLM reasoning tasks where models resist high-quality guidance, discovering that confidence predicts feedback receptiveness and revealing mitigation strategies.
Langue du texte source : anglais
Systematically adapt state-of-the-art distillation methods for T2I generation. Compare sCM (stabilized Consistency Models), MeanFlow, and IMM within unified framework. sCM excels at extreme few-step regimes (52.81% GenEval at 2 steps), MeanFlow achieves…
Langue du texte source : anglais
Demonstrate that adversarial attacks on vision-language models need not target all tokens equally. Entropy-guided attacks identify high-entropy tokens (critical decision points) where perturbations have maximum impact, achieving comparable attack success with…
Langue du texte source : anglais
Research contribution advancing agent and reasoning capabilities through novel approaches to model development, training, and evaluation.
Langue du texte source : anglais
Active learning (AL) has the potential to drastically reduce annotation costs in 3D biomedical image segmentation, where expert labeling of volumetric data is both time-consuming and expensive. Yet, existing AL methods are unable to consistently outperform…
Langue du texte source : anglais
Provide continuous confidence scores throughout LLM text generation via supervised learning and backward confidence integration, enabling real-time uncertainty awareness
Langue du texte source : anglais
Financial agents powered by large language models (LLMs) are increasingly deployed for investment analysis, risk assessment, and automated decision-making, where their abilities to plan, invoke tools, and manipulate mutable state introduce new security risks…
Langue du texte source : anglais
Enable video generation customization via first-frame reuse—treat initial frame as a visual entity buffer storing objects for reuse during generation with just 20-50 examples, requiring minimal architectural change.
Langue du texte source : anglais
Train small models to recover from tool execution errors by treating errors as training signals. Use error simulators to generate recovery examples and fission failed trajectories into multiple recovery attempts.
Langue du texte source : anglais