← all publishers

adu2021

@adu2021 source repo

1228 published skills · page 12 of 13

  1. Reasoning Core Synthetic Data · adu2021
    Reasoning Core procedurally generates verifiable symbolic reasoning datasets across formal domains (planning, logic, parsing), with external solvers and curriculum control.
    0 installs
  2. Rebalance Efficient Reasoning · adu2021
    Diagnose and correct reasoning inefficiencies (overthinking and underthinking) in large reasoning models using confidence-based steering vectors, without retraining. Enables optimal reasoning budgets across model scales.
    0 installs
  3. REST Stress Testing Reasoning · adu2021
    Evaluate large reasoning models under stress by asking multiple problems simultaneously, revealing true multi-tasking capacity and context management. Use to identify robustness gaps invisible in single-problem evaluations and discriminate model capabilities beyond traditional benchmarks.
    0 installs
  4. Revisual Multimodal Reasoning · adu2021
    Develop sophisticated multimodal reasoning through text-centric cold-start initialization, prioritized advantage distillation, and staged RL refinement.
    0 installs
  5. Rlad Discovering Abstractions · adu2021
    Train LLMs to discover domain-specific abstractions (concise representations of procedural and factual knowledge) through two-player RL. An abstraction generator proposes key insights, a solution generator uses them to solve problems, and both receive RL rewards, learning structured reasoning that transfers to harder problems.
    0 installs
  6. Roboscape Physics World Model · adu2021
    Generate physically plausible robot manipulation videos by jointly learning RGB generation, temporal depth prediction, and keypoint dynamics. Enables training manipulation policies on synthetic data with strong correlation to simulator performance.
    0 installs
  7. Robovip Robot Video Synthesis · adu2021
    Generate synthetic robot manipulation data via diffusion models using visual identity prompting from exemplar images. Improve multi-view temporal coherence and scalability for robot policy training without extensive real-world data collection.
    0 installs
  8. Sched Fast Diffusion Decoding · adu2021
    Accelerate diffusion LLM decoding by halting when confidence stabilizes using progress-dependent thresholds. SchED achieves 3.8-4.0× speedup while retaining 99.8-100% quality—training-free and model-agnostic for any dLLM.
    0 installs
  9. Slime Preference Optimization · adu2021
    Optimize model preferences by decoupling preference learning from generation quality. Explicitly maximize chosen response likelihood while using token-level stabilization to prevent quality degradation from over-suppressing rejected responses.
    0 installs
  10. Smart Search Query Refinement · adu2021
    Improve LLM search agents by optimizing query quality at each step using process-level rewards. Framework teaches agents to iteratively refine search queries through imitation, alignment, and generalization stages. Agents learn to identify low-quality queries and regenerate improved ones, significantly improving search efficiency and answer quality on knowledge-intensive reasoning tasks.
    0 installs
  11. Sparc Vl Perception Reasoning · adu2021
    Improve vision-language model reasoning efficiency by decoupling perception (identifying task-relevant image regions) from reasoning (generating explanations), enabling asymmetric compute allocation. Reduces token overhead while improving accuracy through separate optimization of visual grounding and semantic reasoning stages.
    0 installs
  12. Srpo Multimodal Reflection Rl · adu2021
    Teach multimodal language models to reflect on their reasoning and improve answers through structured RL training.
    0 installs
  13. Swimbird Switchable Reasoning · adu2021
    Enable multimodal models to dynamically switch between text and vision reasoning modes, allocating computation based on perceived difficulty and image resolution, achieving strong performance on both vision-dense and text-heavy benchmarks.
    0 installs
  14. Tabdsr Tabular Reasoning Llms · adu2021
    Improve language model performance on complex numerical reasoning over tables through three-stage pipeline: decompose questions into sub-questions, sanitize and clean table data, then generate executable Python code for precise computation.
    0 installs
  15. Terminator Early Stopping Cot · adu2021
    Learn when to terminate chain-of-thought reasoning by predicting answer arrival patterns. Train an early-exit mechanism on empirical first-answer positions to reduce reasoning length by 14-55% while maintaining or improving accuracy.
    0 installs
  16. Think Router Hybrid Reasoning · adu2021
    Route reasoning between discrete token space (when uncertain) and latent soft embeddings (when confident). Use maximum next-token probability as a routing threshold to dynamically select the reasoning space, improving accuracy under latent reasoning while reducing computational cost through selective discrete sampling.
    0 installs
  17. Tokenbridge Visual Generation · adu2021
    Build autoregressive image generators using post-training quantization that bridges continuous VAE tokens with discrete vocabulary modeling. Achieves state-of-the-art visual quality via dimension-wise token prediction without training instability.
    0 installs
  18. Vespo Variational Sequence Rl · adu2021
    Stabilize off-policy RL training for LLMs by deriving principled importance weight reshaping from variational optimization. Instead of heuristic clamping, VESPO uses closed-form exponential weighting W^c1 * exp(c2*(1-W)) to suppress overweighted samples while maintaining smooth gradients. Enables stable training at 64× policy staleness and under fully asynchronous execution with sequence-level operations that avoid length-dependent biases.
    0 installs
  19. Vision Transformers Registers · adu2021
    Apply test-time register token injection to pre-trained Vision Transformers without retraining, eliminating high-norm outlier artifacts and improving attention map quality.
    0 installs
  20. Visual Reasoning Revisitation · adu2021
    Enable multimodal models to dynamically revisit and re-ground reasoning steps in images using point-and-copy mechanisms for better long-horizon reasoning.
    0 installs
  21. Wide Seek Multi Agent Scaling · adu2021
    Dynamically fork sub-agents at any step based on task requirements instead of using fixed agent counts. Linearize hierarchical trajectories into unified sequences for GRPO training. Demonstrates 6.36x more sub-agents than baselines via learned orchestration.
    0 installs
  22. Wmpo World Model Vla Training · adu2021
    Train Vision-Language-Action models for robotic control through world model simulation without real-world interaction—using pixel-based world models aligned with VLA features to enable self-correction and robust policy optimization.
    0 installs
  23. World Compass Rl World Models · adu2021
    Improve long-horizon world model fidelity using RL with clip-level rollouts and complementary reward functions for action accuracy and visual quality. Breaks computational constraints by evaluating candidate clips incrementally rather than full sequences, enabling efficient multi-objective optimization.
    0 installs
  24. Agent Skills Security Analysis · adu2021
    Empirically analyzes 31,132 agent skills to identify 14 distinct vulnerability patterns, finding 26.1% contain security flaws including data exfiltration, privilege escalation, and malicious intent risks that require mandatory vetting.
    0 installs
  25. Agentic Confidence Calibration · adu2021
    Diagnose and correct overconfidence failures in autonomous agents using Holistic Trajectory Calibration (HTC), analyzing process-level features across entire execution paths. Use when building reliable autonomous systems that need better confidence estimates and reduced overconfidence failures.
    0 installs
  26. Agentscope Developer Framework · adu2021
    Build agentic applications using unified agent interfaces, asynchronous design patterns, ReAct paradigm grounding, and developer-centric evaluation and deployment tools.
    0 installs
  27. Aorchestra Agent Orchestration · adu2021
    Automate sub-agent creation by treating agents as dynamically creatable executors defined by four-tuple abstraction (Instruction, Context, Tools, Model), enabling flexible delegation and cost-aware routing for complex multi-step tasks.
    0 installs
  28. Apd Adaptive Parallel Decoding · adu2021
    Accelerate diffusion language model inference by dynamically adjusting parallel tokens per step using a small auxiliary autoregressive model, achieving substantial throughput gains.
    0 installs
  29. Atom Searcher Agentic Research · adu2021
    Decompose agent reasoning into atomic thoughts guided by curriculum-based reasoning reward models, enabling multi-hop information retrieval and interpretable deep research.
    0 installs
  30. Automind Adaptive Data Science · adu2021
    Build LLM-driven data science agents grounded in empirical knowledge through expert knowledge base, tree search algorithms, and complexity-adaptive code generation, surpassing SOTA by 8% on MLE-Bench.
    0 installs
  31. Blockwise Advantage Estimation · adu2021
    Improve credit assignment in multi-objective RL by decomposing advantages into segment-specific values. Use Outcome-Conditioned Baselines to reduce cross-objective interference without expensive rollouts, enabling better training signals for multi-step completions with different reward functions per segment.
    0 installs
  32. Control R Controllable Scaling · adu2021
    Enable dynamic control over reasoning depth during inference using Reasoning Control Fields that guide long chain-of-thought generation based on execution and quality parameters.
    0 installs
  33. Curriculum Efficient Reasoning · adu2021
    Improves reasoning efficiency through curriculum learning that progressively constrains token budgets, enabling models to first discover solution strategies then distill them into concise traces.
    0 installs
  34. Deep Search Mcts Rlvr Training · adu2021
    Overcome exploration bottlenecks in reasoning RL by integrating Monte Carlo Tree Search during training (not just inference). Global frontier selection and entropy-guided sampling reduce GPU hours by 5.7x while improving performance.
    0 installs
  35. Differential Sequence Modeling · adu2021
    Improve state-space model performance on language modeling and retrieval by applying differential mechanisms to reduce noise in intermediate representations and enhance long-context reasoning.
    0 installs
  36. Every Token Counts 16m Context · adu2021
    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.
    0 installs
  37. Feedback Friction LLM Response · adu2021
    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.
    0 installs
  38. Gdpo Multi Reward Optimization · adu2021
    Optimize language models against multiple reward signals simultaneously by decoupling reward normalization. GDPO prevents reward combination collapse that undermines training signal quality when aligning models to multiple human preferences like accuracy, safety, efficiency, and format compliance.
    0 installs
  39. Gimbaldiffusion Camera Control · adu2021
    Control video camera motion using gravity-aligned absolute coordinates instead of relative trajectories. GimbalDiffusion enables precise camera control with null-pitch conditioning—ideal when you need interpretable, physics-aware camera motion in text-to-video.
    0 installs
  40. Humanomni Multimodal Reasoning · adu2021
    Improve multimodal reasoning by requiring explicit context understanding before reasoning. Use specialized reward mechanisms and context-aware training to prevent information-skipping shortcuts.
    0 installs
  41. I Grpo Self Feedback Reasoning · adu2021
    Improve LLM reasoning through iterative refinement where the model refines its best previous attempts. Two-stage training: exploratory draft generation, then conditioned refinement using GRPO. Dynamic conditioning signals evolve with policy, enabling state-of-the-art math reasoning on AIME (85.62%).
    0 installs
  42. Iot MCP LLM Device Interaction · adu2021
    Connect LLM agents to IoT sensors and microcontrollers through MCP standardization. Use to build monitoring systems and smart home automation where LLMs reason over real-world sensor data.
    0 installs
  43. Lite Attention Temporal Sparse · adu2021
    Accelerate video diffusion generation by exploiting temporal attention sparsity—skip redundant attention tiles across denoising steps using persistent skip masks, achieving 40% speedup with quality retention.
    0 installs
  44. Lk Losses Speculative Decoding · adu2021
    LK Losses replace KL divergence with direct acceptance rate optimization for speculative decoding, achieving 8-10% improvements without computational overhead.
    0 installs
  45. Mimo V2 Flash Technical Report · adu2021
    Research contribution advancing agent and reasoning capabilities through novel approaches to model development, training, and evaluation.
    0 installs
  46. Minimax M1 Lightning Attention · adu2021
    Hybrid-attention MoE reasoning model supporting 1M token context and 80K token generation, combining lightning attention with CISPO RL algorithm for efficient scaling.
    0 installs
  47. Mobile Agent V3 Gui Automation · adu2021
    Build GUI automation agents using self-evolving trajectory generation, trajectory-aware policy optimization, and integrated action semantics for cross-platform interaction.
    0 installs
  48. Multimodal Diffusion Alignment · adu2021
    Improve text-image alignment in diffusion transformers through Temperature-Adjusted Cross-modal Attention (TACA), addressing token imbalance and timestep-dependent weighting with parameter-efficient LoRA fine-tuning.
    0 installs
  49. Multiverse Parallel Generation · adu2021
    Enable native parallel token generation in language models by implementing adaptive task decomposition and merge strategies, achieving 2x speedup with 1.87% performance gains.
    0 installs
  50. Nemotron Flash Latency Optimal · adu2021
    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.
    0 installs
  51. Nepa Next Embedding Prediction · adu2021
    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 accuracy with strong transfer to downstream tasks.
    0 installs
  52. Nextflow Multimodal Generation · adu2021
    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 specialized diffusion models.
    0 installs
  53. Ope Outline Guided Exploration · adu2021
    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% shorter correct paths).
    0 installs
  54. Openvlthinker Vision Reasoning · adu2021
    Train vision-language models for complex reasoning by alternating SFT (supervised fine-tuning via text-only reasoning models) and curriculum RL (Group Relative Policy Optimization). Progressively improve through iterative cycles where each iteration generates better training data.
    0 installs
  55. Partcrafter 3d Mesh Generation · adu2021
    Generates semantically-meaningful 3D parts from single images via compositional diffusion transformers with part-level identity and local-global attention.
    0 installs
  56. Pyramidal Wan Video Efficiency · adu2021
    Convert pretrained video diffusion models into pyramidal architectures via low-cost finetuning while preserving output quality. Explore step distillation for enhanced efficiency, enabling deployment of efficient inference without training from scratch.
    0 installs
  57. Quantized Evolution Strategies · adu2021
    Fine-tune quantized LLMs directly in low-precision discrete parameter space using evolution strategies with accumulated error feedback. Overcome gradient stagnation in quantized models by accumulating fractional updates using Delta-Sigma modulation, achieving significant improvements in INT4 quantized models without full-precision gradients.
    0 installs
  58. R Zero Self Evolving Reasoning · adu2021
    Co-evolutionary framework where Challenger generates tasks and Solver solves them. Models evolve autonomously from scratch without human annotations. Improves math reasoning +6.49pts and general reasoning +7.54pts.
    0 installs
  59. Re Trac Trajectory Compression · adu2021
    Compress search trajectories into structured states capturing partial answers, evidence, and uncertainties. Recursive execution leverages compressed states to avoid redundant exploration, improving resource efficiency by 50%.
    0 installs
  60. Recursive Think Answer Process · adu2021
    Recursive Think-Answer Process enables models to iteratively refine reasoning and answers during inference, reducing self-correction errors and improving accuracy without retraining.
    0 installs
  61. Rl Awb Nighttime White Balance · adu2021
    Correct color distortion in nighttime photos by combining statistical gray-pixel detection with reinforcement learning parameter optimization. Achieves superior cross-camera generalization without extensive labeled nighttime training data through a hybrid architecture that preserves interpretability while gaining adaptive tuning capability.
    0 installs
  62. Sage Retrieval Research Agents · adu2021
    Build effective retrieval systems for deep research agents by understanding query-retriever mismatch, preferring BM25 for keyword-oriented queries, and augmenting corpus documents with metadata and LLM-generated keywords to improve information discovery.
    0 installs
  63. Scaling Behavior Cloning Games · adu2021
    Train video game-playing foundation models discovering that increasing training data and network depth enables learning more causal policies. Release 8300+ hours of gameplay data and open-source models for real-time consumer GPU inference.
    0 installs
  64. Semantic Visual Reconstruction · adu2021
    Add explicit visual supervision to VLMs by training models to autoregressively reconstruct semantic image tokens, achieving 2-3% average gains and 10-point improvements on hallucination robustness.
    0 installs
  65. Silvr Language Video Reasoning · adu2021
    Convert videos to language-based representations and leverage LLM reasoning without video-specific training.
    0 installs
  66. Soft Grpo Soft Thinking Rl Lms · adu2021
    Enable policy gradient optimization on soft LLM tokens by injecting Gumbel noise and applying Gumbel-Softmax reparameterization—allowing soft-thinking patterns to match discrete-token RL performance while maintaining continuous optimization advantages.
    0 installs
  67. Sonicmoe Training Optimization · adu2021
    Optimize MoE training through memory-efficient backward pass, IO-aware kernel design overlapping memory operations, and token rounding routing. Avoid caching large-scale activations, fuse operations with GEMM, implement ping-pong scheduling. Achieve 1.86× compute throughput on Hopper GPUs and 16% higher TFLOPS in sparse configurations.
    0 installs
  68. Sotopia Rl Social Intelligence · adu2021
    Train socially intelligent LLMs via utterance-level credit assignment and multi-dimensional reward aggregation for social interactions.
    0 installs
  69. Sparse Vdit Video Acceleration · adu2021
    Accelerate video diffusion transformer inference by 1.58-1.85× through discovering and exploiting sparse attention patterns that exhibit diagonal, multi-diagonal, and vertical-stripe structures.
    0 installs
  70. Specontext Speculative Caching · adu2021
    Uses distilled language model (DLM) for KV cache token retrieval, reducing layer-wise retrieval parameters by 90% via head-level attention weights, with asynchronous prefetching and elastic CPU offloading. Deploy for ultra-long-context inference with memory constraints.
    0 installs
  71. Spiral Zero Sum Game Reasoning · adu2021
    A self-play framework enabling language models to develop sophisticated reasoning through competitive multi-turn games without human supervision. Achieves 10% improvement on reasoning benchmarks by training models to win against evolving opponents while maintaining interpretable thinking traces.
    0 installs
  72. Stapo Spurious Token Silencing · adu2021
    Stabilize RL training in LLMs by detecting and masking gradient contributions from spurious tokens that comprise 0.01% of output but cause disproportionate instability. Identifies tokens with low probability, low entropy, and positive advantage, then suppresses their gradients during optimization to maintain stable policy entropy and improve reasoning performance by 7%+ across model scales.
    0 installs
  73. Swe World Docker Free Training · adu2021
    Replace Docker environments with learned LLM surrogates comprising a lightweight sandbox for deterministic file operations, a transition model predicting execution feedback, and a reward model acting as virtual test runner. Reduces training infrastructure costs while scaling SWE agent training data.
    0 installs
  74. Test Time Self Improving Video · adu2021
    Generate high-quality videos through iterative test-time refinement: agents critique outputs on visual/audio/context fidelity and a reasoning agent synthesizes feedback to improve prompts across multiple generations.
    0 installs
  75. Tool Integrated Rl Repo Search · adu2021
    Two-stage post-training framework combining rejection-sampled SFT and RL for LLM-guided repository code search and issue localization.
    0 installs
  76. Tool Use Training Multilingual · adu2021
    Enable non-English language models to reliably generate function calls and tool invocations through continued training on bilingual function-calling datasets. Achieves 28% improvement in parsing accuracy while preserving language understanding.
    0 installs
  77. Trajectory Selection Reasoning · adu2021
    Select best reasoning trajectories from multiple samples using step-level scoring from a 0.6B lightweight verifier that exploits hidden states, outperforming external reward models by 4-12% without massive annotations.
    0 installs
  78. Tuna Unified Visual Multimodal · adu2021
    Cascaded VAE+SigLIP encoders creating single continuous representation space supporting both vision understanding and generation, trained jointly on both tasks without format mismatches. Deploy for unified multimodal models where understanding and generation enhance each other.
    0 installs
  79. Verse Craft Video World Models · adu2021
    Control video generation via 4D geometric representation combining static background point clouds and per-object 3D Gaussian trajectories. Enable category-agnostic control over camera and multi-object motion in realistic video synthesis.
    0 installs
  80. Vocabtrim Speculative Decoding · adu2021
    Accelerate speculative decoding by pruning drafter vocabulary to high-frequency tokens. Achieves 16% speedup in memory-bound settings by eliminating unused vocabulary entries without retraining.
    0 installs
  81. Web Coach Self Evolving Agents · adu2021
    Enable web agents to improve over time by curating episodic memory from navigation trajectories and dynamically injecting task-specific guidance at runtime—no retraining required, persistent improvement across sessions.
    0 installs
  82. Weboperator Tree Search Agents · adu2021
    Enable autonomous web agents to navigate partially observable environments through action-aware tree search. Handle destructive actions via snapshot validation, implement speculative backtracking with parallel tabs, and dynamically prioritize actions based on safety and reversibility. Achieves 54.6% success on WebArena.
    0 installs
  83. Additivellm2 Domain Adaptation · adu2021
    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 enable real-time defect identification from manufacturing images.
    0 installs
  84. Geometric Foundation Multiview · adu2021
    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 boundary layer, then deterministically derive deeper features from frozen encoder, resulting in 4.4× faster convergence with superior geometric consistency compared to VAE-based approaches.
    0 installs
  85. Rlvr Update Direction Analysis · adu2021
    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 reweighting techniques.
    0 installs
  86. Worldcache Video Model Caching · adu2021
    Replace zero-order hold assumptions with perception-constrained approximation via four-module caching system: motion-aware skip thresholds, saliency-weighted drift, least-squares blending, and adaptive scheduling. Achieves 2.1–2.3× speedup at 2B scale with 99.4–99.6% quality retention on Cosmos-Predict video generation; apply when optimizing diffusion world model inference under real-time constraints.
    0 installs
  87. Acon Context Compression Agents · adu2021
    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 act as efficient long-context agents.
    0 installs
  88. Adaptive Agent Foundation Model · adu2021
    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.
    0 installs
  89. Arbitrage Advantage Speculation · adu2021
    Route generation dynamically based on relative model advantage for 2× latency reduction in reasoning. Arbitrage learns when draft models excel versus when target models are worthwhile—critical for balancing cost and quality in long reasoning chains.
    0 installs
  90. Balanced Policy Optimization Rl · adu2021
    Stabilize off-policy RL for LLMs using adaptive clipping that dynamically rebalances positive/negative gradients and preserves entropy, improving mathematical reasoning performance vs standard PPO.
    0 installs
  91. Beyondweb Synthetic Pretraining · adu2021
    Generate high-quality synthetic training data that enables 7.7x faster training than web data, with smaller models achieving better performance through strategic content rephasing and data optimization.
    0 installs
  92. Causal Attention Lookahead Keys · adu2021
    Implement CASTLE, a causal attention mechanism that dynamically updates key representations as context expands. Reduces validation loss by 0.006-0.037 across model scales while maintaining O(L²d) training complexity and O(td) decoding speed. Deploy for improved language model perplexity without inference overhead.
    0 installs
  93. Coding Comprehension Evaluation · adu2021
    Evaluate LLM coding capabilities across three dimensions—problem analysis, code implementation, and test validation—to identify specific reasoning gaps and improve model robustness through ensemble approaches.
    0 installs
  94. Crinn Contrastive Rl Ann Search · adu2021
    Optimize approximate nearest neighbor search via contrastive RL, learning to generate efficient code for HNSW graph construction, search, and refinement.
    0 installs
  95. Deep Ignorance Safety Filtering · adu2021
    Enhances model safety by filtering dual-use topics from pretraining data, creating tamper-resistant models robust to adversarial fine-tuning without degrading unrelated capabilities.
    0 installs
  96. Discrete Diffusion Scaling Laws · adu2021
    Reformulate discrete diffusion using signal-to-noise ratio for hybrid masked-uniform noise scheduling. Derive compute-optimal scaling laws through careful hyperparameter tuning, showing uniform diffusion scales more favorably in token-constrained settings than autoregressive models.
    0 installs
  97. Dream2flow Robotic Manipulation · adu2021
    Convert video generation model outputs into executable robotic manipulation by extracting 3D object flow trajectories as an intermediate representation. Enables zero-shot manipulation of diverse object types (rigid, articulated, deformable, granular) without task-specific training. Use when pre-trained video models capture plausible manipulation patterns but need grounding in low-level robot control.
    0 installs
  98. Editthinker Iterative Reasoning · adu2021
    Enable image editors to handle complex instructions through iterative critique and refinement cycles. A multimodal LLM critiques editing results, reasons about improvements, and refines instructions until satisfactory output—ideal for instruction-following challenges in visual editing.
    0 installs
  99. Exgrpo Learning From Experience · adu2021
    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 exploration, achieving 3.5-7.6 point gains over on-policy methods.
    0 installs
  100. Ffacenerf Few Shot Face Editing · adu2021
    Edit 3D faces with flexible mask layouts using only a few training samples. FFaceNeRF employs geometry adapters with feature injection and latent mixing for tri-plane augmentation, enabling rapid NeRF adaptation without fixed segmentation masks. Ideal for personalized medical imaging, creative face editing, and applications requiring user-defined mask control.
    0 installs