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.
Teach multimodal LLMs to read and understand sheet music through a synthetic QA dataset with kern+ symbolic notation. Enables models to handle music sheet OCR, symbol recognition, and chord estimation at 8× better performance than GPT-4o.
Langue du texte source : anglais
Improves LLM reasoning quality at inference time by optimizing token logits using gradient descent, combining reward model signals with KL-regularization. Bridges parametric training-time and non-parametric test-time scaling through token-level optimization.
Langue du texte source : anglais
Apply training-free negative guidance in diffusion models by extrapolating in attention space with L1-based normalization, restoring suppression of unwanted attributes across architectures and modalities.
Langue du texte source : anglais
Enable LLMs to develop genuine parallel reasoning without external supervision through progressive self-distilled training. Transform models from sequential reasoning to native parallel cognition with 4.6× speedup—ideal when latency and reasoning quality both…
Langue du texte source : anglais
Convert auto-regressive language models to efficient diffusion-based generators through gradual block size increments. NBDiff-7B inherits long-context capabilities from AR predecessors while achieving state-of-the-art parallel generation—ideal when you need…
Langue du texte source : anglais
Efficient agentic reasoning via sparse MoE activating 50% parameters per token. Combines Mamba-Transformer hybrid with 6-of-128 expert routing, three-stage post-training (SFT, verifiable RL, RLHF), and Group Relative Length Control—achieving 3.3× inference…
Langue du texte source : anglais
Build efficient open-source LLMs via hybrid Mamba-Transformer MoE architecture with LatentMoE expert design, multi-token prediction training, FP4 precision, and multi-environment RL post-training—achieving 3.3× higher throughput than equivalently-sized models…
Langue du texte source : anglais
Train language models through sequential, domain-wise RL stages (RLHF → Instruction-Following → Math → Code → SWE) without catastrophic forgetting. Exploit policy-dependent training data distribution where previous behaviors persist when reward-relevant. 14B…
Langue du texte source : anglais
Deploy multiple reasoning model sizes efficiently by embedding nested submodels within a single parent—use end-to-end trained routers to select submodels at inference, achieving 360× cost reduction vs training families separately.
Langue du texte source : anglais
Evolutionary architecture search discovering optimal depth-width ratios and operator combinations under deployment latency constraints using augmented scaling laws. Deploy when you need fastest inference per latency target with mixed attention mechanisms.
Langue du texte source : anglais
Create 7.5M long-form mathematical solution traces with multi-mode supervision (high/medium/low reasoning depths, with/without Python). Integrate 85K competition problems (AoPS) and 262K community questions (StackExchange). Implement sequential bucketing…
Langue du texte source : anglais
Build hybrid Mamba-Transformer models combining efficient Mamba-2 layers with standard attention to achieve 6x higher inference throughput while maintaining reasoning accuracy on long-context tasks.
Langue du texte source : anglais
Train vision transformers through autoregressive next-embedding prediction without pixel reconstruction, tokenizers, or contrastive losses. Apply causal masking and stop-gradient on target embeddings. Achieve 83.8% (ViT-B) and 85.3% (ViT-L) ImageNet-1K…
Langue du texte source : anglais
Scale information-seeking agents via nested architecture separating outer reasoning from inner page exploration. Minimal toolkit (search, visit, click, fill) handles dynamic web interactions, inner loop filters content before context injection, multi-task…
Langue du texte source : anglais
Discover that large pretrained models have dense neighborhoods of task-specific experts—random weight perturbations improve performance. Use RandOpt: sample perturbations, select top performers, ensemble via voting for multi-task adaptation.
Langue du texte source : anglais
Simulate GUI behavior by predicting screen frames in response to user inputs. NeuralOS combines hierarchical RNNs for state tracking with diffusion-based rendering, capturing mouse interactions and application state transitions. Trains on synthetic…
Langue du texte source : anglais
Build unified decoder-only transformers for multimodal tasks using 6 trillion interleaved text-image tokens with next-scale prediction for visual content—enabling fast 1024x1024 image generation (5 seconds), image editing, and video generation while rivaling…
Langue du texte source : anglais
Train a unified autoregressive model to generate images and text by directly handling continuous image tokens with flow matching, eliminating the need for quantization or separate diffusion models.
Langue du texte source : anglais
Open-source foundation model trained for diverse agent interactions across gaming and interactive environments, supporting generalist agent development with robust performance foundations.
Langue du texte source : anglais
Scale distributed LLM training without all-reduce synchronization using dynamic pipeline routing and modified Nesterov momentum, achieving 4% faster convergence than DiLoCo with exponentially lower communication.
Langue du texte source : anglais
Agentic systems have recently become the dominant paradigm for formal theorem proving, achieving strong performance by coordinating multiple models and tools. However, existing approaches often rely on task-specific pipelines and trained formal provers,…
Langue du texte source : anglais
Enable vision-language models to self-correct by synthesizing dense training examples from existing rollouts, creating n² correction pairs from n original trajectories.
Langue du texte source : anglais
Solve IMO-level problems through multi-stage hierarchical reasoning with lemma-based memory compression. Intern-S1-MO achieves 26/35 on IMO2025 geometry-excluded problems—ideal when complex reasoning exceeds single-pass context.
Langue du texte source : anglais
Scale mixture-of-experts models efficiently by decomposing experts into atomic vector pairs with Cartesian product routing and expert-centric scheduling. Achieves 10.9× speedup and 50% fewer parameters versus fine-grained baselines through system-algorithm…
Langue du texte source : anglais
Builds generalist reward models evaluating outputs across 5 modalities (text, image, video, audio, 3D) using free-form preference data. Combines discriminative and generative reward modeling approaches. Covers 9 tasks with 317K preference examples, enabling…
Langue du texte source : anglais
Videos convey richer information than images or text, capturing both spatial and temporal dynamics. However, most existing video customization methods rely on reference images or task-specific temporal priors, failing to fully exploit the rich spatio-temporal…
Langue du texte source : anglais
Compress verbose reasoning by conditioning the same model on a conciseness instruction to create a teacher. Minimize KL divergence between student outputs and concise teacher without ground truth, enabling implicit reward learning that improves accuracy while…
Langue du texte source : anglais
Demonstrate that a single strategically engineered training sample can improve reasoning across multiple domains. Polymath learning shows sample quality and multidisciplinary design matter more than quantity, enabling extreme data efficiency in RL training.
Langue du texte source : anglais
Improve deployed language models by learning from real-world user interactions. Extract transferable knowledge from interaction trajectories and consolidate via on-policy context distillation without needing environment access.
Langue du texte source : anglais
Improve parallel reasoning by explicitly generating diverse outlines before executing solution paths. Overcomes mode collapse where independent samples converge on same (often wrong) answer. Generates unique answers (27.6 vs 23.5) with focused reasoning (10%…
Langue du texte source : anglais
Scales computer-use agent capabilities through reflective Chain-of-Thought reasoning in large-scale annotated datasets spanning multiple operating systems and 200+ applications.
Langue du texte source : anglais
Transfer reasoning behaviors learned in language models to visual domains through two-stage training: cold-start linguistic fine-tuning followed by multimodal RL. Open-Vision-Reasoner achieves 95.3% on MATH500 and 54.6% on MathVerse by learning visual analogs…
Langue du texte source : anglais
Designs terminal-based AI coding agents through workload-specialized model routing, where distinct models handle planning, thinking, critique, and execution tasks. Implements extended ReAct loop with context compaction and approval gates for safe command…
Langue du texte source : anglais
Build agentic systems for transparent, evidence-based novelty analysis of research submissions through four-phase pipelines: contribution extraction, prior work retrieval, hierarchical comparison, and structured reporting with explicit citations—enabling fair…
Langue du texte source : anglais
Comprehensive evaluation dataset for systematic vulnerability testing of language models, enabling identification and mitigation of failure modes before agent deployment.
Langue du texte source : anglais
Enable open-ended mathematical learning through co-evolutionary teacher-student self-play where a single model alternates roles to generate progressively harder problems and solve them, creating a virtuous cycle without external data.
Langue du texte source : anglais
Design data generation pipelines for reasoning models through systematic experimentation with answer sampling, teacher selection, and source quality optimization.
Langue du texte source : anglais
Implements OpenTinker from arXiv:2601.07376
Langue du texte source : anglais
Learn a single visual representation supporting both image understanding and generation by combining VAE-based generative training with contrastive learning objectives. Use when building multimodal systems that need unified image representations for both…
Langue du texte source : anglais
Verify long reasoning chains by combining outcome and process verification through active learning. OPV achieves 83.1 F1 on verification—crucial when both final answers and reasoning paths must be validated with minimal annotation.
Langue du texte source : anglais