← all publishers

adu2021

@adu2021 source repo

1228 published skills · page 10 of 13

  1. Webworld · adu2021
    Train autoregressive world models on 1M+ real web interactions for accurate browser state prediction. Enables agent training with 100× more data than prior approaches, achieving GPT-4o comparable performance with format flexibility and cross-domain generalization.
    0 installs
  2. R Horizon Long Horizon Reasoning · adu2021
    Construct multi-step reasoning benchmarks with interdependent problems to evaluate and improve long-horizon reasoning in large reasoning models. Enables evaluation of reasoning depth and breadth beyond single-step tasks.
    0 installs
  3. Robust R1 · adu2021
    Enable MLLMs to handle visually degraded images by explicitly reasoning about degradation types and severity. Trains models to perceive degradation parameters, analyze semantic impact, and reconstruct interpretations while adapting reasoning depth to degradation complexity—achieving robust understanding with interpretable explanations.
    0 installs
  4. Paper2skill Evaluation Infrastructure · adu2021
    Convert dataset and benchmark papers into evaluation infrastructure skills. For datasets: extracts collection protocol, annotation design, quality control. For benchmarks: extracts task definition, metric selection, leaderboard design. Use this skill when extracting skills from Category 2 (Evaluation Infrastructure) papers — ImageNet-style dataset papers, SWE-bench-style benchmark papers, or any paper whose primary contribution is evaluation methodology.
    0 installs
  5. Deep Prune · adu2021
    Reduce redundant tokens in parallel reasoning by 80% while maintaining accuracy via dynamic pruning of equivalent reasoning paths. Trigger: improve efficiency of consensus-based reasoning (multiple CoT generation).
    0 installs
  6. Nemotron 3 · adu2021
    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 while maintaining state-of-the-art reasoning, coding, and tool-use capabilities.
    0 installs
  7. Rise Robot · adu2021
    Enable robot policies to self-improve through imagination using learned dynamics and value models without physical trial-and-error. Compositional world model separates concerns enabling 35-45% performance gains on contact-rich manipulation.
    0 installs
  8. Stable Drl · adu2021
    Fixes training instability in Group Relative Policy Optimization for discrete language models by replacing conditional clipping with strict importance ratio bounds and self-normalized advantages. Prevents gradient spikes and policy collapse.
    0 installs
  9. Code2worlds · adu2021
    Generate physically grounded 4D scenes from natural language through dual-stream architecture separating object detail from scene orchestration. VLM-Motion Critic validates physics parameters iteratively, bridging semantic-physical execution gap.
    0 installs
  10. Steer2adapt · adu2021
    Adapt LLMs efficiently by composing multiple pre-existing semantic steering vectors via Bayesian optimization, balancing adaptation gain and safety without retraining model parameters.
    0 installs
  11. World Cache · adu2021
    Accelerates iterative world model inference by classifying tokens by temporal curvature (predictability) and applying differentiated caching: stable tokens reused, linear tokens extrapolated, chaotic tokens updated. Achieves 3.7x speedup with 98% rollout quality.
    0 installs
  12. Causal Armor · adu2021
    Defend against indirect prompt injection attacks by detecting dominance shifts using leave-one-out attribution, enabling selective sanitization without sacrificing latency or utility.
    0 installs
  13. Himap Travel · adu2021
    Solves long-horizon planning problems with global constraints by decoupling planning into strategic (resource allocation) and tactical (execution) levels. Prevents constraint drift through synchronized state tracking and cooperative bargaining.
    0 installs
  14. Minicpm Sala · adu2021
    Combine sparse attention (25% of layers) and linear attention (75% of layers) via strategic layer placement to handle 1M-token contexts with 75% training cost reduction. Hybrid positional encoding preserves long-range information while maintaining position awareness.
    0 installs
  15. Simko Pass K · adu2021
    Improve pass@K by using asymmetric probability boosting: increase probabilities of top-K correct solutions while penalizing top-1 incorrect predictions. Focus boosting on high-entropy tokens where exploration helps most.
    0 installs
  16. Browser Agent · adu2021
    Build web agents using human-inspired browser actions (scrolling, clicking, typing) operated directly on raw HTML via Playwright. Combine supervised fine-tuning and rejection fine-tuning with explicit memory for strong generalization on web tasks.
    0 installs
  17. Config Agents · adu2021
    Learn optimal configurations for agentic AI systems through hierarchical RL that treats configuration as a query-wise decision problem. Structure policy selects workflows/tools/budgets while prompt policy composes specific instructions, achieving 25% accuracy improvement with 35% cost reduction.
    0 installs
  18. Flash Prefill · adu2021
    Accelerates long-context LLM prefilling by identifying sparse attention patterns without expensive scoring, using block-level approximations and dynamic thresholding. Achieves 27.78x speedup at 256K tokens while maintaining accuracy.
    0 installs
  19. Gtr Turbo Vlm · adu2021
    Eliminate expensive external teacher dependencies in VLM RL training via merged-checkpoint teachers. Uses TIES merging of historical RL checkpoints to create free, stable teacher models for step-level guidance—matching external teacher performance while reducing training time 50% and computational costs 60%.
    0 installs
  20. Lamer Meta Rl · adu2021
    Enable LLM agents to actively explore and adapt policies through meta-RL instead of converging to fixed behaviors. Uses cross-episode training with trajectory-level discounting and in-context policy adaptation via textual reflections—achieving 11-19% improvements in exploration-exploitation balance across interactive environments.
    0 installs
  21. Mai UI Agents · adu2021
    Scale GUI agents to real-world complexity via extended action space (user interaction, tool calls) and device-cloud collaboration. Online RL supports 500+ parallel environments with asynchronous handling; local agent monitors trajectory alignment and handoffs to cloud when drift detected—achieving 41.7% MobileWorld success with privacy-preserving delegation.
    0 installs
  22. Reflexi Coder · adu2021
    Trains LLMs to autonomously debug and improve code through structured RL-optimized reflection cycles. Internalizes debugging process into model weights rather than relying on external oracles or expensive iterative prompting.
    0 installs
  23. Sage Rl Agent · adu2021
    Enable agents to continuously improve by accumulating reusable skills across sequential task chains. Train via GRPO across task sequences where skills persist and compound, provide dual rewards for both task completion and skill generation/reuse—improving completion rates 8.9% while reducing token costs by 59% compared to non-skill baselines.
    0 installs
  24. Self Eval T2i · adu2021
    Train text-to-image models from scratch for any inference step count via self-evaluation mechanism. Model evaluates its own generated samples using current score estimates as dynamic self-teacher, enabling global distribution matching without external teachers—achieving few-step quality equivalent to many-step models at all budgets.
    0 installs
  25. Truncated Ppo · adu2021
    T-PPO improves training efficiency via truncated rollouts and extended GAE, enabling batch continuity without waiting for full sequence completion.
    0 installs
  26. Spatial Boost · adu2021
    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 incorporating dense 3D spatial information. Frozen original parameters prevent catastrophic forgetting; only new channel and mixture weights update. Maintains visual fidelity while enabling precise spatial reasoning (depth, relative positions, distances).
    0 installs
  27. AI Coscientist · adu2021
    Train LLMs to generate high-quality research plans via rubric-based RL without requiring experimental verification. Extracts research goals and domain-specific rubrics from scientific papers, uses frozen model as grader with 12-22% relative improvements, achieves human-expert preference 70% of time with strong cross-domain generalization.
    0 installs
  28. Calm Reasoning · adu2021
    Adapt large reasoning models for optimization tasks using expert-guided hint correction. Generate high-quality training data with minimal expert intervention (<2.6% token modification). Trigger: fine-tune reasoning models on domain-specific tasks without large supervised datasets.
    0 installs
  29. Casa Vl Fusion · adu2021
    Replace token-insertion for fusing vision and language with efficient cross-attention that maintains separate text self-attention. Enables text tokens to attend images within local windows, preserves gist tokens from prior images, and maintains near-constant memory costs for streaming video—more practical than direct token insertion for resource-constrained applications.
    0 installs
  30. Eaglet Planner · adu2021
    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 performance.
    0 installs
  31. Lopa Lookahead · adu2021
    Maximize parallelism in diffusion language models by intelligently exploring token filling orders. Spawn multiple candidate branches predicting high-confidence positions, evaluate all branches in one forward pass, and select the branch enabling most future parallelism—increasing tokens-per-forward-pass 4.4× without accuracy loss.
    0 installs
  32. Nabla Reasoner · adu2021
    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.
    0 installs
  33. Slm Agentic AI · adu2021
    Design heterogeneous agentic systems combining specialized small models with selective large model deployment for superior economics and performance.
    0 installs
  34. State Thoughts · adu2021
    Guide multi-step reasoning through structured action templates that decompose problems into discrete, executable steps. STATe improves exploration efficiency in tree-of-thoughts by constraining action space while maintaining reasoning flexibility.
    0 installs
  35. Va Pi Pixel Ar · adu2021
    Align autoregressive image models with pixel-space quality via variational optimization. Formulates alignment as ELBO combining reconstruction (pixel supervision) and prior regularization (token distribution), treating model as RL policy with tokenizer reconstruction as reward—achieving 86.6% cost reduction vs standard RL fine-tuning.
    0 installs
  36. Agentcpm Report · adu2021
    Enable research agents to interleave evidence-based drafting with reasoning-driven deepening, automatically expanding outlines based on discovered gaps, using trajectory pruning for efficient RL training.
    0 installs
  37. Alignment Waltz · adu2021
    Train safety-aligned agents using collaborative multi-agent RL where conversation and feedback agents improve together. Trigger: reduce overrefusal while maintaining safety on sensitive queries.
    0 installs
  38. Chain Of Agents · adu2021
    Train single models to simulate multi-agent collaboration through distillation from complex multi-agent systems and agentic RL, creating efficient Agent Foundation Models for tool use and web navigation.
    0 installs
  39. Coco Text Image · adu2021
    Generates complex text-heavy and structured images by converting natural language descriptions into executable code that specifies layouts, then renders and refines. Achieves 68% improvement on structured image generation benchmarks.
    0 installs
  40. Deep Search Hmc · adu2021
    Monitor search agent reasoning quality via hierarchical uncertainty detection. Fast consistency checks identify anomalies; slow experience-driven feedback provides corrections. Minimal overhead while catching misalignment.
    0 installs
  41. Nemotron 3 Nano · adu2021
    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 throughput of competitors while maintaining 1M token context support and superior reasoning.
    0 installs
  42. Qwen3 Embedding · adu2021
    Leverages Qwen3 foundation models for text embedding and reranking via multi-stage training combining weakly-supervised pre-training on 150M synthetic pairs with supervised fine-tuning.
    0 installs
  43. Seed Prover 1 5 · adu2021
    Enable LLM agents to incrementally construct formal proofs through strategic tool orchestration rather than one-shot generation. Combines natural language reasoning, sketch translation, and formal verification in an agentic workflow trained via PPO and Rubric RL, achieving competitive performance on undergraduate and graduate proof problems.
    0 installs
  44. Srpo Vla Policy · adu2021
    Train VLA models for robotic manipulation by using the model's own successful trajectories as self-reference for reward—enable progress-based feedback for failed attempts without external rewards or demonstrations.
    0 installs
  45. Swe Rm Verifier · adu2021
    Improve SWE agent RL via execution-free reward models optimized for three metrics beyond TTS: discriminative ability (AUC) and calibration (ECE). Shows TTS alone insufficient—models must distinguish correct/incorrect trajectories and align confidence with actual correctness—improving SWE-Bench Verified by 7-10 points with 30B MoE verifier.
    0 installs
  46. Tour Planner Rl · adu2021
    Implements TourPlanner from arXiv:2601.04698
    0 installs
  47. Vlash Async Vla · adu2021
    Rolls forward robot state using previously generated actions to condition predictions on estimated future states, paired with temporal-offset training augmentation. Achieve 2× speedup and 17.4× latency reduction in vision-language-action models without architectural changes.
    0 installs
  48. Open Researcher · adu2021
    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, analyzable reasoning chains through three primitives: Search (ranked retrieval), Open (full document fetch), Find (intra-document verification).
    0 installs
  49. Video Detective · adu2021
    Enable VLMs to find relevant clips in long videos through sparse observation and graph-based propagation. Iteratively hypothesize promising segments, extract multimodal evidence (captions, OCR, speech), and propagate relevance scores via visual-temporal affinity graph. Jointly model extrinsic relevance (query-to-segment matching) and intrinsic relevance (video internal structure) to infer unobserved segments. Achieves competitive accuracy with significantly fewer tokens than dense sampling.
    0 installs
  50. Bottom Up Policy · adu2021
    Optimize language model policies layer-by-layer rather than monolithically to understand internal reasoning structure. Decompose models into per-layer and per-module policies via residual streams, analyze entropy patterns revealing exploration→convergence phases, and optimize layers sequentially—improving reasoning on math tasks by up to 4.69 points.
    0 installs
  51. Complementary Rl · adu2021
    Improve RL sample efficiency through co-evolution of policy and experience extractor, enabling dynamic experience replay that adapts to the agent's skill level.
    0 installs
  52. Dmtd Multi Token · adu2021
    Generate multiple tokens simultaneously by having late transformer layers directly predict multiple outputs after early layer processing. No auxiliary parameters or verification needed. Achieve up to 2x generation speedup.
    0 installs
  53. Memory As Action · adu2021
    Treat memory management as learnable RL policy actions (delete/insert) rather than fixed mechanisms. Enable models to autonomously decide what to keep, remove, or add to context, reducing average context length by 51% while matching larger models.
    0 installs
  54. Prism Hypothesis · adu2021
    Unify semantic understanding and pixel-level detail in a single representation by decomposing features into frequency bands. Low frequencies encode semantics while high frequencies capture pixels—enabling one tokenizer for both understanding and generation through frequency-based modulation and semantic-wise alignment.
    0 installs
  55. Robo Dopamine Rl · adu2021
    Overcome reward function design challenges via General Reward Model (GRM) for step-wise progress assessment. Uses multi-view observations for occlusion robustness, hop-based progress normalization, Policy-Invariant Reward Shaping—enabling 95% robot task success within 150 interactions with theoretically-grounded dense rewards.
    0 installs
  56. Shape Of Thought · adu2021
    Demonstrate that synthetic CoT traces with incorrect final answers outperform human-written correct solutions for supervised fine-tuning. Distribution proximity between training data and student model's natural output matters more than correctness—validating human traces with model-like distributions improves performance, providing practical guidance for dataset curation.
    0 installs
  57. Smartsnap Agents · adu2021
    Shift agent verification from post-hoc external judgment to proactive in-situ self-evidence curation. Agents generate atomic evidence tuples during execution, guided by 3C principles (Completeness, Conciseness, Creativity), with structured verifier feedback across four dimensions—reducing verification costs and enabling dense learning signals.
    0 installs
  58. Test Time Rl Vlm · adu2021
    Adapt vision-language models at inference without labeled data by generating multiple predictions and rewarding high-frequency outputs. Trigger: improve VLM accuracy on deployment with self-generated supervision signals.
    0 installs
  59. Tool Learning Lm · adu2021
    Prove that tool-augmented learning unboundedly scales factual knowledge recall compared to parameter-constrained memorization, enabling efficient knowledge retrieval via external tools
    0 installs
  60. Web World Models · adu2021
    Bridge deterministic web code and generative LLMs via hybrid world models. State and physics defined by TypeScript code, LLMs generate narrative/aesthetics on top. Uses typed interfaces, deterministic hashing, graceful degradation—enabling scalable interactive environments from travel atlases to fictional worlds without databases.
    0 installs
  61. X Vla Embodiment · adu2021
    Use soft-prompted transformer architecture for multi-robot learning. Add learnable embodiment-specific prompt embeddings to handle different robot types while maintaining single shared backbone. Scale to 0.9B parameters across 6 simulators and 3 real robots.
    0 installs
  62. Omni World Bench · adu2021
    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 plausibility. Identifies the gap between visual fidelity and true interactive state transition modeling.
    0 installs
  63. Confu Speculative · adu2021
    Improves speculative decoding acceptance rates by exposing target model's intermediate reasoning through contemplate tokens. Achieves 8-11% acceptance rate improvement over EAGLE through future-direction guidance without extra forward passes.
    0 installs
  64. Dirl Diffusion Rl · adu2021
    Enable effective RL for diffusion language models via DiPO (unbiased GRPO for dLLMs) and framework optimizations. FlexAttention accelerates blockwise training, LMDeploy optimizes inference, achieving training-inference consistency—improving dLLM math performance to rival larger autoregressive models.
    0 installs
  65. Dpwriter Planning · adu2021
    Implements DPWriter from arXiv:2601.09609
    0 installs
  66. Fast Thinkact Vla · adu2021
    Implements Fast-ThinkAct from arXiv:2601.09708
    0 installs
  67. Finece Confidence · adu2021
    Provide continuous confidence scores throughout LLM text generation via supervised learning and backward confidence integration, enabling real-time uncertainty awareness
    0 installs
  68. Laser Self Reward · adu2021
    Compute reasoning rewards from the model's own next-token probability distribution at solution end. Integrates verification-based feedback into single model without separate evaluator, enabling efficient RL training with minimal overhead.
    0 installs
  69. Long Cot Training · adu2021
    Navigate Long CoT Degradation phenomenon when training small models on extended reasoning, understanding recovery dynamics and implementing strategies to maintain performance.
    0 installs
  70. M3 Bench Tool Use · adu2021
    Design and evaluate multimodal agents for tool use with M3-Bench: assess three interconnected dimensions (multi-modal grounding, multi-hop causality, multi-threaded parallelism) using similarity-bucketed Hungarian alignment for transparent tool call evaluation without LLM judges.
    0 installs
  71. Markovian Thinker · adu2021
    Enable LLMs to scale reasoning length from O(n²) to O(n) by structuring thinking into fixed-size chunks with learnable cross-chunk summaries. Trigger: train reasoning models with unbounded or expensive chain-of-thought sequences.
    0 installs
  72. Qerl Quantization Rl · adu2021
    Combine NFVP4 quantization with LoRA to accelerate RL rollout phases while using quantization noise as implicit exploration bonus. Achieve 1.5x speedup and better strategy discovery through noise-enhanced policy entropy.
    0 installs
  73. R Wom World Model · adu2021
    Ground LLM world models with retrieved current knowledge from tutorials and documentation. Reduce hallucination in environment prediction and improve long-horizon planning by 16-23% on web agent benchmarks.
    0 installs
  74. Reasoning Palette · adu2021
    Overcome token-level randomness limitations in RL by shifting exploration to latent reasoning strategies. Train a VAE encoding diverse reasoning patterns, sample latents during RL, decode to prefix embeddings steering internal reasoning—enabling structured exploration across math, coding, and QA with interpretable, controllable behavior.
    0 installs
  75. Rl Rubric Anchors · adu2021
    Extend RL to open-ended tasks using structured rubrics as reward anchors, enabling fine-grained evaluation of subjective outputs without requiring binary correctness signals.
    0 installs
  76. Scaling Laws Code · adu2021
    Establish language-specific scaling laws for multilingual code pre-training across 7 programming languages (0.2B-14B models, 1T tokens). Show interpreted languages scale better than compiled, synergy gains depend on syntax similarity, and parallel pairing improves translation—enabling proportion-dependent token allocation outperforming uniform distribution.
    0 installs
  77. Semanticgen Video · adu2021
    Accelerate video generation and enable long-video synthesis by decomposing into two diffusion stages: first generate compact semantic features for global planning, then generate VAE latents conditioned on semantics. Includes learnable semantic compression to improve training convergence—enabling minute-long videos with faster convergence than direct VAE modeling.
    0 installs
  78. Step Deepresearch · adu2021
    Enable autonomous AI research systems to move beyond web search toward true research through four composable atomic capabilities: planning/decomposition, deep search/synthesis, reflection/verification, and report generation. Progressive training across 32K→128K context with SFT and RL produces single ReAct agents matching proprietary systems with lower costs.
    0 installs
  79. Green Vla Robotics · adu2021
    Train robot controllers via five-stage curriculum progressing from base vision-language models to embodiment-specific RL-refined policies. Unified action space enables cross-embodiment transfer with minimal performance loss.
    0 installs
  80. Ieap Image Editing · adu2021
    Enable robust image editing by decomposing free-form instructions into sequential atomic operations executed through a neural program interpreter.
    0 installs
  81. Llds Grpo Collapse · adu2021
    Identifies Lazy Likelihood Displacement (LLD) as GRPO failure mechanism in tool-integrated LLMs and proposes lightweight LLDS regularization that penalizes only tokens responsible for likelihood decrease, achieving up to 45.2% performance gains.
    0 installs
  82. Lynx Dynamic Exits · adu2021
    Enable models to stop generating when confident through lightweight hidden-state probes with distributional guarantees. LYNX achieves cross-domain transferability without retraining—ideal when you need confidence-controlled reasoning efficiency.
    0 installs
  83. Memory T1 Temporal · adu2021
    Enable agents to accurately identify temporally relevant information in long multi-session dialogues through RL-based memory retrieval. Combines coarse-to-fine candidate selection with multi-level temporal consistency rewards—providing dense supervision that disambiguates time expressions and maintains coherence across 128k-token contexts.
    0 installs
  84. Mm Helix Reasoning · adu2021
    Train multimodal models for long-chain reflective reasoning (iterative thinking, backtracking) using Adaptive Hybrid Policy Optimization. Trigger: improve VLM performance on tasks requiring iterative refinement and error correction.
    0 installs
  85. Multi Agent Evolve · adu2021
    Enables LLM self-improvement without external verification through multi-agent co-evolution. Proposer generates questions, Solver attempts solutions, Judge evaluates both. All agents evolve together via RL, achieving 4.54% improvement on reasoning benchmarks without human supervision.
    0 installs
  86. Pass At K Training · adu2021
    Use Pass@k as the reward metric in RL training to balance exploration and exploitation, enabling models to learn diverse sampling strategies while maintaining correctness.
    0 installs
  87. Play To Generalize · adu2021
    Develop reasoning capabilities in multimodal models through interactive gameplay rather than supervised learning, achieving superior transfer to diverse reasoning tasks.
    0 installs
  88. Remix Lora Routing · adu2021
    Learn to route requests across multiple LoRA adapters using RL-based router training with constant routing weights. Prevents weight collapse and ensures balanced contribution from all selected adapters during inference.
    0 installs
  89. Self Forcing Video · adu2021
    Address exposure bias in video generation by training on self-generated sequences, achieving 17 FPS real-time performance while matching quality of slower baselines.
    0 installs
  90. Self Rewarding Vlm · adu2021
    Enable VLMs to self-assess visual perception accuracy through decomposed two-stage reasoning: perception generation then validation, eliminating external supervision dependency
    0 installs
  91. Single Matrix Lora · adu2021
    Replace LoRA's two-matrix decomposition with a single learnable matrix (AA⊤) to eliminate scale imbalances and improve training stability. Reduces parameters by ~50% while maintaining or exceeding LoRA performance.
    0 installs
  92. Thinking To Recall · adu2021
    Demonstrates that chain-of-thought reasoning improves LLM factual retrieval through computational buffering and self-priming. Improves single-hop factual accuracy by enabling models to generate contextual bridge facts before recalling answers.
    0 installs
  93. Timebill Inference · adu2021
    Guarantee LLM inference completes within time budgets via response length prediction, execution time estimation, and adaptive KV cache eviction. Three-stage pipeline predicts response length, estimates end-to-end time with 1.22% accuracy, adjusts cache eviction ratio—enabling time-critical deployment in robotics and autonomous systems.
    0 installs
  94. Training Free Grpo · adu2021
    Improve LLM outputs without parameter updates using learned token priors that guide inference. Trigger: optimize agent behavior in deployment without model retraining or fine-tuning.
    0 installs
  95. Yolo Moe Detection · adu2021
    MoE-enhanced YOLOv9-Tiny using lightweight routers to adaptively weight specialized expert outputs at each feature resolution, improving detection quality while maintaining end-to-end differentiability. Deploy for efficient multi-scale object detection with dynamic specialization.
    0 installs
  96. Agent Data Protocol · adu2021
    Standardizes agent training data representation across diverse sources (API use, web browsing, coding, software engineering). Single lightweight protocol unifies 13 datasets enabling 20% performance gains without domain-specific tuning. Enables reproducible agent training and scalable data combination.
    0 installs
  97. Cort Code Reasoning · adu2021
    Enhance reasoning models by integrating executable code within thinking traces, enabling grounded computation verification and reducing hallucination in mathematical and logical reasoning.
    0 installs
  98. Era Embodied Agents · adu2021
    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.
    0 installs
  99. Gui Actor Grounding · adu2021
    Enable GUI agents to ground actions without generating pixel coordinates by using attention-based patch-level alignment and a verifier for selecting optimal action regions from candidates.
    0 installs
  100. Kernelevole Agentic · adu2021
    Automate compute kernel optimization via agentic AI and retrieval-augmented prompting. Unified context-aware transformation function, hardware-specific constraint KB, self-improving state machine exploring kernel variants—achieving 1.25-17× speedups on production recommendation workloads in hours vs weeks of manual effort.
    0 installs